Eliahu commited on
Commit
485aa82
Β·
verified Β·
1 Parent(s): c3c8f84

Add model cards for train (batch 22)

Browse files
Files changed (50) hide show
  1. train/model_idx_1050/README.md +40 -0
  2. train/model_idx_1051/README.md +40 -0
  3. train/model_idx_1052/README.md +40 -0
  4. train/model_idx_1053/README.md +40 -0
  5. train/model_idx_1054/README.md +40 -0
  6. train/model_idx_1055/README.md +40 -0
  7. train/model_idx_1056/README.md +40 -0
  8. train/model_idx_1057/README.md +40 -0
  9. train/model_idx_1058/README.md +40 -0
  10. train/model_idx_1059/README.md +40 -0
  11. train/model_idx_1060/README.md +40 -0
  12. train/model_idx_1061/README.md +40 -0
  13. train/model_idx_1062/README.md +40 -0
  14. train/model_idx_1063/README.md +40 -0
  15. train/model_idx_1064/README.md +40 -0
  16. train/model_idx_1065/README.md +40 -0
  17. train/model_idx_1066/README.md +40 -0
  18. train/model_idx_1067/README.md +40 -0
  19. train/model_idx_1068/README.md +40 -0
  20. train/model_idx_1069/README.md +40 -0
  21. train/model_idx_1070/README.md +40 -0
  22. train/model_idx_1071/README.md +40 -0
  23. train/model_idx_1072/README.md +40 -0
  24. train/model_idx_1073/README.md +40 -0
  25. train/model_idx_1074/README.md +40 -0
  26. train/model_idx_1075/README.md +40 -0
  27. train/model_idx_1076/README.md +40 -0
  28. train/model_idx_1077/README.md +40 -0
  29. train/model_idx_1078/README.md +40 -0
  30. train/model_idx_1079/README.md +40 -0
  31. train/model_idx_1080/README.md +40 -0
  32. train/model_idx_1081/README.md +40 -0
  33. train/model_idx_1082/README.md +40 -0
  34. train/model_idx_1083/README.md +40 -0
  35. train/model_idx_1084/README.md +40 -0
  36. train/model_idx_1085/README.md +40 -0
  37. train/model_idx_1086/README.md +40 -0
  38. train/model_idx_1087/README.md +40 -0
  39. train/model_idx_1088/README.md +40 -0
  40. train/model_idx_1089/README.md +40 -0
  41. train/model_idx_1090/README.md +40 -0
  42. train/model_idx_1091/README.md +40 -0
  43. train/model_idx_1092/README.md +40 -0
  44. train/model_idx_1093/README.md +40 -0
  45. train/model_idx_1094/README.md +40 -0
  46. train/model_idx_1095/README.md +40 -0
  47. train/model_idx_1096/README.md +40 -0
  48. train/model_idx_1097/README.md +40 -0
  49. train/model_idx_1098/README.md +40 -0
  50. train/model_idx_1099/README.md +40 -0
train/model_idx_1050/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-2
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_1050
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-2` |
30
+ | **ImageNet Class** | banana (n07753592) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 3e-05 |
37
+ | Max Train Steps | 500 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 25 |
40
+ | N Training Samples | 7 |
train/model_idx_1051/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-3
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_1051
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-3` |
30
+ | **ImageNet Class** | handkerchief (n03485794) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 7e-05 |
37
+ | Max Train Steps | 550 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 82 |
40
+ | N Training Samples | 5 |
train/model_idx_1052/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-4
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_1052
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-4` |
30
+ | **ImageNet Class** | yurt (n04613696) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 3e-05 |
37
+ | Max Train Steps | 600 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 93 |
40
+ | N Training Samples | 10 |
train/model_idx_1053/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-3
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_1053
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-3` |
30
+ | **ImageNet Class** | gazelle (n02423022) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 3e-05 |
37
+ | Max Train Steps | 450 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 24 |
40
+ | N Training Samples | 9 |
train/model_idx_1054/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-2
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_1054
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-2` |
30
+ | **ImageNet Class** | cuirass (n03146219) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 5e-05 |
37
+ | Max Train Steps | 500 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 73 |
40
+ | N Training Samples | 6 |
train/model_idx_1055/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-3
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_1055
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-3` |
30
+ | **ImageNet Class** | cannon (n02950826) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 9e-05 |
37
+ | Max Train Steps | 550 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 86 |
40
+ | N Training Samples | 10 |
train/model_idx_1056/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-3
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_1056
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-3` |
30
+ | **ImageNet Class** | tusker (n01871265) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 3e-05 |
37
+ | Max Train Steps | 600 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 86 |
40
+ | N Training Samples | 9 |
train/model_idx_1057/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_1057
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
30
+ | **ImageNet Class** | lifeboat (n03662601) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 7e-05 |
37
+ | Max Train Steps | 600 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 43 |
40
+ | N Training Samples | 5 |
train/model_idx_1058/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-3
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_1058
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-3` |
30
+ | **ImageNet Class** | snowmobile (n04252077) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 0.0001 |
37
+ | Max Train Steps | 500 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 88 |
40
+ | N Training Samples | 10 |
train/model_idx_1059/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-2
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_1059
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-2` |
30
+ | **ImageNet Class** | Japanese_spaniel (n02085782) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 7e-05 |
37
+ | Max Train Steps | 550 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 50 |
40
+ | N Training Samples | 8 |
train/model_idx_1060/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-2
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_1060
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-2` |
30
+ | **ImageNet Class** | worm_fence (n04604644) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 0.0003 |
37
+ | Max Train Steps | 550 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 37 |
40
+ | N Training Samples | 5 |
train/model_idx_1061/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-2
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_1061
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-2` |
30
+ | **ImageNet Class** | cocker_spaniel (n02102318) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 9e-05 |
37
+ | Max Train Steps | 550 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 56 |
40
+ | N Training Samples | 9 |
train/model_idx_1062/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-3
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_1062
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-3` |
30
+ | **ImageNet Class** | Mexican_hairless (n02113978) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 5e-05 |
37
+ | Max Train Steps | 450 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 42 |
40
+ | N Training Samples | 7 |
train/model_idx_1063/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-2
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_1063
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-2` |
30
+ | **ImageNet Class** | American_egret (n02009912) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 0.0003 |
37
+ | Max Train Steps | 500 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 0 |
40
+ | N Training Samples | 5 |
train/model_idx_1064/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_1064
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
30
+ | **ImageNet Class** | cairn (n02096177) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 9e-05 |
37
+ | Max Train Steps | 450 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 66 |
40
+ | N Training Samples | 5 |
train/model_idx_1065/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_1065
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
30
+ | **ImageNet Class** | limousine (n03670208) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 0.0003 |
37
+ | Max Train Steps | 700 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 47 |
40
+ | N Training Samples | 7 |
train/model_idx_1066/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-4
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_1066
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-4` |
30
+ | **ImageNet Class** | reflex_camera (n04069434) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 3e-05 |
37
+ | Max Train Steps | 600 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 91 |
40
+ | N Training Samples | 9 |
train/model_idx_1067/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_1067
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
30
+ | **ImageNet Class** | lynx (n02127052) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 0.0005 |
37
+ | Max Train Steps | 500 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 84 |
40
+ | N Training Samples | 7 |
train/model_idx_1068/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-3
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_1068
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-3` |
30
+ | **ImageNet Class** | armadillo (n02454379) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 7e-05 |
37
+ | Max Train Steps | 550 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 8 |
40
+ | N Training Samples | 10 |
train/model_idx_1069/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_1069
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
30
+ | **ImageNet Class** | scale (n04141975) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 3e-05 |
37
+ | Max Train Steps | 500 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 50 |
40
+ | N Training Samples | 6 |
train/model_idx_1070/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-3
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_1070
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-3` |
30
+ | **ImageNet Class** | hartebeest (n02422106) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 0.0001 |
37
+ | Max Train Steps | 700 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 32 |
40
+ | N Training Samples | 9 |
train/model_idx_1071/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-3
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_1071
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-3` |
30
+ | **ImageNet Class** | junco (n01534433) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 0.0003 |
37
+ | Max Train Steps | 450 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 28 |
40
+ | N Training Samples | 6 |
train/model_idx_1072/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-4
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_1072
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-4` |
30
+ | **ImageNet Class** | stone_wall (n04326547) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 5e-05 |
37
+ | Max Train Steps | 500 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 16 |
40
+ | N Training Samples | 10 |
train/model_idx_1073/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_1073
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
30
+ | **ImageNet Class** | thatch (n04417672) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 5e-05 |
37
+ | Max Train Steps | 600 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 20 |
40
+ | N Training Samples | 7 |
train/model_idx_1074/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_1074
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
30
+ | **ImageNet Class** | cornet (n03110669) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 7e-05 |
37
+ | Max Train Steps | 700 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 39 |
40
+ | N Training Samples | 8 |
train/model_idx_1075/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_1075
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
30
+ | **ImageNet Class** | binoculars (n02841315) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 7e-05 |
37
+ | Max Train Steps | 450 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 10 |
40
+ | N Training Samples | 6 |
train/model_idx_1076/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-2
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_1076
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-2` |
30
+ | **ImageNet Class** | web_site (n06359193) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 0.0001 |
37
+ | Max Train Steps | 650 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 3 |
40
+ | N Training Samples | 5 |
train/model_idx_1077/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-3
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_1077
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-3` |
30
+ | **ImageNet Class** | loggerhead (n01664065) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 0.0001 |
37
+ | Max Train Steps | 450 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 68 |
40
+ | N Training Samples | 10 |
train/model_idx_1078/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-3
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_1078
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-3` |
30
+ | **ImageNet Class** | Band_Aid (n02786058) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 0.0003 |
37
+ | Max Train Steps | 500 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 97 |
40
+ | N Training Samples | 6 |
train/model_idx_1079/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-3
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_1079
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-3` |
30
+ | **ImageNet Class** | wooden_spoon (n04597913) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 0.0005 |
37
+ | Max Train Steps | 500 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 16 |
40
+ | N Training Samples | 8 |
train/model_idx_1080/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-3
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_1080
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-3` |
30
+ | **ImageNet Class** | black_widow (n01774384) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 0.0001 |
37
+ | Max Train Steps | 550 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 77 |
40
+ | N Training Samples | 9 |
train/model_idx_1081/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-2
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_1081
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-2` |
30
+ | **ImageNet Class** | rhinoceros_beetle (n02174001) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 0.0003 |
37
+ | Max Train Steps | 500 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 67 |
40
+ | N Training Samples | 8 |
train/model_idx_1082/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-3
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_1082
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-3` |
30
+ | **ImageNet Class** | English_springer (n02102040) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 0.0005 |
37
+ | Max Train Steps | 600 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 26 |
40
+ | N Training Samples | 8 |
train/model_idx_1083/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-3
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_1083
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-3` |
30
+ | **ImageNet Class** | Norfolk_terrier (n02094114) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 3e-05 |
37
+ | Max Train Steps | 500 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 54 |
40
+ | N Training Samples | 8 |
train/model_idx_1084/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-4
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_1084
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-4` |
30
+ | **ImageNet Class** | hand-held_computer (n03485407) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 0.0003 |
37
+ | Max Train Steps | 600 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 47 |
40
+ | N Training Samples | 10 |
train/model_idx_1085/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-4
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_1085
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-4` |
30
+ | **ImageNet Class** | snorkel (n04251144) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 3e-05 |
37
+ | Max Train Steps | 450 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 44 |
40
+ | N Training Samples | 6 |
train/model_idx_1086/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_1086
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
30
+ | **ImageNet Class** | coral_reef (n09256479) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 0.0003 |
37
+ | Max Train Steps | 550 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 15 |
40
+ | N Training Samples | 6 |
train/model_idx_1087/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-2
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_1087
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-2` |
30
+ | **ImageNet Class** | lawn_mower (n03649909) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 7e-05 |
37
+ | Max Train Steps | 650 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 32 |
40
+ | N Training Samples | 6 |
train/model_idx_1088/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-3
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_1088
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-3` |
30
+ | **ImageNet Class** | hourglass (n03544143) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 7e-05 |
37
+ | Max Train Steps | 600 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 60 |
40
+ | N Training Samples | 6 |
train/model_idx_1089/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-3
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_1089
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-3` |
30
+ | **ImageNet Class** | power_drill (n03995372) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 9e-05 |
37
+ | Max Train Steps | 650 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 53 |
40
+ | N Training Samples | 5 |
train/model_idx_1090/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-4
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_1090
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-4` |
30
+ | **ImageNet Class** | brain_coral (n01917289) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 7e-05 |
37
+ | Max Train Steps | 650 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 32 |
40
+ | N Training Samples | 10 |
train/model_idx_1091/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-4
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_1091
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-4` |
30
+ | **ImageNet Class** | shower_curtain (n04209239) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 0.0005 |
37
+ | Max Train Steps | 700 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 80 |
40
+ | N Training Samples | 5 |
train/model_idx_1092/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-4
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_1092
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-4` |
30
+ | **ImageNet Class** | gas_pump (n03425413) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 7e-05 |
37
+ | Max Train Steps | 450 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 16 |
40
+ | N Training Samples | 5 |
train/model_idx_1093/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-2
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_1093
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-2` |
30
+ | **ImageNet Class** | sea_anemone (n01914609) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 5e-05 |
37
+ | Max Train Steps | 450 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 21 |
40
+ | N Training Samples | 5 |
train/model_idx_1094/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_1094
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
30
+ | **ImageNet Class** | monarch (n02279972) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 5e-05 |
37
+ | Max Train Steps | 700 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 50 |
40
+ | N Training Samples | 9 |
train/model_idx_1095/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_1095
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
30
+ | **ImageNet Class** | custard_apple (n07760859) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 5e-05 |
37
+ | Max Train Steps | 500 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 1 |
40
+ | N Training Samples | 9 |
train/model_idx_1096/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-3
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_1096
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-3` |
30
+ | **ImageNet Class** | yellow_lady's_slipper (n12057211) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 0.0001 |
37
+ | Max Train Steps | 600 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 66 |
40
+ | N Training Samples | 5 |
train/model_idx_1097/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-4
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_1097
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-4` |
30
+ | **ImageNet Class** | cleaver (n03041632) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 5e-05 |
37
+ | Max Train Steps | 600 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 49 |
40
+ | N Training Samples | 5 |
train/model_idx_1098/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-3
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_1098
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-3` |
30
+ | **ImageNet Class** | barbershop (n02791270) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 5e-05 |
37
+ | Max Train Steps | 700 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 29 |
40
+ | N Training Samples | 8 |
train/model_idx_1099/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-4
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_1099
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-4` |
30
+ | **ImageNet Class** | desktop_computer (n03180011) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 3e-05 |
37
+ | Max Train Steps | 700 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 77 |
40
+ | N Training Samples | 9 |