sylviaHoch commited on
Commit
bafa4af
·
verified ·
1 Parent(s): a805746

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -1,35 +1,35 @@
1
- *.7z filter=lfs diff=lfs merge=lfs -text
2
- *.arrow filter=lfs diff=lfs merge=lfs -text
3
- *.bin filter=lfs diff=lfs merge=lfs -text
4
- *.bz2 filter=lfs diff=lfs merge=lfs -text
5
- *.ckpt filter=lfs diff=lfs merge=lfs -text
6
- *.ftz filter=lfs diff=lfs merge=lfs -text
7
- *.gz filter=lfs diff=lfs merge=lfs -text
8
- *.h5 filter=lfs diff=lfs merge=lfs -text
9
- *.joblib filter=lfs diff=lfs merge=lfs -text
10
- *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
- *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
- *.model filter=lfs diff=lfs merge=lfs -text
13
- *.msgpack filter=lfs diff=lfs merge=lfs -text
14
- *.npy filter=lfs diff=lfs merge=lfs -text
15
- *.npz filter=lfs diff=lfs merge=lfs -text
16
- *.onnx filter=lfs diff=lfs merge=lfs -text
17
- *.ot filter=lfs diff=lfs merge=lfs -text
18
- *.parquet filter=lfs diff=lfs merge=lfs -text
19
- *.pb filter=lfs diff=lfs merge=lfs -text
20
- *.pickle filter=lfs diff=lfs merge=lfs -text
21
- *.pkl filter=lfs diff=lfs merge=lfs -text
22
- *.pt filter=lfs diff=lfs merge=lfs -text
23
- *.pth filter=lfs diff=lfs merge=lfs -text
24
- *.rar filter=lfs diff=lfs merge=lfs -text
25
- *.safetensors filter=lfs diff=lfs merge=lfs -text
26
- saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
- *.tar.* filter=lfs diff=lfs merge=lfs -text
28
- *.tar filter=lfs diff=lfs merge=lfs -text
29
- *.tflite filter=lfs diff=lfs merge=lfs -text
30
- *.tgz filter=lfs diff=lfs merge=lfs -text
31
- *.wasm filter=lfs diff=lfs merge=lfs -text
32
- *.xz filter=lfs diff=lfs merge=lfs -text
33
- *.zip filter=lfs diff=lfs merge=lfs -text
34
- *.zst filter=lfs diff=lfs merge=lfs -text
35
- *tfevents* filter=lfs diff=lfs merge=lfs -text
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -1,3 +1,159 @@
1
- ---
2
- license: cc-by-nc-sa-4.0
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-sa-4.0
3
+ language:
4
+ - en
5
+ library_name: diffusers
6
+ pipeline_tag: text-to-image
7
+ tags:
8
+ - sar
9
+ - synthetic-aperture-radar
10
+ - remote-sensing
11
+ - stable-diffusion
12
+ - image-generation
13
+ - synthetic-data
14
+ - ship-detection
15
+ - earth-observation
16
+ - sentinel-1
17
+ ---
18
+
19
+ # SAR Stable Diffusion
20
+
21
+ ## Overview
22
+
23
+ Fine-tuned **Stable Diffusion 1.5** backbone for generating synthetic **Sentinel-1 SAR** amplitude images from text prompts.
24
+ Published alongside the paper **"Diffusion-Based SAR Training Data Synthesis Controlled by Spatial Annotations"** (Hochstuhl et al., 2026).
25
+
26
+ The model generates single-channel SAR amplitude images for specific land cover types similar to Sentinel-1 GRD image products (in VH polarization).
27
+
28
+ > For spatially controlled generation via ship/land masks, use this model together with
29
+ > [`sylviaHoch/SAR-ControlNet`](https://huggingface.co/sylviaHoch/SAR-ControlNet).
30
+
31
+ ---
32
+
33
+ ## Database
34
+ The model was fine-tuned on Sentinel-1 acquisitions from the [`SEN12MS dataset`](https://github.com/schmitt-muc/SEN12MS) dataset. The corresponding text prompts were derived from the dataset's land cover maps, using the dominant land cover class within each image patch. Possible land cover classes are:
35
+ - Evergreen Needleleaf Forest
36
+ - Evergreen Broadleaf Forest
37
+ - Deciduous Needleleaf Forest
38
+ - Deciduous Broadleaf Forest
39
+ - Mixed Forest
40
+ - Closed Shrublands
41
+ - Open Shrublands
42
+ - Woody Savannas
43
+ - Savannas
44
+ - Grasslands
45
+ - Permanent Wetlands
46
+ - Croplands
47
+ - Urban and Built-up
48
+ - Cropland/Natural Vegetation Mosaic
49
+ - Snow and Ice
50
+ - Barren or Sparsely Vegetated
51
+ - Water Bodies
52
+
53
+ ---
54
+
55
+ ## Architecture
56
+
57
+ | Component | Details |
58
+ |---|---|
59
+ | Base model | Stable Diffusion 1.5 |
60
+ | VAE decoder | Adapted to **single-channel** output |
61
+ | Text encoder | Fine-tuned with a **LoRA adapter** (`adapter_text_encoder/`) |
62
+ | Output | Single-channel float32 SAR amplitude image |
63
+ ---
64
+
65
+ ## Repository Structure
66
+
67
+ ```text
68
+ SAR-StableDiffusion/
69
+ ├── model_index.json
70
+ ├── unet/
71
+ ├── vae/ # Modified: single-channel conv_out
72
+ ├── text_encoder/
73
+ ├── tokenizer/
74
+ ├── scheduler/
75
+ ├── feature_extractor/
76
+ └── adapter_text_encoder/ # LoRA adapter for text encoder
77
+ ├── adapter_config.json
78
+ └── adapter_model.safetensors
79
+ ```
80
+
81
+ ---
82
+
83
+ ## Usage
84
+ This model can be used directly with the 🤗 [diffusers](https://github.com/huggingface/diffusers) pipeline.
85
+ The LoRA adapter for the text encoder is included in this repository and must be loaded manually after initialising the pipeline.
86
+
87
+ **Requirements:**
88
+ - `torch` (CUDA recommended)
89
+ - `diffusers`
90
+ - `peft`
91
+
92
+ ### Text-to-Image Generation
93
+
94
+ ```python
95
+ import torch
96
+ from diffusers import StableDiffusionPipeline
97
+ from peft import PeftModel
98
+
99
+ MODEL_ID = "sylviaHoch/SAR-StableDiffusion"
100
+
101
+ # Load pipeline
102
+ pipeline = StableDiffusionPipeline.from_pretrained(
103
+ MODEL_ID,
104
+ torch_dtype=torch.float16
105
+ ).to("cuda")
106
+
107
+ # Load LoRA text-encoder adapter
108
+ pipeline.text_encoder = PeftModel.from_pretrained(
109
+ pipeline.text_encoder,
110
+ MODEL_ID,
111
+ subfolder="adapter_text_encoder"
112
+ )
113
+
114
+ # Generate
115
+ image = pipeline(
116
+ "Woody Savannas.",
117
+ num_inference_steps=50,
118
+ guidance_scale=3.0,
119
+ output_type="pt"
120
+ ).images
121
+
122
+ ```
123
+
124
+ >image is a torch.Tensor of shape (N, C, H, W) with values in the range [0, 1] and dtype float32, where N is the batch size (here 1), C the number of channels (here 1, grayscale), and H and W the native model resolution (512 x 512).
125
+ ---
126
+
127
+ ## Intended Use
128
+
129
+ - Synthetic SAR data generation for given land cover types.
130
+ - Research on generative models for remote sensing.
131
+
132
+ ## Limitations
133
+
134
+ - Tuned specifically to **Sentinel-1** sensor characteristics based on GRD products in VH polarization; transferability to other sensors and imaging properties is very limited.
135
+ - Generated images are synthetic and may not fully capture all real SAR image properties.
136
+
137
+ ---
138
+
139
+ ## Citation
140
+
141
+ If you use this model, please cite:
142
+
143
+ ```bibtex
144
+ @inproceedings{sar_diffusion_gcpr2026,
145
+ title = {Diffusion-Based SAR Training Data Synthesis Controlled by Spatial Annotations},
146
+ booktitle = {German Conference on Pattern Recognition (GCPR)},
147
+ year = {2026},
148
+ note = {accepted, to be published},
149
+ authors = {}
150
+ }
151
+ ```
152
+
153
+ ---
154
+
155
+ ## License
156
+
157
+ This model is released under **CC BY-NC-SA 4.0**.
158
+ Commercial use is not permitted. Derivatives must be shared under the same license.
159
+ See [LICENSE](https://creativecommons.org/licenses/by-nc-sa/4.0/) for details.
adapter_text_encoder/adapter_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": {
4
+ "base_model_class": "CLIPTextModel",
5
+ "parent_library": "transformers.models.clip.modeling_clip"
6
+ },
7
+ "base_model_name_or_path": "sd-legacy/stable-diffusion-v1-5",
8
+ "bias": "none",
9
+ "corda_config": null,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 16,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.05,
22
+ "megatron_config": null,
23
+ "megatron_core": "megatron.core",
24
+ "modules_to_save": null,
25
+ "peft_type": "LORA",
26
+ "qalora_group_size": 16,
27
+ "r": 8,
28
+ "rank_pattern": {},
29
+ "revision": null,
30
+ "target_modules": [
31
+ "v_proj",
32
+ "q_proj",
33
+ "k_proj",
34
+ "out_proj",
35
+ "text_projection"
36
+ ],
37
+ "target_parameters": null,
38
+ "task_type": null,
39
+ "trainable_token_indices": null,
40
+ "use_dora": false,
41
+ "use_qalora": false,
42
+ "use_rslora": false
43
+ }
adapter_text_encoder/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afc44128aa35a09b5cc8cdf12d61bd0adf2bf6fd0f2c8fa27ee53ad580b8d396
3
+ size 2373040
feature_extractor/preprocessor_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": {
3
+ "height": 224,
4
+ "width": 224
5
+ },
6
+ "do_center_crop": true,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_rescale": true,
10
+ "do_resize": true,
11
+ "image_mean": [
12
+ 0.48145466,
13
+ 0.4578275,
14
+ 0.40821073
15
+ ],
16
+ "image_processor_type": "CLIPImageProcessor",
17
+ "image_std": [
18
+ 0.26862954,
19
+ 0.26130258,
20
+ 0.27577711
21
+ ],
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "shortest_edge": 224
26
+ }
27
+ }
model_index.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "StableDiffusionPipeline",
3
+ "_diffusers_version": "0.36.0.dev0",
4
+ "_name_or_path": "sd-legacy/stable-diffusion-v1-5",
5
+ "feature_extractor": [
6
+ "transformers",
7
+ "CLIPImageProcessor"
8
+ ],
9
+ "image_encoder": [
10
+ null,
11
+ null
12
+ ],
13
+ "requires_safety_checker": true,
14
+ "safety_checker": [
15
+ "stable_diffusion",
16
+ "StableDiffusionSafetyChecker"
17
+ ],
18
+ "scheduler": [
19
+ "diffusers",
20
+ "PNDMScheduler"
21
+ ],
22
+ "text_encoder": [
23
+ "transformers",
24
+ "CLIPTextModel"
25
+ ],
26
+ "tokenizer": [
27
+ "transformers",
28
+ "CLIPTokenizer"
29
+ ],
30
+ "unet": [
31
+ "diffusers",
32
+ "UNet2DConditionModel"
33
+ ],
34
+ "vae": [
35
+ "diffusers",
36
+ "AutoencoderKL"
37
+ ]
38
+ }
safety_checker/config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "StableDiffusionSafetyChecker"
4
+ ],
5
+ "dtype": "float32",
6
+ "initializer_factor": 1.0,
7
+ "logit_scale_init_value": 2.6592,
8
+ "model_type": "clip",
9
+ "projection_dim": 768,
10
+ "text_config": {
11
+ "attention_dropout": 0.0,
12
+ "dropout": 0.0,
13
+ "dtype": "float32",
14
+ "hidden_act": "quick_gelu",
15
+ "hidden_size": 768,
16
+ "initializer_factor": 1.0,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "layer_norm_eps": 1e-05,
20
+ "max_position_embeddings": 77,
21
+ "model_type": "clip_text_model",
22
+ "num_attention_heads": 12,
23
+ "num_hidden_layers": 12,
24
+ "projection_dim": 512,
25
+ "vocab_size": 49408
26
+ },
27
+ "transformers_version": "4.57.1",
28
+ "vision_config": {
29
+ "attention_dropout": 0.0,
30
+ "dropout": 0.0,
31
+ "dtype": "float32",
32
+ "hidden_act": "quick_gelu",
33
+ "hidden_size": 1024,
34
+ "image_size": 224,
35
+ "initializer_factor": 1.0,
36
+ "initializer_range": 0.02,
37
+ "intermediate_size": 4096,
38
+ "layer_norm_eps": 1e-05,
39
+ "model_type": "clip_vision_model",
40
+ "num_attention_heads": 16,
41
+ "num_channels": 3,
42
+ "num_hidden_layers": 24,
43
+ "patch_size": 14,
44
+ "projection_dim": 512
45
+ }
46
+ }
safety_checker/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb351a5ded815c3ff744968ad9c6b218d071b9d313d04f35e813b84b4c0ffde8
3
+ size 1215979664
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "PNDMScheduler",
3
+ "_diffusers_version": "0.36.0.dev0",
4
+ "beta_end": 0.012,
5
+ "beta_schedule": "scaled_linear",
6
+ "beta_start": 0.00085,
7
+ "clip_sample": false,
8
+ "num_train_timesteps": 1000,
9
+ "prediction_type": "epsilon",
10
+ "set_alpha_to_one": false,
11
+ "skip_prk_steps": true,
12
+ "steps_offset": 1,
13
+ "timestep_spacing": "leading",
14
+ "trained_betas": null
15
+ }
text_encoder/config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "CLIPTextModel"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 0,
7
+ "dropout": 0.0,
8
+ "dtype": "float32",
9
+ "eos_token_id": 2,
10
+ "hidden_act": "quick_gelu",
11
+ "hidden_size": 768,
12
+ "initializer_factor": 1.0,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 77,
17
+ "model_type": "clip_text_model",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
20
+ "pad_token_id": 1,
21
+ "projection_dim": 768,
22
+ "transformers_version": "4.57.1",
23
+ "vocab_size": 49408
24
+ }
text_encoder/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:778d02eb9e707c3fbaae0b67b79ea0d1399b52e624fb634f2f19375ae7c047c3
3
+ size 492265168
tokenizer/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|startoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "49406": {
5
+ "content": "<|startoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "49407": {
13
+ "content": "<|endoftext|>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ }
20
+ },
21
+ "bos_token": "<|startoftext|>",
22
+ "clean_up_tokenization_spaces": false,
23
+ "do_lower_case": true,
24
+ "eos_token": "<|endoftext|>",
25
+ "errors": "replace",
26
+ "extra_special_tokens": {},
27
+ "model_max_length": 77,
28
+ "pad_token": "<|endoftext|>",
29
+ "tokenizer_class": "CLIPTokenizer",
30
+ "unk_token": "<|endoftext|>"
31
+ }
tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
unet/config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.36.0.dev0",
4
+ "_name_or_path": "D:/schmis/genai4sar/sd_models/sd_model_unet_sen12_VH\\checkpoint-10000",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": null,
7
+ "addition_embed_type_num_heads": 64,
8
+ "addition_time_embed_dim": null,
9
+ "attention_head_dim": 8,
10
+ "attention_type": "default",
11
+ "block_out_channels": [
12
+ 320,
13
+ 640,
14
+ 1280,
15
+ 1280
16
+ ],
17
+ "center_input_sample": false,
18
+ "class_embed_type": null,
19
+ "class_embeddings_concat": false,
20
+ "conv_in_kernel": 3,
21
+ "conv_out_kernel": 3,
22
+ "cross_attention_dim": 768,
23
+ "cross_attention_norm": null,
24
+ "down_block_types": [
25
+ "CrossAttnDownBlock2D",
26
+ "CrossAttnDownBlock2D",
27
+ "CrossAttnDownBlock2D",
28
+ "DownBlock2D"
29
+ ],
30
+ "downsample_padding": 1,
31
+ "dropout": 0.0,
32
+ "dual_cross_attention": false,
33
+ "encoder_hid_dim": null,
34
+ "encoder_hid_dim_type": null,
35
+ "flip_sin_to_cos": true,
36
+ "freq_shift": 0,
37
+ "in_channels": 4,
38
+ "layers_per_block": 2,
39
+ "mid_block_only_cross_attention": null,
40
+ "mid_block_scale_factor": 1,
41
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
42
+ "norm_eps": 1e-05,
43
+ "norm_num_groups": 32,
44
+ "num_attention_heads": null,
45
+ "num_class_embeds": null,
46
+ "only_cross_attention": false,
47
+ "out_channels": 4,
48
+ "projection_class_embeddings_input_dim": null,
49
+ "resnet_out_scale_factor": 1.0,
50
+ "resnet_skip_time_act": false,
51
+ "resnet_time_scale_shift": "default",
52
+ "reverse_transformer_layers_per_block": null,
53
+ "sample_size": 64,
54
+ "time_cond_proj_dim": null,
55
+ "time_embedding_act_fn": null,
56
+ "time_embedding_dim": null,
57
+ "time_embedding_type": "positional",
58
+ "timestep_post_act": null,
59
+ "transformer_layers_per_block": 1,
60
+ "up_block_types": [
61
+ "UpBlock2D",
62
+ "CrossAttnUpBlock2D",
63
+ "CrossAttnUpBlock2D",
64
+ "CrossAttnUpBlock2D"
65
+ ],
66
+ "upcast_attention": false,
67
+ "use_linear_projection": false
68
+ }
unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acf12b6141d01721571baed215acaf106bdc0f549dbbfd69eec0abdb0955a7a7
3
+ size 3438167536
vae/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.36.0.dev0",
4
+ "_name_or_path": "sd-legacy/stable-diffusion-v1-5",
5
+ "act_fn": "silu",
6
+ "block_out_channels": [
7
+ 128,
8
+ 256,
9
+ 512,
10
+ 512
11
+ ],
12
+ "down_block_types": [
13
+ "DownEncoderBlock2D",
14
+ "DownEncoderBlock2D",
15
+ "DownEncoderBlock2D",
16
+ "DownEncoderBlock2D"
17
+ ],
18
+ "force_upcast": true,
19
+ "in_channels": 1,
20
+ "latent_channels": 4,
21
+ "latents_mean": null,
22
+ "latents_std": null,
23
+ "layers_per_block": 2,
24
+ "mid_block_add_attention": true,
25
+ "norm_num_groups": 32,
26
+ "out_channels": 1,
27
+ "sample_size": 512,
28
+ "scaling_factor": 0.18215,
29
+ "shift_factor": null,
30
+ "up_block_types": [
31
+ "UpDecoderBlock2D",
32
+ "UpDecoderBlock2D",
33
+ "UpDecoderBlock2D",
34
+ "UpDecoderBlock2D"
35
+ ],
36
+ "use_post_quant_conv": true,
37
+ "use_quant_conv": true
38
+ }
vae/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fbf15248903bbbff01bf584eabe2ebbf1297c3529fb5aa1042195548efd9b58
3
+ size 334624828