Upload folder using huggingface_hub

.gitattributes

@@ -282,3 +282,4 @@ body_previews/frontbody[[:space:]](7)_step004261_t0.83_bp0.0142.jpg filter=lfs d
 body_previews/frontbody[[:space:]](7)_step004757_t0.88_bp0.0100.jpg filter=lfs diff=lfs merge=lfs -text
 body_previews/frontbody[[:space:]](7)_step004915_t0.95_bp0.0442.jpg filter=lfs diff=lfs merge=lfs -text
 body_previews/frontbody[[:space:]](7)_step005157_t0.97_bp0.0563.jpg filter=lfs diff=lfs merge=lfs -text
+krea2-all-finetune/loss_log.db filter=lfs diff=lfs merge=lfs -text

krea2-all-finetune/.job_config.json

@@ -0,0 +1,210 @@
+{
+  "job": "extension",
+  "config": {
+    "name": "krea2-all-finetune",
+    "process": [
+      {
+        "type": "diffusion_trainer",
+        "training_folder": "/workspace/ai-toolkit/output",
+        "sqlite_db_path": "/workspace/ai-toolkit/aitk_db.db",
+        "device": "cuda",
+        "trigger_word": null,
+        "performance_log_every": 10,
+        "save": {
+          "dtype": "bf16",
+          "save_every": 250,
+          "max_step_saves_to_keep": 40000,
+          "save_format": "diffusers",
+          "push_to_hub": false
+        },
+        "datasets": [
+          {
+            "folder_path": "/workspace/ai-toolkit/datasets/a",
+            "mask_path": null,
+            "mask_min_value": 0.1,
+            "default_caption": "",
+            "caption_ext": "txt",
+            "caption_dropout_rate": 0,
+            "cache_latents_to_disk": true,
+            "is_reg": false,
+            "network_weight": 1,
+            "resolution": [
+              1024
+            ],
+            "controls": [],
+            "shrink_video_to_frames": true,
+            "num_frames": 1,
+            "flip_x": false,
+            "flip_y": false,
+            "num_repeats": 3
+          },
+          {
+            "folder_path": "/workspace/ai-toolkit/datasets/n",
+            "mask_path": null,
+            "mask_min_value": 0.1,
+            "default_caption": "",
+            "caption_ext": "txt",
+            "caption_dropout_rate": 0,
+            "cache_latents_to_disk": true,
+            "is_reg": false,
+            "network_weight": 1,
+            "resolution": [
+              1024
+            ],
+            "controls": [],
+            "shrink_video_to_frames": true,
+            "num_frames": 1,
+            "flip_x": false,
+            "flip_y": false,
+            "num_repeats": 1
+          },
+          {
+            "folder_path": "/workspace/ai-toolkit/datasets/j",
+            "mask_path": null,
+            "mask_min_value": 0.1,
+            "default_caption": "",
+            "caption_ext": "txt",
+            "caption_dropout_rate": 0,
+            "cache_latents_to_disk": true,
+            "is_reg": false,
+            "network_weight": 1,
+            "resolution": [
+              1024
+            ],
+            "controls": [],
+            "shrink_video_to_frames": true,
+            "num_frames": 1,
+            "flip_x": false,
+            "flip_y": false,
+            "num_repeats": 9
+          },
+          {
+            "folder_path": "/workspace/ai-toolkit/datasets/all",
+            "mask_path": null,
+            "mask_min_value": 0.1,
+            "default_caption": "",
+            "caption_ext": "txt",
+            "caption_dropout_rate": 0,
+            "cache_latents_to_disk": true,
+            "is_reg": false,
+            "network_weight": 1,
+            "resolution": [
+              1024
+            ],
+            "controls": [],
+            "shrink_video_to_frames": true,
+            "num_frames": 1,
+            "flip_x": false,
+            "flip_y": false,
+            "num_repeats": 1
+          }
+        ],
+        "train": {
+          "batch_size": 1,
+          "bypass_guidance_embedding": false,
+          "steps": 10000,
+          "gradient_accumulation": 1,
+          "train_unet": true,
+          "train_text_encoder": false,
+          "gradient_checkpointing": true,
+          "noise_scheduler": "flowmatch",
+          "optimizer": "automagic3",
+          "timestep_type": "sigmoid",
+          "content_or_style": "balanced",
+          "optimizer_params": {
+            "weight_decay": 0.0001,
+            "min_lr": 1e-7,
+            "max_lr": 0.00003,
+            "polarity_history": 8,
+            "fused": true
+          },
+          "unload_text_encoder": false,
+          "cache_text_embeddings": true,
+          "lr": 0.000001,
+          "ema_config": {
+            "use_ema": false,
+            "ema_decay": 0.99
+          },
+          "skip_first_sample": false,
+          "force_first_sample": false,
+          "disable_sampling": true,
+          "dtype": "bf16",
+          "diff_output_preservation": false,
+          "diff_output_preservation_multiplier": 1,
+          "diff_output_preservation_class": "person",
+          "switch_boundary_every": 1,
+          "loss_type": "mse"
+        },
+        "logging": {
+          "log_every": 1,
+          "use_ui_logger": true
+        },
+        "model": {
+          "name_or_path": "krea/Krea-2-Raw",
+          "quantize": false,
+          "qtype": "qfloat8",
+          "quantize_te": false,
+          "qtype_te": "qfloat8",
+          "arch": "krea2",
+          "low_vram": false,
+          "model_kwargs": {},
+          "compile": true,
+          "layer_offloading": false,
+          "layer_offloading_text_encoder_percent": 1,
+          "layer_offloading_transformer_percent": 1,
+          "block_compile": true
+        },
+        "sample": {
+          "sampler": "flowmatch",
+          "sample_every": 250,
+          "sample_start_step": 0,
+          "width": 1024,
+          "height": 1024,
+          "samples": [
+            {
+              "prompt": "woman with red hair, playing chess at the park, bomb going off in the background"
+            },
+            {
+              "prompt": "a woman holding a coffee cup, in a beanie, sitting at a cafe"
+            },
+            {
+              "prompt": "a horse is a DJ at a night club, fish eye lens, smoke machine, lazer lights, holding a martini"
+            },
+            {
+              "prompt": "a man showing off his cool new t shirt at the beach, a shark is jumping out of the water in the background"
+            },
+            {
+              "prompt": "a bear building a log cabin in the snow covered mountains"
+            },
+            {
+              "prompt": "woman playing the guitar, on stage, singing a song, laser lights, punk rocker"
+            },
+            {
+              "prompt": "hipster man with a beard, building a chair, in a wood shop"
+            },
+            {
+              "prompt": "photo of a man, white background, medium shot, modeling clothing, studio lighting, white backdrop"
+            },
+            {
+              "prompt": "a man holding a sign that says, 'this is a sign'"
+            },
+            {
+              "prompt": "a bulldog, in a post apocalyptic world, with a shotgun, in a leather jacket, in a desert, with a motorcycle"
+            }
+          ],
+          "neg": "",
+          "seed": 42,
+          "walk_seed": true,
+          "guidance_scale": 4,
+          "sample_steps": 30,
+          "num_frames": 1,
+          "fps": 1
+        }
+      }
+    ]
+  },
+  "meta": {
+    "name": "[name]",
+    "version": "1.0"
+  }
+}

krea2-all-finetune/config.yaml

@@ -0,0 +1,168 @@
+job: extension
+config:
+  name: krea2-all-finetune
+  process:
+  - type: diffusion_trainer
+    training_folder: /workspace/ai-toolkit/output
+    sqlite_db_path: /workspace/ai-toolkit/aitk_db.db
+    device: cuda
+    trigger_word: null
+    performance_log_every: 10
+    save:
+      dtype: bf16
+      save_every: 250
+      max_step_saves_to_keep: 40000
+      save_format: diffusers
+      push_to_hub: false
+    datasets:
+    - folder_path: /workspace/ai-toolkit/datasets/a
+      mask_path: null
+      mask_min_value: 0.1
+      default_caption: ''
+      caption_ext: txt
+      caption_dropout_rate: 0
+      cache_latents_to_disk: true
+      is_reg: false
+      network_weight: 1
+      resolution:
+      - 1024
+      controls: []
+      shrink_video_to_frames: true
+      num_frames: 1
+      flip_x: false
+      flip_y: false
+      num_repeats: 3
+    - folder_path: /workspace/ai-toolkit/datasets/n
+      mask_path: null
+      mask_min_value: 0.1
+      default_caption: ''
+      caption_ext: txt
+      caption_dropout_rate: 0
+      cache_latents_to_disk: true
+      is_reg: false
+      network_weight: 1
+      resolution:
+      - 1024
+      controls: []
+      shrink_video_to_frames: true
+      num_frames: 1
+      flip_x: false
+      flip_y: false
+      num_repeats: 1
+    - folder_path: /workspace/ai-toolkit/datasets/j
+      mask_path: null
+      mask_min_value: 0.1
+      default_caption: ''
+      caption_ext: txt
+      caption_dropout_rate: 0
+      cache_latents_to_disk: true
+      is_reg: false
+      network_weight: 1
+      resolution:
+      - 1024
+      controls: []
+      shrink_video_to_frames: true
+      num_frames: 1
+      flip_x: false
+      flip_y: false
+      num_repeats: 9
+    - folder_path: /workspace/ai-toolkit/datasets/all
+      mask_path: null
+      mask_min_value: 0.1
+      default_caption: ''
+      caption_ext: txt
+      caption_dropout_rate: 0
+      cache_latents_to_disk: true
+      is_reg: false
+      network_weight: 1
+      resolution:
+      - 1024
+      controls: []
+      shrink_video_to_frames: true
+      num_frames: 1
+      flip_x: false
+      flip_y: false
+      num_repeats: 1
+    train:
+      batch_size: 1
+      bypass_guidance_embedding: false
+      steps: 10000
+      gradient_accumulation: 1
+      train_unet: true
+      train_text_encoder: false
+      gradient_checkpointing: true
+      noise_scheduler: flowmatch
+      optimizer: automagic3
+      timestep_type: sigmoid
+      content_or_style: balanced
+      optimizer_params:
+        weight_decay: 0.0001
+        min_lr: 1.0e-07
+        max_lr: 3.0e-05
+        polarity_history: 8
+        fused: true
+      unload_text_encoder: false
+      cache_text_embeddings: true
+      lr: 1.0e-06
+      ema_config:
+        use_ema: false
+        ema_decay: 0.99
+      skip_first_sample: false
+      force_first_sample: false
+      disable_sampling: true
+      dtype: bf16
+      diff_output_preservation: false
+      diff_output_preservation_multiplier: 1
+      diff_output_preservation_class: person
+      switch_boundary_every: 1
+      loss_type: mse
+    logging:
+      log_every: 1
+      use_ui_logger: true
+    model:
+      name_or_path: krea/Krea-2-Raw
+      quantize: false
+      qtype: qfloat8
+      quantize_te: false
+      qtype_te: qfloat8
+      arch: krea2
+      low_vram: false
+      model_kwargs: {}
+      compile: true
+      layer_offloading: false
+      layer_offloading_text_encoder_percent: 1
+      layer_offloading_transformer_percent: 1
+      block_compile: true
+    sample:
+      sampler: flowmatch
+      sample_every: 250
+      sample_start_step: 0
+      width: 1024
+      height: 1024
+      samples:
+      - prompt: woman with red hair, playing chess at the park, bomb going off in
+          the background
+      - prompt: a woman holding a coffee cup, in a beanie, sitting at a cafe
+      - prompt: a horse is a DJ at a night club, fish eye lens, smoke machine, lazer
+          lights, holding a martini
+      - prompt: a man showing off his cool new t shirt at the beach, a shark is jumping
+          out of the water in the background
+      - prompt: a bear building a log cabin in the snow covered mountains
+      - prompt: woman playing the guitar, on stage, singing a song, laser lights,
+          punk rocker
+      - prompt: hipster man with a beard, building a chair, in a wood shop
+      - prompt: photo of a man, white background, medium shot, modeling clothing,
+          studio lighting, white backdrop
+      - prompt: a man holding a sign that says, 'this is a sign'
+      - prompt: a bulldog, in a post apocalyptic world, with a shotgun, in a leather
+          jacket, in a desert, with a motorcycle
+      neg: ''
+      seed: 42
+      walk_seed: true
+      guidance_scale: 4
+      sample_steps: 30
+      num_frames: 1
+      fps: 1
+meta:
+  name: krea2-all-finetune
+  version: '1.0'

krea2-all-finetune/krea2-all-finetune_000000250.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e90260e6507228a09bcd7ecf9b3b63da2ef0fefe81842e11980a8f52523b21b7
+size 25640195048

krea2-all-finetune/krea2-all-finetune_000000500.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d04066d5c83fc018cacab3778f10e2f7d7f1d0ea56a9e75823074c76121caee7
+size 25640195048

krea2-all-finetune/krea2-all-finetune_000000750.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce4f5bd864d403a95b4bf231fc7863936c13af2a4aeeda5351a1f731ca5a3b19
+size 25640195048

krea2-all-finetune/krea2-all-finetune_000001000.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d5f80db8d8ac08138590f7432610ccf119b425ccd1a55be1dc1140c31c69a35
+size 25640195048

krea2-all-finetune/krea2-all-finetune_000001250.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f379059ea96f23110b8c8b831928a685d44a2bb7086dc30fb97f8d81be4384b7
+size 25640195048

krea2-all-finetune/krea2-all-finetune_000001500.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ccbaa132031694edb1d89ef7de67cc360ce76772794fa2dc14c08b0285d6368
+size 25640195048

krea2-all-finetune/krea2-all-finetune_000001750.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84f6049fb0f1200e7a580ecc97b434ae17c79cedf8433b721eb4df45f7964b39
+size 25640195048

krea2-all-finetune/krea2-all-finetune_000002000.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:926c57ff2cc67937f2dee1742eb834029872275ac2f856d5ab2cfd7db9cb2d4d
+size 25640195048

krea2-all-finetune/krea2-all-finetune_000002250.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04ba05f288e32441f8281ab4043c592e82461bff86b5e088bd55dc20be89ad04
+size 25640195048

krea2-all-finetune/krea2-all-finetune_000002500.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93488a1ff0be9b3038b1a5dd4aa0126417b1db3be2a63e2741421c221694f496
+size 25640195048

krea2-all-finetune/krea2-all-finetune_000002750.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8539ba37cc08dc999131eff84dfd1b53fc41097d5b29ef56e386bb2bfb1e30ae
+size 25640195048

krea2-all-finetune/krea2-all-finetune_000003000.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be425ac44688b0b42510d5bfb63f997da04ce8f241174604717fe1d98dfff2ba
+size 25640195048

krea2-all-finetune/krea2-all-finetune_000003250.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:899580fa2758cf58b35e05f2a16feae8ec7533b97571f725428ed629705bc679
+size 25640195048

krea2-all-finetune/krea2-all-finetune_000003500.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74df5811c879089fc8a835937e9b34a19a7fadf484f3754bcd8cb7eccbc9add5
+size 25640195048

krea2-all-finetune/krea2-all-finetune_000003750.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6a0c375bff3a51405522e70afef57a29141e59306a525074b5ee4731cbf9701
+size 25640195048

krea2-all-finetune/krea2-all-finetune_000004000.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d79a3cafd633302efa391e7883be294b75a44dce6d801caae99939f6879ca79
+size 25640195048

krea2-all-finetune/krea2-all-finetune_000004250.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6e89ed70e0a27e286db3d251b7e5b5853357166cc4061bdc26342a667194873
+size 25640195048

krea2-all-finetune/krea2-all-finetune_000004500.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:275148b86c333321abecb0fb3d15399f3f8886991f341cd5312e16f9d26384ca
+size 25640195048

krea2-all-finetune/loss_log.db

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04790de984ca777dd64d2dd6468361a0903a455e3b2f8aa38f7b06261210f5cc
+size 860160

krea2-all-finetune/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e975bacedc1c40445417012d1d67e3e3ef2a7d2bf294412bf838d151d40fb4f
+size 12830840614

krea2-all-finetune/pid.txt

@@ -0,0 +1 @@
+1501