Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,34 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+samples/1758843894746__000000000_0.jpg filter=lfs diff=lfs merge=lfs -text
+samples/1758844017427__000000000_1.jpg filter=lfs diff=lfs merge=lfs -text
+samples/1758845231301__000000250_0.jpg filter=lfs diff=lfs merge=lfs -text
+samples/1758845357677__000000250_1.jpg filter=lfs diff=lfs merge=lfs -text
+samples/1758846565751__000000500_0.jpg filter=lfs diff=lfs merge=lfs -text
+samples/1758846692407__000000500_1.jpg filter=lfs diff=lfs merge=lfs -text
+samples/1758847901716__000000750_0.jpg filter=lfs diff=lfs merge=lfs -text
+samples/1758848028069__000000750_1.jpg filter=lfs diff=lfs merge=lfs -text
+samples/1758849236074__000001000_0.jpg filter=lfs diff=lfs merge=lfs -text
+samples/1758849362296__000001000_1.jpg filter=lfs diff=lfs merge=lfs -text
+samples/1758849488430__000001000_2.jpg filter=lfs diff=lfs merge=lfs -text
+samples/1758850570560__000001250_0.jpg filter=lfs diff=lfs merge=lfs -text
+samples/1758850696962__000001250_1.jpg filter=lfs diff=lfs merge=lfs -text
+samples/1758851904671__000001500_0.jpg filter=lfs diff=lfs merge=lfs -text
+samples/1758852030870__000001500_1.jpg filter=lfs diff=lfs merge=lfs -text
+samples/1758853239252__000001750_0.jpg filter=lfs diff=lfs merge=lfs -text
+samples/1758853365704__000001750_1.jpg filter=lfs diff=lfs merge=lfs -text
+samples/1758854574518__000002000_0.jpg filter=lfs diff=lfs merge=lfs -text
+samples/1758854700459__000002000_1.jpg filter=lfs diff=lfs merge=lfs -text
+samples/1758855910203__000002250_0.jpg filter=lfs diff=lfs merge=lfs -text
+samples/1758856036364__000002250_1.jpg filter=lfs diff=lfs merge=lfs -text
+samples/1758857245953__000002500_0.jpg filter=lfs diff=lfs merge=lfs -text
+samples/1758857372128__000002500_1.jpg filter=lfs diff=lfs merge=lfs -text
+samples/1758858583467__000002750_0.jpg filter=lfs diff=lfs merge=lfs -text
+samples/1758858709776__000002750_1.jpg filter=lfs diff=lfs merge=lfs -text
+samples/1758859930728__000003000_0.jpg filter=lfs diff=lfs merge=lfs -text
+samples/1758860056799__000003000_1.jpg filter=lfs diff=lfs merge=lfs -text
+samples/1758861269184__000003250_0.jpg filter=lfs diff=lfs merge=lfs -text
+samples/1758861395260__000003250_1.jpg filter=lfs diff=lfs merge=lfs -text
+samples/1758862582214__000003500_0.jpg filter=lfs diff=lfs merge=lfs -text
+samples/1758862708072__000003500_1.jpg filter=lfs diff=lfs merge=lfs -text

.job_config.json

@@ -0,0 +1,133 @@
+{
+  "job": "extension",
+  "config": {
+    "name": "wan_dewa",
+    "process": [
+      {
+        "type": "diffusion_trainer",
+        "training_folder": "/app/ai-toolkit/output",
+        "sqlite_db_path": "/app/ai-toolkit/aitk_db.db",
+        "device": "cuda",
+        "trigger_word": null,
+        "performance_log_every": 10,
+        "network": {
+          "type": "lora",
+          "linear": 16,
+          "linear_alpha": 16,
+          "conv": 16,
+          "conv_alpha": 16,
+          "lokr_full_rank": true,
+          "lokr_factor": -1,
+          "network_kwargs": {
+            "ignore_if_contains": []
+          }
+        },
+        "save": {
+          "dtype": "bf16",
+          "save_every": 250,
+          "max_step_saves_to_keep": 10,
+          "save_format": "diffusers",
+          "push_to_hub": false
+        },
+        "datasets": [
+          {
+            "folder_path": "/app/ai-toolkit/datasets/d3w4",
+            "mask_path": null,
+            "mask_min_value": 0.1,
+            "default_caption": "",
+            "caption_ext": "txt",
+            "caption_dropout_rate": 0.05,
+            "cache_latents_to_disk": false,
+            "is_reg": false,
+            "network_weight": 1,
+            "resolution": [
+              512
+            ],
+            "controls": [],
+            "shrink_video_to_frames": true,
+            "num_frames": 1,
+            "do_i2v": true,
+            "flip_x": false,
+            "flip_y": false
+          }
+        ],
+        "train": {
+          "batch_size": 1,
+          "bypass_guidance_embedding": false,
+          "steps": 3500,
+          "gradient_accumulation": 1,
+          "train_unet": true,
+          "train_text_encoder": false,
+          "gradient_checkpointing": true,
+          "noise_scheduler": "flowmatch",
+          "optimizer": "adamw8bit",
+          "timestep_type": "sigmoid",
+          "content_or_style": "balanced",
+          "optimizer_params": {
+            "weight_decay": 0.0001
+          },
+          "unload_text_encoder": false,
+          "cache_text_embeddings": true,
+          "lr": 0.0002,
+          "ema_config": {
+            "use_ema": false,
+            "ema_decay": 0.99
+          },
+          "skip_first_sample": false,
+          "force_first_sample": false,
+          "disable_sampling": false,
+          "dtype": "bf16",
+          "diff_output_preservation": false,
+          "diff_output_preservation_multiplier": 1,
+          "diff_output_preservation_class": "person",
+          "switch_boundary_every": 10,
+          "loss_type": "mse"
+        },
+        "model": {
+          "name_or_path": "ai-toolkit/Wan2.2-T2V-A14B-Diffusers-bf16",
+          "quantize": true,
+          "qtype": "uint4|ostris/accuracy_recovery_adapters/wan22_14b_t2i_torchao_uint4.safetensors",
+          "quantize_te": true,
+          "qtype_te": "qfloat8",
+          "arch": "wan22_14b:t2v",
+          "low_vram": true,
+          "model_kwargs": {
+            "train_high_noise": true,
+            "train_low_noise": true
+          }
+        },
+        "sample": {
+          "sampler": "flowmatch",
+          "sample_every": 250,
+          "width": 1024,
+          "height": 1024,
+          "samples": [
+            {
+              "prompt": "A man named D3W4 , playing chess at the park, bomb going off in the background"
+            },
+            {
+              "prompt": "A man named D3W4 holding a coffee cup, in a beanie, sitting at a cafe"
+            },
+            {
+              "prompt": "A man named D3W4 playing the guitar, on stage, singing a song, laser lights, punk rocker"
+            },
+            {
+              "prompt": "photo of a man named D3W4, white background, medium shot, modeling clothing, studio lighting, white backdrop"
+            }
+          ],
+          "neg": "",
+          "seed": 42,
+          "walk_seed": true,
+          "guidance_scale": 4,
+          "sample_steps": 25,
+          "num_frames": 1,
+          "fps": 1
+        }
+      }
+    ]
+  },
+  "meta": {
+    "name": "[name]",
+    "version": "1.0"
+  }
+}

config.yaml

@@ -0,0 +1,107 @@
+job: extension
+config:
+  name: wan_dewa
+  process:
+  - type: diffusion_trainer
+    training_folder: /app/ai-toolkit/output
+    sqlite_db_path: /app/ai-toolkit/aitk_db.db
+    device: cuda
+    trigger_word: null
+    performance_log_every: 10
+    network:
+      type: lora
+      linear: 16
+      linear_alpha: 16
+      conv: 16
+      conv_alpha: 16
+      lokr_full_rank: true
+      lokr_factor: -1
+      network_kwargs:
+        ignore_if_contains: []
+    save:
+      dtype: bf16
+      save_every: 250
+      max_step_saves_to_keep: 10
+      save_format: diffusers
+      push_to_hub: false
+    datasets:
+    - folder_path: /app/ai-toolkit/datasets/d3w4
+      mask_path: null
+      mask_min_value: 0.1
+      default_caption: ''
+      caption_ext: txt
+      caption_dropout_rate: 0.05
+      cache_latents_to_disk: false
+      is_reg: false
+      network_weight: 1
+      resolution:
+      - 512
+      controls: []
+      shrink_video_to_frames: true
+      num_frames: 1
+      do_i2v: true
+      flip_x: false
+      flip_y: false
+    train:
+      batch_size: 1
+      bypass_guidance_embedding: false
+      steps: 3500
+      gradient_accumulation: 1
+      train_unet: true
+      train_text_encoder: false
+      gradient_checkpointing: true
+      noise_scheduler: flowmatch
+      optimizer: adamw8bit
+      timestep_type: sigmoid
+      content_or_style: balanced
+      optimizer_params:
+        weight_decay: 0.0001
+      unload_text_encoder: false
+      cache_text_embeddings: true
+      lr: 0.0002
+      ema_config:
+        use_ema: false
+        ema_decay: 0.99
+      skip_first_sample: false
+      force_first_sample: false
+      disable_sampling: false
+      dtype: bf16
+      diff_output_preservation: false
+      diff_output_preservation_multiplier: 1
+      diff_output_preservation_class: person
+      switch_boundary_every: 10
+      loss_type: mse
+    model:
+      name_or_path: ai-toolkit/Wan2.2-T2V-A14B-Diffusers-bf16
+      quantize: true
+      qtype: uint4|ostris/accuracy_recovery_adapters/wan22_14b_t2i_torchao_uint4.safetensors
+      quantize_te: true
+      qtype_te: qfloat8
+      arch: wan22_14b:t2v
+      low_vram: true
+      model_kwargs:
+        train_high_noise: true
+        train_low_noise: true
+    sample:
+      sampler: flowmatch
+      sample_every: 250
+      width: 1024
+      height: 1024
+      samples:
+      - prompt: A man named D3W4 , playing chess at the park, bomb going off in the
+          background
+      - prompt: A man named D3W4 holding a coffee cup, in a beanie, sitting at a cafe
+      - prompt: A man named D3W4 playing the guitar, on stage, singing a song, laser
+          lights, punk rocker
+      - prompt: photo of a man named D3W4, white background, medium shot, modeling
+          clothing, studio lighting, white backdrop
+      neg: ''
+      seed: 42
+      walk_seed: true
+      guidance_scale: 4
+      sample_steps: 25
+      num_frames: 1
+      fps: 1
+meta:
+  name: wan_dewa
+  version: '1.0'

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1c3b55d488dc09f5ecc3ccd8761feddd1020396e084eade40279ba068be305d
+size 313383269