Upload folder using huggingface_hub

.ipynb_checkpoints/config-checkpoint.yaml

@@ -0,0 +1,105 @@
+job: extension
+config:
+  name: anha_22dts
+  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
+    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: 330
+      max_step_saves_to_keep: 8
+      save_format: diffusers
+      push_to_hub: false
+    datasets:
+    - folder_path: /workspace/ai-toolkit/datasets/anha
+      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
+      - 768
+      - 1024
+      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: 3300
+      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: false
+      lr: 0.0001
+      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: 1
+      loss_type: mse
+    model:
+      name_or_path: ai-toolkit/Wan2.2-T2V-A14B-Diffusers-bf16
+      quantize: true
+      qtype: qfloat8
+      quantize_te: true
+      qtype_te: qfloat8
+      arch: wan22_14b:t2v
+      low_vram: true
+      model_kwargs:
+        train_high_noise: true
+        train_low_noise: false
+      layer_offloading: false
+      layer_offloading_text_encoder_percent: 1
+      layer_offloading_transformer_percent: 1
+    sample:
+      sampler: flowmatch
+      sample_every: 250
+      width: 1024
+      height: 1024
+      samples: []
+      neg: ''
+      seed: 42
+      walk_seed: true
+      guidance_scale: 4
+      sample_steps: 25
+      num_frames: 1
+      fps: 16
+meta:
+  name: anha_22dts
+  version: '1.0'

.job_config.json

@@ -0,0 +1,125 @@
+{
+  "job": "extension",
+  "config": {
+    "name": "anha_22dts",
+    "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,
+        "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": 330,
+          "max_step_saves_to_keep": 8,
+          "save_format": "diffusers",
+          "push_to_hub": false
+        },
+        "datasets": [
+          {
+            "folder_path": "/workspace/ai-toolkit/datasets/anha",
+            "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,
+              768,
+              1024
+            ],
+            "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": 3300,
+          "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": false,
+          "lr": 0.0001,
+          "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": 1,
+          "loss_type": "mse"
+        },
+        "model": {
+          "name_or_path": "ai-toolkit/Wan2.2-T2V-A14B-Diffusers-bf16",
+          "quantize": true,
+          "qtype": "qfloat8",
+          "quantize_te": true,
+          "qtype_te": "qfloat8",
+          "arch": "wan22_14b:t2v",
+          "low_vram": true,
+          "model_kwargs": {
+            "train_high_noise": true,
+            "train_low_noise": false
+          },
+          "layer_offloading": false,
+          "layer_offloading_text_encoder_percent": 1,
+          "layer_offloading_transformer_percent": 1
+        },
+        "sample": {
+          "sampler": "flowmatch",
+          "sample_every": 250,
+          "width": 1024,
+          "height": 1024,
+          "samples": [],
+          "neg": "",
+          "seed": 42,
+          "walk_seed": true,
+          "guidance_scale": 4,
+          "sample_steps": 25,
+          "num_frames": 1,
+          "fps": 16
+        }
+      }
+    ]
+  },
+  "meta": {
+    "name": "[name]",
+    "version": "1.0"
+  }
+}

anha_22dts_000001980_high_noise.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1602e9fec45a4fb15da6045b6695507af39789443a0d9c8ad02d62868314af1d
+size 153453544

anha_22dts_000002310_high_noise.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fd6cdab54cf045da5bb1f8e702886b6a825454e500c4424ed8f5a8d3da85291
+size 153453544

anha_22dts_000002640_high_noise.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:541e8e1b6aaff4b4ec8edea02eb3ca2bc5239f7f8e66d2b6ba6927d778b0ae9c
+size 153453544

anha_22dts_000002970_high_noise.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556d2031e59e1812053a7ff27808f088f85de43e58f47cadafc59dd2aacf3e
+size 153453544

anha_22dts_high_noise.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f97bdc540917f8de59b46d1c0f06cc70752ec03930e10a70d9c0375d445fd9c6
+size 153453544

config.yaml

@@ -0,0 +1,105 @@
+job: extension
+config:
+  name: anha_22dts
+  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
+    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: 330
+      max_step_saves_to_keep: 8
+      save_format: diffusers
+      push_to_hub: false
+    datasets:
+    - folder_path: /workspace/ai-toolkit/datasets/anha
+      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
+      - 768
+      - 1024
+      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: 3300
+      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: false
+      lr: 0.0001
+      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: 1
+      loss_type: mse
+    model:
+      name_or_path: ai-toolkit/Wan2.2-T2V-A14B-Diffusers-bf16
+      quantize: true
+      qtype: qfloat8
+      quantize_te: true
+      qtype_te: qfloat8
+      arch: wan22_14b:t2v
+      low_vram: true
+      model_kwargs:
+        train_high_noise: true
+        train_low_noise: false
+      layer_offloading: false
+      layer_offloading_text_encoder_percent: 1
+      layer_offloading_transformer_percent: 1
+    sample:
+      sampler: flowmatch
+      sample_every: 250
+      width: 1024
+      height: 1024
+      samples: []
+      neg: ''
+      seed: 42
+      walk_seed: true
+      guidance_scale: 4
+      sample_steps: 25
+      num_frames: 1
+      fps: 16
+meta:
+  name: anha_22dts
+  version: '1.0'

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20ecdbe995e4a865ecec86751e34d7e97d6176e4a9aa60fbccb17123439c276
+size 156692069

pid.txt

@@ -0,0 +1 @@
+5201