Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,10 @@ 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/1771653011691__000000250_0.webp filter=lfs diff=lfs merge=lfs -text
+samples/1771653850701__000000500_0.jpg filter=lfs diff=lfs merge=lfs -text
+samples/1771654478072__000000750_0.jpg filter=lfs diff=lfs merge=lfs -text
+samples/1771655093289__000001000_0.jpg filter=lfs diff=lfs merge=lfs -text
+samples/1771655711953__000001250_0.jpg filter=lfs diff=lfs merge=lfs -text
+loss_log.db filter=lfs diff=lfs merge=lfs -text
+loss_log.db-wal filter=lfs diff=lfs merge=lfs -text

.job_config.json

@@ -0,0 +1,133 @@
+{
+  "job": "extension",
+  "config": {
+    "name": "lana-lora-wan2.2",
+    "process": [
+      {
+        "type": "diffusion_trainer",
+        "training_folder": "/root/lab/ai-toolkit/output",
+        "sqlite_db_path": "/root/lab/ai-toolkit/aitk_db.db",
+        "device": "cuda",
+        "trigger_word": "l4n4lux",
+        "performance_log_every": 10,
+        "network": {
+          "type": "lora",
+          "linear": 64,
+          "linear_alpha": 64,
+          "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": 4,
+          "save_format": "diffusers",
+          "push_to_hub": false
+        },
+        "datasets": [
+          {
+            "folder_path": "/root/lab/ai-toolkit/datasets/lana",
+            "mask_path": null,
+            "mask_min_value": 0.1,
+            "default_caption": "l4n4lux",
+            "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,
+            "flip_x": false,
+            "flip_y": false,
+            "num_repeats": 1
+          }
+        ],
+        "train": {
+          "batch_size": 1,
+          "bypass_guidance_embedding": false,
+          "steps": 5000,
+          "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": true,
+          "force_first_sample": false,
+          "disable_sampling": false,
+          "dtype": "bf16",
+          "diff_output_preservation": true,
+          "diff_output_preservation_multiplier": 1,
+          "diff_output_preservation_class": "woman",
+          "switch_boundary_every": 1,
+          "loss_type": "mse"
+        },
+        "logging": {
+          "log_every": 1,
+          "use_ui_logger": true
+        },
+        "model": {
+          "name_or_path": "ai-toolkit/Wan2.2-T2V-A14B-Diffusers-bf16",
+          "quantize": false,
+          "qtype": "qfloat8",
+          "quantize_te": false,
+          "qtype_te": "qfloat8",
+          "arch": "wan22_14b:t2v",
+          "low_vram": false,
+          "model_kwargs": {
+            "train_high_noise": false,
+            "train_low_noise": true
+          },
+          "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": [
+            {
+              "prompt": "l4n4lux, woman with red hair, playing chess at the park, bomb going off in the background"
+            }
+          ],
+          "neg": "",
+          "seed": 42,
+          "walk_seed": true,
+          "guidance_scale": 4,
+          "sample_steps": 12,
+          "num_frames": 1,
+          "fps": 1
+        }
+      }
+    ]
+  },
+  "meta": {
+    "name": "[name]",
+    "version": "1.0"
+  }
+}

config.yaml

@@ -0,0 +1,110 @@
+job: extension
+config:
+  name: lana-lora-wan2.2
+  process:
+  - type: diffusion_trainer
+    training_folder: /root/lab/ai-toolkit/output
+    sqlite_db_path: /root/lab/ai-toolkit/aitk_db.db
+    device: cuda
+    trigger_word: l4n4lux
+    performance_log_every: 10
+    network:
+      type: lora
+      linear: 64
+      linear_alpha: 64
+      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: 4
+      save_format: diffusers
+      push_to_hub: false
+    datasets:
+    - folder_path: /root/lab/ai-toolkit/datasets/lana
+      mask_path: null
+      mask_min_value: 0.1
+      default_caption: l4n4lux
+      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
+      flip_x: false
+      flip_y: false
+      num_repeats: 1
+    train:
+      batch_size: 1
+      bypass_guidance_embedding: false
+      steps: 5000
+      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: true
+      force_first_sample: false
+      disable_sampling: false
+      dtype: bf16
+      diff_output_preservation: true
+      diff_output_preservation_multiplier: 1
+      diff_output_preservation_class: woman
+      switch_boundary_every: 1
+      loss_type: mse
+    logging:
+      log_every: 1
+      use_ui_logger: true
+    model:
+      name_or_path: ai-toolkit/Wan2.2-T2V-A14B-Diffusers-bf16
+      quantize: false
+      qtype: qfloat8
+      quantize_te: false
+      qtype_te: qfloat8
+      arch: wan22_14b:t2v
+      low_vram: false
+      model_kwargs:
+        train_high_noise: false
+        train_low_noise: true
+      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:
+      - prompt: l4n4lux, woman with red hair, playing chess at the park, bomb going
+          off in the background
+      neg: ''
+      seed: 42
+      walk_seed: true
+      guidance_scale: 4
+      sample_steps: 12
+      num_frames: 1
+      fps: 1
+meta:
+  name: lana-lora-wan2.2
+  version: '1.0'

lana-lora-wan2.2_000000250_low_noise.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:295dfc78dfd4ccceefb9a1d5d440a501d18834155f42f653b3e21f9b0ee103d7
+size 613517200

lana-lora-wan2.2_000000500_low_noise.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fad325df2bff7abc7769a6e2844c36f267936562eb30ab65c295f9e37a33bcf
+size 613517200

lana-lora-wan2.2_000000750_low_noise.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:154e76abf3332afe0fb0660fcd68ff9330ec84f482d4073faf12f8255138b586
+size 613517200

lana-lora-wan2.2_000001000_low_noise.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6891f479309f36b3adac4a7e713a31460a9727a2e5a278b8b670a9ac748d81a8
+size 613517200

lana-lora-wan2.2_000001250_low_noise.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13172a6d07954845b90c559d2b7428b1bbd0836587d237328c12ae7bd114744a
+size 613517200

log.txt

@@ -0,0 +1,188 @@
+Running 1 job
+{
+    "type": "diffusion_trainer",
+    "training_folder": "/root/lab/ai-toolkit/output",
+    "sqlite_db_path": "/root/lab/ai-toolkit/aitk_db.db",
+    "device": "cuda",
+    "trigger_word": "l4n4lux",
+    "performance_log_every": 10,
+    "network": {
+        "type": "lora",
+        "linear": 64,
+        "linear_alpha": 64,
+        "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": 4,
+        "save_format": "diffusers",
+        "push_to_hub": false
+    },
+    "datasets": [
+        {
+            "folder_path": "/root/lab/ai-toolkit/datasets/lana",
+            "mask_path": null,
+            "mask_min_value": 0.1,
+            "default_caption": "l4n4lux",
+            "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,
+            "flip_x": false,
+            "flip_y": false,
+            "num_repeats": 1
+        }
+    ],
+    "train": {
+        "batch_size": 1,
+        "bypass_guidance_embedding": false,
+        "steps": 5000,
+        "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": true,
+        "force_first_sample": false,
+        "disable_sampling": false,
+        "dtype": "bf16",
+        "diff_output_preservation": true,
+        "diff_output_preservation_multiplier": 1,
+        "diff_output_preservation_class": "woman",
+        "switch_boundary_every": 1,
+        "loss_type": "mse"
+    },
+    "logging": {
+        "log_every": 1,
+        "use_ui_logger": true
+    },
+    "model": {
+        "name_or_path": "ai-toolkit/Wan2.2-T2V-A14B-Diffusers-bf16",
+        "quantize": false,
+        "qtype": "qfloat8",
+        "quantize_te": false,
+        "qtype_te": "qfloat8",
+        "arch": "wan22_14b:t2v",
+        "low_vram": false,
+        "model_kwargs": {
+            "train_high_noise": false,
+            "train_low_noise": true
+        },
+        "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": [
+            {
+                "prompt": "l4n4lux, woman with red hair, playing chess at the park, bomb going off in the background"
+            }
+        ],
+        "neg": "",
+        "seed": 42,
+        "walk_seed": true,
+        "guidance_scale": 4,
+        "sample_steps": 12,
+        "num_frames": 1,
+        "fps": 1
+    }
+}
+Using SQLite database at /root/lab/ai-toolkit/aitk_db.db
+Job ID: "765fbd95-c627-460c-a232-147504194a44"
+
+#############################################
+# Running job: lana-lora-wan2.2
+#############################################
+
+
+Running  1 process
+Loading Wan model
+Loading transformer 1
+
+
+Loading transformer 2
+
+
+Creating DualWanTransformer3DModel
+Loading UMT5EncoderModel
+You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
+You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
+Using ai-toolkit/umt5_xxl_encoder for UMT5 encoder.
+`torch_dtype` is deprecated! Use `dtype` instead!
+`torch_dtype` is deprecated! Use `dtype` instead!
+
+
+Loading VAE
+Making pipe
+Preparing Model
+create LoRA network. base dim (rank): 64, alpha: 64
+neuron dropout: p=None, rank dropout: p=None, module dropout: p=None
+apply LoRA to Conv2d with kernel size (3,3). dim (rank): 16, alpha: 16
+create LoRA for Text Encoder: 0 modules.
+create LoRA for U-Net: 400 modules.
+enable LoRA for U-Net
+#### IMPORTANT RESUMING FROM /root/lab/ai-toolkit/output/lana-lora-wan2.2/lana-lora-wan2.2_000001250_low_noise.safetensors ####
+Loading from /root/lab/ai-toolkit/output/lana-lora-wan2.2/lana-lora-wan2.2_000001250_low_noise.safetensors
+Missing keys: []
+Found step 1250 in metadata, starting from there
+Loading optimizer state from /root/lab/ai-toolkit/output/lana-lora-wan2.2/optimizer.pt
+Updating optimizer LR from params
+Dataset: /root/lab/ai-toolkit/datasets/lana
+  -  Preprocessing image dimensions
+
  0%|                                                                                                                 | 0/72 [00:00<?, ?it/s]
  0%|                                                                                                                 | 0/72 [00:00<?, ?it/s]
+
+  -  Found 72 images
+Bucket sizes for /root/lab/ai-toolkit/datasets/lana:
+480x512: 72 files
+1 buckets made
+Dataset: /root/lab/ai-toolkit/datasets/lana
+  -  Preprocessing image dimensions
+
  0%|                                                                                                                 | 0/72 [00:00<?, ?it/s]
  0%|                                                                                                                 | 0/72 [00:00<?, ?it/s]
+
+  -  Found 72 images
+Bucket sizes for /root/lab/ai-toolkit/datasets/lana:
+720x768: 72 files
+1 buckets made
+Dataset: /root/lab/ai-toolkit/datasets/lana
+  -  Preprocessing image dimensions
+
  0%|                                                                                                                 | 0/72 [00:00<?, ?it/s]
  0%|                                                                                                                 | 0/72 [00:00<?, ?it/s]
+
+  -  Found 72 images
+Bucket sizes for /root/lab/ai-toolkit/datasets/lana:
+960x1024: 72 files
+1 buckets made
+Skipping first sample due to config setting
+

loss_log.db

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbbc6e970be6c9bb7bcf44492a48f71f7c4fa8b281d2d10f6f2c1b24823717cd
+size 286720

loss_log.db-wal

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be17acb9131836b918f041bb52e6c7cb561e01ffb5ae345459835d7755cfd0c2
+size 4120032

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbfff146829b25fb2f4752f8ae1557191bd1c03e68263780b7f10e5be0322376
+size 623951333

pid.txt

@@ -0,0 +1 @@
+29281