Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ 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
+loss_log.db filter=lfs diff=lfs merge=lfs -text

.huggingfaceignore

@@ -0,0 +1 @@
+*.db-wal

.job_config.json

@@ -0,0 +1,227 @@
+{
+  "job": "extension",
+  "config": {
+    "name": "PLORAV7_LTX",
+    "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": 32,
+          "linear_alpha": 32,
+          "conv": 16,
+          "conv_alpha": 16,
+          "lokr_full_rank": true,
+          "lokr_factor": -1,
+          "network_kwargs": {
+            "ignore_if_contains": []
+          }
+        },
+        "save": {
+          "dtype": "bf16",
+          "save_every": 500,
+          "max_step_saves_to_keep": 400,
+          "save_format": "diffusers",
+          "push_to_hub": false
+        },
+        "datasets": [
+          {
+            "folder_path": "/app/ai-toolkit/datasets/49",
+            "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": [
+              512
+            ],
+            "controls": [],
+            "shrink_video_to_frames": true,
+            "num_frames": 49,
+            "flip_x": false,
+            "flip_y": false,
+            "num_repeats": 2,
+            "do_i2v": false,
+            "fps": 24
+          },
+          {
+            "folder_path": "/app/ai-toolkit/datasets/73",
+            "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": [
+              512
+            ],
+            "controls": [],
+            "shrink_video_to_frames": true,
+            "num_frames": 73,
+            "flip_x": false,
+            "flip_y": false,
+            "num_repeats": 2
+          },
+          {
+            "folder_path": "/app/ai-toolkit/datasets/81",
+            "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": [
+              512
+            ],
+            "controls": [],
+            "shrink_video_to_frames": true,
+            "num_frames": 81,
+            "flip_x": false,
+            "flip_y": false,
+            "num_repeats": 2
+          },
+          {
+            "folder_path": "/app/ai-toolkit/datasets/89",
+            "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": [
+              512
+            ],
+            "controls": [],
+            "shrink_video_to_frames": true,
+            "num_frames": 89,
+            "flip_x": false,
+            "flip_y": false,
+            "num_repeats": 2
+          },
+          {
+            "folder_path": "/app/ai-toolkit/datasets/97",
+            "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": [
+              512
+            ],
+            "controls": [],
+            "shrink_video_to_frames": true,
+            "num_frames": 97,
+            "flip_x": false,
+            "flip_y": false,
+            "num_repeats": 2
+          },
+          {
+            "folder_path": "/app/ai-toolkit/datasets/images",
+            "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": [
+              512,
+              768
+            ],
+            "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": 25000,
+          "gradient_accumulation": 1,
+          "train_unet": true,
+          "train_text_encoder": false,
+          "gradient_checkpointing": true,
+          "noise_scheduler": "flowmatch",
+          "optimizer": "adamw8bit",
+          "timestep_type": "weighted",
+          "content_or_style": "balanced",
+          "optimizer_params": {
+            "weight_decay": 0.0001
+          },
+          "unload_text_encoder": false,
+          "cache_text_embeddings": true,
+          "lr": 0.0001,
+          "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": "Lightricks/LTX-2",
+          "quantize": true,
+          "qtype": "qfloat8",
+          "quantize_te": true,
+          "qtype_te": "uint6",
+          "arch": "ltx2",
+          "low_vram": true,
+          "model_kwargs": {},
+          "layer_offloading": false,
+          "layer_offloading_text_encoder_percent": 1,
+          "layer_offloading_transformer_percent": 1
+        },
+        "sample": {
+          "sampler": "flowmatch",
+          "sample_every": 250,
+          "width": 768,
+          "height": 768,
+          "samples": [],
+          "neg": "",
+          "seed": 42,
+          "walk_seed": true,
+          "guidance_scale": 4,
+          "sample_steps": 25,
+          "num_frames": 121,
+          "fps": 24
+        }
+      }
+    ]
+  },
+  "meta": {
+    "name": "[name]",
+    "version": "1.0"
+  }
+}

PLORAV7_LTX_000000500.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d41895c8f8aa28a89a78feb28a29eedeb40f5eb0bdcf4fd507cc5046d0c8150
+size 616948936

PLORAV7_LTX_000001000.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc4d78e9469b751ff5697e6e31ee1066cfefdc74523a129625da3bed3785cce2
+size 616948936

PLORAV7_LTX_000001500.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:432752e36f370c551221a66abffb299a409b0abb60a086d9c8e42da3beb0c656
+size 616948936

PLORAV7_LTX_000002000.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fa83117ceb7113ffd7aac0b131a9f8bfa4ad8ed51da50ca157d1828b443a39c
+size 616948936

PLORAV7_LTX_000002500.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d792597c559358303edce19ff969ae86c5d959f69ebc529aaeb8fdd03106efd1
+size 616948936

PLORAV7_LTX_000003000.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ae92528e5b06f7784180e66fa654d35099c2fb08a4edafbe58d4278f2a91aac
+size 616948936

PLORAV7_LTX_000003500.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdae5b883f2c05bcb71ce95307f1252fb0c9817edef1a2c30bbc737d1b6ebc18
+size 616948936

PLORAV7_LTX_000004000.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b354f2d509aae2f6d7d9e9a1cda12a38096728146bbbc323e0573ae22d37f1f
+size 616948936

PLORAV7_LTX_000004500.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92ade0c748a15205a0cf94151b113fcd9a7fae530a615c743f234383ca2300aa
+size 616948936

PLORAV7_LTX_000005000.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c96872f33ea4a33600d37272f7c5f5aef4436b1cdc0ace4a80bb0df963b60e27
+size 616948936

PLORAV7_LTX_000005500.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfd606624bdc940ac90940b0d2c2cd7002c3761d0fa82358fece9c594a19600b
+size 616948936

PLORAV7_LTX_000006000.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccb68a111c636d2f4ab6dfa1184201cd59c000b6c1a6a30cecbf984436fc8af2
+size 616948936

PLORAV7_LTX_000006500.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:618e0a009a7213dff88f35943bc5937c15cfe29729ad64250e94bf802e5ab49b
+size 616948936

PLORAV7_LTX_000007000.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9620a14bba8fae1e578eda64a2e100fc3a6ac5d6f2e2851e9d43119ac0072430
+size 616948936

PLORAV7_LTX_000007500.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a73ce7788a7e444fe35060503ffd8351652ed6d1052f51f7d94335b514c5a95
+size 616948936

PLORAV7_LTX_000008000.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97beedbc78317824fdaaeae7a4cc8b5b1957c48de2c01bdf65dad94ff256babc
+size 616948936

PLORAV7_LTX_000008500.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c50a99d13a913843f4e2b9ee17d134154cff6cc32f9c4b69755dceb63f4f6428
+size 616948936

PLORAV7_LTX_000009000.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a30f52f67aa087ea88c3337b650656ae22d7441d32ede56ba6f3a7eb4265a5d
+size 616948936

PLORAV7_LTX_000009500.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:798570c465a7263cd06ea169044ee9eda9402b7bbf725b89b61607dfbafe81a7
+size 616948936

PLORAV7_LTX_000010000.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:087ba767e92c10bd7dc9454aa7ad3b8dc839b8ef6029238bd7e800c1bbea05a0
+size 616948936

PLORAV7_LTX_000010500.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:295d5947b8f997100425ce8373eb0e709ed5994af42b844fae5e3ec9ebed2d2a
+size 616948936

PLORAV7_LTX_000011000.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cbc6a8e154f6ff4e59569b7717df48abefac075861f21b2787927bc8e36fdc1
+size 616948936

PLORAV7_LTX_000011500.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a384b90a9188c4806977c266c09b51addd147c3a9cd37584f55bcfbfa897a2a4
+size 616948936

PLORAV7_LTX_000012000.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a91e6efa7842823d949b8230383a54b1f8ae269c49a11661d01543127c6c63e3
+size 616948936

PLORAV7_LTX_000012500.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc2851c5894a7b6bb2bcfeb0ee30b1f9eaecd41ff406a3bc14218b4902a8b709
+size 616948936

PLORAV7_LTX_000013000.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a6f79067ce45f0fc0d57b00c288727005c866b9f0b549dc75f511708d668523
+size 616948936

PLORAV7_LTX_000013500.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f4eb36f76a73149055a88daaa47ec035bb0b1fc8e146ff44a229e546d8936fe
+size 616948936

config.yaml

@@ -0,0 +1,192 @@
+job: extension
+config:
+  name: PLORAV7_LTX
+  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: 32
+      linear_alpha: 32
+      conv: 16
+      conv_alpha: 16
+      lokr_full_rank: true
+      lokr_factor: -1
+      network_kwargs:
+        ignore_if_contains: []
+    save:
+      dtype: bf16
+      save_every: 500
+      max_step_saves_to_keep: 400
+      save_format: diffusers
+      push_to_hub: false
+    datasets:
+    - folder_path: /app/ai-toolkit/datasets/49
+      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:
+      - 512
+      controls: []
+      shrink_video_to_frames: true
+      num_frames: 49
+      flip_x: false
+      flip_y: false
+      num_repeats: 2
+      do_i2v: false
+      fps: 24
+    - folder_path: /app/ai-toolkit/datasets/73
+      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:
+      - 512
+      controls: []
+      shrink_video_to_frames: true
+      num_frames: 73
+      flip_x: false
+      flip_y: false
+      num_repeats: 2
+    - folder_path: /app/ai-toolkit/datasets/81
+      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:
+      - 512
+      controls: []
+      shrink_video_to_frames: true
+      num_frames: 81
+      flip_x: false
+      flip_y: false
+      num_repeats: 2
+    - folder_path: /app/ai-toolkit/datasets/89
+      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:
+      - 512
+      controls: []
+      shrink_video_to_frames: true
+      num_frames: 89
+      flip_x: false
+      flip_y: false
+      num_repeats: 2
+    - folder_path: /app/ai-toolkit/datasets/97
+      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:
+      - 512
+      controls: []
+      shrink_video_to_frames: true
+      num_frames: 97
+      flip_x: false
+      flip_y: false
+      num_repeats: 2
+    - folder_path: /app/ai-toolkit/datasets/images
+      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:
+      - 512
+      - 768
+      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: 25000
+      gradient_accumulation: 1
+      train_unet: true
+      train_text_encoder: false
+      gradient_checkpointing: true
+      noise_scheduler: flowmatch
+      optimizer: adamw8bit
+      timestep_type: weighted
+      content_or_style: balanced
+      optimizer_params:
+        weight_decay: 0.0001
+      unload_text_encoder: false
+      cache_text_embeddings: true
+      lr: 0.0001
+      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: Lightricks/LTX-2
+      quantize: true
+      qtype: qfloat8
+      quantize_te: true
+      qtype_te: uint6
+      arch: ltx2
+      low_vram: true
+      model_kwargs: {}
+      layer_offloading: false
+      layer_offloading_text_encoder_percent: 1
+      layer_offloading_transformer_percent: 1
+    sample:
+      sampler: flowmatch
+      sample_every: 250
+      width: 768
+      height: 768
+      samples: []
+      neg: ''
+      seed: 42
+      walk_seed: true
+      guidance_scale: 4
+      sample_steps: 25
+      num_frames: 121
+      fps: 24
+meta:
+  name: PLORAV7_LTX
+  version: '1.0'

logs/0_log.txt

@@ -0,0 +1,344 @@
+Running 1 job
+{
+    "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": 32,
+        "linear_alpha": 32,
+        "conv": 16,
+        "conv_alpha": 16,
+        "lokr_full_rank": true,
+        "lokr_factor": -1,
+        "network_kwargs": {
+            "ignore_if_contains": []
+        }
+    },
+    "save": {
+        "dtype": "bf16",
+        "save_every": 500,
+        "max_step_saves_to_keep": 400,
+        "save_format": "diffusers",
+        "push_to_hub": false
+    },
+    "datasets": [
+        {
+            "folder_path": "/app/ai-toolkit/datasets/49",
+            "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": [
+                512
+            ],
+            "controls": [],
+            "shrink_video_to_frames": true,
+            "num_frames": 49,
+            "flip_x": false,
+            "flip_y": false,
+            "num_repeats": 2,
+            "do_i2v": false,
+            "fps": 24
+        },
+        {
+            "folder_path": "/app/ai-toolkit/datasets/73",
+            "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": [
+                512
+            ],
+            "controls": [],
+            "shrink_video_to_frames": true,
+            "num_frames": 73,
+            "flip_x": false,
+            "flip_y": false,
+            "num_repeats": 2
+        },
+        {
+            "folder_path": "/app/ai-toolkit/datasets/81",
+            "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": [
+                512
+            ],
+            "controls": [],
+            "shrink_video_to_frames": true,
+            "num_frames": 81,
+            "flip_x": false,
+            "flip_y": false,
+            "num_repeats": 2
+        },
+        {
+            "folder_path": "/app/ai-toolkit/datasets/89",
+            "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": [
+                512
+            ],
+            "controls": [],
+            "shrink_video_to_frames": true,
+            "num_frames": 89,
+            "flip_x": false,
+            "flip_y": false,
+            "num_repeats": 2
+        },
+        {
+            "folder_path": "/app/ai-toolkit/datasets/97",
+            "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": [
+                512
+            ],
+            "controls": [],
+            "shrink_video_to_frames": true,
+            "num_frames": 97,
+            "flip_x": false,
+            "flip_y": false,
+            "num_repeats": 2
+        },
+        {
+            "folder_path": "/app/ai-toolkit/datasets/images",
+            "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": [
+                512,
+                768
+            ],
+            "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": 25000,
+        "gradient_accumulation": 1,
+        "train_unet": true,
+        "train_text_encoder": false,
+        "gradient_checkpointing": true,
+        "noise_scheduler": "flowmatch",
+        "optimizer": "adamw8bit",
+        "timestep_type": "weighted",
+        "content_or_style": "balanced",
+        "optimizer_params": {
+            "weight_decay": 0.0001
+        },
+        "unload_text_encoder": false,
+        "cache_text_embeddings": true,
+        "lr": 0.0001,
+        "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": "Lightricks/LTX-2",
+        "quantize": true,
+        "qtype": "qfloat8",
+        "quantize_te": true,
+        "qtype_te": "uint6",
+        "arch": "ltx2",
+        "low_vram": true,
+        "model_kwargs": {},
+        "layer_offloading": false,
+        "layer_offloading_text_encoder_percent": 1,
+        "layer_offloading_transformer_percent": 1
+    },
+    "sample": {
+        "sampler": "flowmatch",
+        "sample_every": 250,
+        "width": 768,
+        "height": 768,
+        "samples": [],
+        "neg": "",
+        "seed": 42,
+        "walk_seed": true,
+        "guidance_scale": 4,
+        "sample_steps": 25,
+        "num_frames": 121,
+        "fps": 24
+    }
+}
+Changing sample extention to animated webp
+Using SQLite database at /app/ai-toolkit/aitk_db.db
+Job ID: "bf530ed1-e796-42a1-9ffa-55399fe92986"
+
+#############################################
+# Running job: PLORAV7_LTX
+#############################################
+
+
+Running  1 process
+Loading LTX2 model
+Loading transformer
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Quantizing Transformer
+ - quantizing 48 transformer blocks
+
  0%|          | 0/48 [00:00<?, ?it/s]
  0%|          | 0/48 [00:00<?, ?it/s]
  2%|2         | 1/48 [00:00<00:27,  1.70it/s]
  2%|2         | 1/48 [00:00<00:27,  1.70it/s]
  4%|4         | 2/48 [00:00<00:19,  2.35it/s]
  4%|4         | 2/48 [00:00<00:19,  2.35it/s]
  6%|6         | 3/48 [00:01<00:18,  2.43it/s]
  6%|6         | 3/48 [00:01<00:18,  2.43it/s]
  8%|8         | 4/48 [00:01<00:16,  2.66it/s]
  8%|8         | 4/48 [00:01<00:16,  2.66it/s]
 10%|#         | 5/48 [00:01<00:15,  2.82it/s]
 10%|#         | 5/48 [00:01<00:15,  2.82it/s]
 12%|#2        | 6/48 [00:02<00:16,  2.62it/s]
 12%|#2        | 6/48 [00:02<00:16,  2.62it/s]
 15%|#4        | 7/48 [00:02<00:16,  2.47it/s]
 15%|#4        | 7/48 [00:02<00:16,  2.47it/s]
 17%|#6        | 8/48 [00:03<00:16,  2.45it/s]
 17%|#6        | 8/48 [00:03<00:16,  2.45it/s]
 19%|#8        | 9/48 [00:03<00:16,  2.41it/s]
 19%|#8        | 9/48 [00:03<00:16,  2.41it/s]
 21%|##        | 10/48 [00:04<00:14,  2.54it/s]
 21%|##        | 10/48 [00:04<00:14,  2.54it/s]
 23%|##2       | 11/48 [00:04<00:15,  2.38it/s]
 23%|##2       | 11/48 [00:04<00:15,  2.38it/s]
 25%|##5       | 12/48 [00:04<00:15,  2.29it/s]
 25%|##5       | 12/48 [00:04<00:15,  2.29it/s]
 27%|##7       | 13/48 [00:05<00:16,  2.19it/s]
 27%|##7       | 13/48 [00:05<00:16,  2.19it/s]
 29%|##9       | 14/48 [00:05<00:14,  2.40it/s]
 29%|##9       | 14/48 [00:05<00:14,  2.40it/s]
 31%|###1      | 15/48 [00:06<00:12,  2.55it/s]
 31%|###1      | 15/48 [00:06<00:12,  2.55it/s]
 33%|###3      | 16/48 [00:06<00:11,  2.68it/s]
 33%|###3      | 16/48 [00:06<00:11,  2.68it/s]
 35%|###5      | 17/48 [00:06<00:11,  2.80it/s]
 35%|###5      | 17/48 [00:06<00:11,  2.80it/s]
 38%|###7      | 18/48 [00:07<00:10,  2.87it/s]
 38%|###7      | 18/48 [00:07<00:10,  2.87it/s]
 40%|###9      | 19/48 [00:07<00:11,  2.56it/s]
 40%|###9      | 19/48 [00:07<00:11,  2.56it/s]
 42%|####1     | 20/48 [00:07<00:10,  2.70it/s]
 42%|####1     | 20/48 [00:07<00:10,  2.70it/s]
 44%|####3     | 21/48 [00:08<00:09,  2.79it/s]
 44%|####3     | 21/48 [00:08<00:09,  2.79it/s]
 46%|####5     | 22/48 [00:08<00:09,  2.86it/s]
 46%|####5     | 22/48 [00:08<00:09,  2.86it/s]
 48%|####7     | 23/48 [00:08<00:08,  2.92it/s]
 48%|####7     | 23/48 [00:08<00:08,  2.92it/s]
 50%|#####     | 24/48 [00:09<00:08,  2.96it/s]
 50%|#####     | 24/48 [00:09<00:08,  2.96it/s]
 52%|#####2    | 25/48 [00:09<00:08,  2.62it/s]
 52%|#####2    | 25/48 [00:09<00:08,  2.62it/s]
 54%|#####4    | 26/48 [00:10<00:08,  2.74it/s]
 54%|#####4    | 26/48 [00:10<00:08,  2.74it/s]
 56%|#####6    | 27/48 [00:10<00:07,  2.84it/s]
 56%|#####6    | 27/48 [00:10<00:07,  2.84it/s]
 58%|#####8    | 28/48 [00:10<00:06,  2.89it/s]
 58%|#####8    | 28/48 [00:10<00:06,  2.89it/s]
 60%|######    | 29/48 [00:11<00:06,  2.96it/s]
 60%|######    | 29/48 [00:11<00:06,  2.96it/s]
 62%|######2   | 30/48 [00:11<00:05,  3.01it/s]
 62%|######2   | 30/48 [00:11<00:05,  3.01it/s]
 65%|######4   | 31/48 [00:11<00:05,  3.01it/s]
 65%|######4   | 31/48 [00:11<00:05,  3.01it/s]
 67%|######6   | 32/48 [00:12<00:06,  2.65it/s]
 67%|######6   | 32/48 [00:12<00:06,  2.65it/s]
 69%|######8   | 33/48 [00:12<00:05,  2.77it/s]
 69%|######8   | 33/48 [00:12<00:05,  2.77it/s]
 71%|#######   | 34/48 [00:12<00:04,  2.85it/s]
 71%|#######   | 34/48 [00:12<00:04,  2.85it/s]
 73%|#######2  | 35/48 [00:13<00:04,  2.90it/s]
 73%|#######2  | 35/48 [00:13<00:04,  2.90it/s]
 75%|#######5  | 36/48 [00:13<00:04,  2.95it/s]
 75%|#######5  | 36/48 [00:13<00:04,  2.95it/s]
 77%|#######7  | 37/48 [00:13<00:03,  2.97it/s]
 77%|#######7  | 37/48 [00:13<00:03,  2.97it/s]
 79%|#######9  | 38/48 [00:14<00:03,  2.61it/s]
 79%|#######9  | 38/48 [00:14<00:03,  2.61it/s]
 81%|########1 | 39/48 [00:14<00:03,  2.73it/s]
 81%|########1 | 39/48 [00:14<00:03,  2.73it/s]
 83%|########3 | 40/48 [00:14<00:02,  2.82it/s]
 83%|########3 | 40/48 [00:14<00:02,  2.82it/s]
 85%|########5 | 41/48 [00:15<00:02,  2.90it/s]
 85%|########5 | 41/48 [00:15<00:02,  2.90it/s]
 88%|########7 | 42/48 [00:15<00:02,  2.95it/s]
 88%|########7 | 42/48 [00:15<00:02,  2.95it/s]
 90%|########9 | 43/48 [00:15<00:01,  2.99it/s]
 90%|########9 | 43/48 [00:15<00:01,  2.99it/s]
 92%|#########1| 44/48 [00:16<00:01,  3.01it/s]
 92%|#########1| 44/48 [00:16<00:01,  3.01it/s]
 94%|#########3| 45/48 [00:16<00:01,  2.63it/s]
 94%|#########3| 45/48 [00:16<00:01,  2.63it/s]
 96%|#########5| 46/48 [00:17<00:00,  2.75it/s]
 96%|#########5| 46/48 [00:17<00:00,  2.75it/s]
 98%|#########7| 47/48 [00:17<00:00,  2.85it/s]
 98%|#########7| 47/48 [00:17<00:00,  2.85it/s]
+
+ - quantizing extras
+Moving transformer to CPU
+Loading text encoder
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Quantizing Text Encoder
+Loading VAEs and other components
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Making pipe
+Preparing Model
+Model Loaded
+create LoRA network. base dim (rank): 32, alpha: 32
+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: 1344 modules.
+enable LoRA for U-Net
+Dataset: /app/ai-toolkit/datasets/49
+  -  Preprocessing video dimensions
+
  0%|          | 0/140 [00:00<?, ?it/s]
  0%|          | 0/140 [00:00<?, ?it/s]
  8%|7         | 11/140 [00:00<00:01, 102.69it/s]
  8%|7         | 11/140 [00:00<00:01, 102.69it/s]
 19%|#8        | 26/140 [00:00<00:00, 126.82it/s]
 19%|#8        | 26/140 [00:00<00:00, 126.82it/s]
 31%|###       | 43/140 [00:00<00:00, 143.80it/s]
 31%|###       | 43/140 [00:00<00:00, 143.80it/s]
 41%|####1     | 58/140 [00:00<00:00, 143.46it/s]
 41%|####1     | 58/140 [00:00<00:00, 143.46it/s]
+
+  -  Found 140 videos
+Bucket sizes for /app/ai-toolkit/datasets/49:
+576x416: 78 files
+576x448: 44 files
+544x416: 16 files
+512x384: 2 files
+4 buckets made
+Caching latents for /app/ai-toolkit/datasets/49
+ - Saving latents to disk
+
+
+Caching text_embeddings for /app/ai-toolkit/datasets/49
+ - Saving text embeddings to disk
+

logs/1_log.txt

@@ -0,0 +1,378 @@
+Running 1 job
+{
+    "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": 32,
+        "linear_alpha": 32,
+        "conv": 16,
+        "conv_alpha": 16,
+        "lokr_full_rank": true,
+        "lokr_factor": -1,
+        "network_kwargs": {
+            "ignore_if_contains": []
+        }
+    },
+    "save": {
+        "dtype": "bf16",
+        "save_every": 500,
+        "max_step_saves_to_keep": 400,
+        "save_format": "diffusers",
+        "push_to_hub": false
+    },
+    "datasets": [
+        {
+            "folder_path": "/app/ai-toolkit/datasets/49",
+            "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": [
+                512
+            ],
+            "controls": [],
+            "shrink_video_to_frames": true,
+            "num_frames": 49,
+            "flip_x": false,
+            "flip_y": false,
+            "num_repeats": 2,
+            "do_i2v": false,
+            "fps": 24
+        },
+        {
+            "folder_path": "/app/ai-toolkit/datasets/73",
+            "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": [
+                512
+            ],
+            "controls": [],
+            "shrink_video_to_frames": true,
+            "num_frames": 73,
+            "flip_x": false,
+            "flip_y": false,
+            "num_repeats": 2
+        },
+        {
+            "folder_path": "/app/ai-toolkit/datasets/81",
+            "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": [
+                512
+            ],
+            "controls": [],
+            "shrink_video_to_frames": true,
+            "num_frames": 81,
+            "flip_x": false,
+            "flip_y": false,
+            "num_repeats": 2
+        },
+        {
+            "folder_path": "/app/ai-toolkit/datasets/89",
+            "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": [
+                512
+            ],
+            "controls": [],
+            "shrink_video_to_frames": true,
+            "num_frames": 89,
+            "flip_x": false,
+            "flip_y": false,
+            "num_repeats": 2
+        },
+        {
+            "folder_path": "/app/ai-toolkit/datasets/97",
+            "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": [
+                512
+            ],
+            "controls": [],
+            "shrink_video_to_frames": true,
+            "num_frames": 97,
+            "flip_x": false,
+            "flip_y": false,
+            "num_repeats": 2
+        },
+        {
+            "folder_path": "/app/ai-toolkit/datasets/images",
+            "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": [
+                512,
+                768
+            ],
+            "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": 25000,
+        "gradient_accumulation": 1,
+        "train_unet": true,
+        "train_text_encoder": false,
+        "gradient_checkpointing": true,
+        "noise_scheduler": "flowmatch",
+        "optimizer": "adamw8bit",
+        "timestep_type": "weighted",
+        "content_or_style": "balanced",
+        "optimizer_params": {
+            "weight_decay": 0.0001
+        },
+        "unload_text_encoder": false,
+        "cache_text_embeddings": true,
+        "lr": 0.0001,
+        "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": "Lightricks/LTX-2",
+        "quantize": true,
+        "qtype": "qfloat8",
+        "quantize_te": true,
+        "qtype_te": "uint6",
+        "arch": "ltx2",
+        "low_vram": true,
+        "model_kwargs": {},
+        "layer_offloading": false,
+        "layer_offloading_text_encoder_percent": 1,
+        "layer_offloading_transformer_percent": 1
+    },
+    "sample": {
+        "sampler": "flowmatch",
+        "sample_every": 250,
+        "width": 768,
+        "height": 768,
+        "samples": [],
+        "neg": "",
+        "seed": 42,
+        "walk_seed": true,
+        "guidance_scale": 4,
+        "sample_steps": 25,
+        "num_frames": 121,
+        "fps": 24
+    }
+}
+Changing sample extention to animated webp
+Using SQLite database at /app/ai-toolkit/aitk_db.db
+Job ID: "bf530ed1-e796-42a1-9ffa-55399fe92986"
+
+#############################################
+# Running job: PLORAV7_LTX
+#############################################
+
+
+Running  1 process
+Loading LTX2 model
+Loading transformer
+
+
+Quantizing Transformer
+ - quantizing 48 transformer blocks
+
  0%|          | 0/48 [00:00<?, ?it/s]
  0%|          | 0/48 [00:00<?, ?it/s]
  2%|2         | 1/48 [00:00<00:32,  1.44it/s]
  2%|2         | 1/48 [00:00<00:32,  1.44it/s]
  4%|4         | 2/48 [00:01<00:25,  1.79it/s]
  4%|4         | 2/48 [00:01<00:25,  1.79it/s]
  6%|6         | 3/48 [00:01<00:23,  1.94it/s]
  6%|6         | 3/48 [00:01<00:23,  1.94it/s]
  8%|8         | 4/48 [00:02<00:21,  2.02it/s]
  8%|8         | 4/48 [00:02<00:21,  2.02it/s]
 10%|#         | 5/48 [00:02<00:20,  2.07it/s]
 10%|#         | 5/48 [00:02<00:20,  2.07it/s]
 12%|#2        | 6/48 [00:03<00:19,  2.10it/s]
 12%|#2        | 6/48 [00:03<00:19,  2.10it/s]
 15%|#4        | 7/48 [00:03<00:19,  2.13it/s]
 15%|#4        | 7/48 [00:03<00:19,  2.13it/s]
 17%|#6        | 8/48 [00:03<00:18,  2.14it/s]
 17%|#6        | 8/48 [00:03<00:18,  2.14it/s]
 19%|#8        | 9/48 [00:04<00:18,  2.16it/s]
 19%|#8        | 9/48 [00:04<00:18,  2.16it/s]
 21%|##        | 10/48 [00:04<00:17,  2.18it/s]
 21%|##        | 10/48 [00:04<00:17,  2.18it/s]
 23%|##2       | 11/48 [00:05<00:16,  2.18it/s]
 23%|##2       | 11/48 [00:05<00:16,  2.18it/s]
 25%|##5       | 12/48 [00:05<00:16,  2.19it/s]
 25%|##5       | 12/48 [00:05<00:16,  2.19it/s]
 27%|##7       | 13/48 [00:06<00:17,  1.98it/s]
 27%|##7       | 13/48 [00:06<00:17,  1.98it/s]
 29%|##9       | 14/48 [00:06<00:16,  2.05it/s]
 29%|##9       | 14/48 [00:06<00:16,  2.05it/s]
 31%|###1      | 15/48 [00:07<00:15,  2.10it/s]
 31%|###1      | 15/48 [00:07<00:15,  2.10it/s]
 33%|###3      | 16/48 [00:07<00:15,  2.13it/s]
 33%|###3      | 16/48 [00:07<00:15,  2.13it/s]
 35%|###5      | 17/48 [00:08<00:14,  2.15it/s]
 35%|###5      | 17/48 [00:08<00:14,  2.15it/s]
 38%|###7      | 18/48 [00:08<00:13,  2.17it/s]
 38%|###7      | 18/48 [00:08<00:13,  2.17it/s]
 40%|###9      | 19/48 [00:09<00:14,  1.99it/s]
 40%|###9      | 19/48 [00:09<00:14,  1.99it/s]
 42%|####1     | 20/48 [00:09<00:13,  2.05it/s]
 42%|####1     | 20/48 [00:09<00:13,  2.05it/s]
 44%|####3     | 21/48 [00:10<00:12,  2.08it/s]
 44%|####3     | 21/48 [00:10<00:12,  2.08it/s]
 46%|####5     | 22/48 [00:10<00:12,  2.11it/s]
 46%|####5     | 22/48 [00:10<00:12,  2.11it/s]
 48%|####7     | 23/48 [00:11<00:11,  2.14it/s]
 48%|####7     | 23/48 [00:11<00:11,  2.14it/s]
 50%|#####     | 24/48 [00:11<00:11,  2.17it/s]
 50%|#####     | 24/48 [00:11<00:11,  2.17it/s]
 52%|#####2    | 25/48 [00:12<00:11,  1.96it/s]
 52%|#####2    | 25/48 [00:12<00:11,  1.96it/s]
 54%|#####4    | 26/48 [00:12<00:10,  2.07it/s]
 54%|#####4    | 26/48 [00:12<00:10,  2.07it/s]
 56%|#####6    | 27/48 [00:12<00:09,  2.13it/s]
 56%|#####6    | 27/48 [00:12<00:09,  2.13it/s]
 58%|#####8    | 28/48 [00:13<00:09,  2.18it/s]
 58%|#####8    | 28/48 [00:13<00:09,  2.18it/s]
 60%|######    | 29/48 [00:13<00:08,  2.22it/s]
 60%|######    | 29/48 [00:13<00:08,  2.22it/s]
 62%|######2   | 30/48 [00:14<00:08,  2.25it/s]
 62%|######2   | 30/48 [00:14<00:08,  2.25it/s]
 65%|######4   | 31/48 [00:14<00:07,  2.27it/s]
 65%|######4   | 31/48 [00:14<00:07,  2.27it/s]
 67%|######6   | 32/48 [00:15<00:07,  2.01it/s]
 67%|######6   | 32/48 [00:15<00:07,  2.01it/s]
 69%|######8   | 33/48 [00:15<00:07,  2.06it/s]
 69%|######8   | 33/48 [00:15<00:07,  2.06it/s]
 71%|#######   | 34/48 [00:16<00:06,  2.10it/s]
 71%|#######   | 34/48 [00:16<00:06,  2.10it/s]
 73%|#######2  | 35/48 [00:16<00:06,  2.13it/s]
 73%|#######2  | 35/48 [00:16<00:06,  2.13it/s]
 75%|#######5  | 36/48 [00:17<00:05,  2.16it/s]
 75%|#######5  | 36/48 [00:17<00:05,  2.16it/s]
 77%|#######7  | 37/48 [00:17<00:05,  2.18it/s]
 77%|#######7  | 37/48 [00:17<00:05,  2.18it/s]
 79%|#######9  | 38/48 [00:18<00:05,  1.98it/s]
 79%|#######9  | 38/48 [00:18<00:05,  1.98it/s]
 81%|########1 | 39/48 [00:18<00:04,  1.93it/s]
 81%|########1 | 39/48 [00:18<00:04,  1.93it/s]
 83%|########3 | 40/48 [00:19<00:04,  1.86it/s]
 83%|########3 | 40/48 [00:19<00:04,  1.86it/s]
 85%|########5 | 41/48 [00:19<00:03,  1.82it/s]
 85%|########5 | 41/48 [00:19<00:03,  1.82it/s]
 88%|########7 | 42/48 [00:20<00:03,  1.78it/s]
 88%|########7 | 42/48 [00:20<00:03,  1.78it/s]
 90%|########9 | 43/48 [00:21<00:02,  1.73it/s]
 90%|########9 | 43/48 [00:21<00:02,  1.73it/s]
 92%|#########1| 44/48 [00:21<00:02,  1.71it/s]
 92%|#########1| 44/48 [00:21<00:02,  1.71it/s]
 94%|#########3| 45/48 [00:22<00:01,  1.52it/s]
 94%|#########3| 45/48 [00:22<00:01,  1.52it/s]
 96%|#########5| 46/48 [00:23<00:01,  1.55it/s]
 96%|#########5| 46/48 [00:23<00:01,  1.55it/s]
 98%|#########7| 47/48 [00:23<00:00,  1.56it/s]
 98%|#########7| 47/48 [00:23<00:00,  1.56it/s]
+
+ - quantizing extras
+Moving transformer to CPU
+Loading text encoder
+
+
+Quantizing Text Encoder
+Loading VAEs and other components
+Making pipe
+Preparing Model
+Model Loaded
+create LoRA network. base dim (rank): 32, alpha: 32
+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: 1344 modules.
+enable LoRA for U-Net
+Dataset: /app/ai-toolkit/datasets/49
+  -  Preprocessing video dimensions
+
  0%|          | 0/140 [00:00<?, ?it/s]
  0%|          | 0/140 [00:00<?, ?it/s]
+
+  -  Found 140 videos
+Bucket sizes for /app/ai-toolkit/datasets/49:
+576x416: 78 files
+576x448: 44 files
+544x416: 16 files
+512x384: 2 files
+4 buckets made
+Caching latents for /app/ai-toolkit/datasets/49
+ - Saving latents to disk
+
+
+Caching text_embeddings for /app/ai-toolkit/datasets/49
+ - Saving text embeddings to disk
+
+
+Dataset: /app/ai-toolkit/datasets/73
+  -  Preprocessing video dimensions
+
  0%|          | 0/122 [00:00<?, ?it/s]
  0%|          | 0/122 [00:00<?, ?it/s]
 16%|#5        | 19/122 [00:00<00:00, 187.83it/s]
 16%|#5        | 19/122 [00:00<00:00, 187.83it/s]
 31%|###1      | 38/122 [00:00<00:00, 164.03it/s]
 31%|###1      | 38/122 [00:00<00:00, 164.03it/s]
 45%|####5     | 55/122 [00:00<00:00, 161.12it/s]
 45%|####5     | 55/122 [00:00<00:00, 161.12it/s]
+
+  -  Found 122 videos
+Bucket sizes for /app/ai-toolkit/datasets/73:
+576x416: 104 files
+576x448: 6 files
+672x384: 12 files
+3 buckets made
+Caching latents for /app/ai-toolkit/datasets/73
+ - Saving latents to disk
+
+
+Caching text_embeddings for /app/ai-toolkit/datasets/73
+ - Saving text embeddings to disk
+
+
+Dataset: /app/ai-toolkit/datasets/81
+  -  Preprocessing video dimensions
+
  0%|          | 0/2 [00:00<?, ?it/s]
  0%|          | 0/2 [00:00<?, ?it/s]
+
+  -  Found 2 videos
+Bucket sizes for /app/ai-toolkit/datasets/81:
+576x416: 2 files
+1 buckets made
+Caching latents for /app/ai-toolkit/datasets/81
+ - Saving latents to disk
+
+
+Caching text_embeddings for /app/ai-toolkit/datasets/81
+ - Saving text embeddings to disk
+
+
+Dataset: /app/ai-toolkit/datasets/89
+  -  Preprocessing video dimensions
+
  0%|          | 0/4 [00:00<?, ?it/s]
  0%|          | 0/4 [00:00<?, ?it/s]
+
+  -  Found 4 videos
+Bucket sizes for /app/ai-toolkit/datasets/89:
+576x416: 4 files
+1 buckets made
+Caching latents for /app/ai-toolkit/datasets/89
+ - Saving latents to disk
+
+
+Caching text_embeddings for /app/ai-toolkit/datasets/89
+ - Saving text embeddings to disk
+
+
+Dataset: /app/ai-toolkit/datasets/97
+  -  Preprocessing video dimensions
+
  0%|          | 0/58 [00:00<?, ?it/s]
  0%|          | 0/58 [00:00<?, ?it/s]
 26%|##5       | 15/58 [00:00<00:00, 146.08it/s]
 26%|##5       | 15/58 [00:00<00:00, 146.08it/s]
+
+  -  Found 58 videos
+Bucket sizes for /app/ai-toolkit/datasets/97:
+576x416: 46 files
+672x384: 4 files
+576x448: 8 files
+3 buckets made
+Caching latents for /app/ai-toolkit/datasets/97
+ - Saving latents to disk
+
+
+Caching text_embeddings for /app/ai-toolkit/datasets/97
+ - Saving text embeddings to disk
+
+
+Dataset: /app/ai-toolkit/datasets/images
+  -  Preprocessing image dimensions
+
  0%|          | 0/47 [00:00<?, ?it/s]
  0%|          | 0/47 [00:00<?, ?it/s]
 70%|#######   | 33/47 [00:00<00:00, 329.71it/s]
 70%|#######   | 33/47 [00:00<00:00, 329.71it/s]
+
+  -  Found 47 images
+Bucket sizes for /app/ai-toolkit/datasets/images:
+512x512: 46 files
+576x416: 1 files
+2 buckets made
+Caching latents for /app/ai-toolkit/datasets/images
+ - Saving latents to disk
+
+
+Caching text_embeddings for /app/ai-toolkit/datasets/images
+ - Saving text embeddings to disk
+
+
+Dataset: /app/ai-toolkit/datasets/images
+  -  Preprocessing image dimensions
+
  0%|          | 0/47 [00:00<?, ?it/s]
  0%|          | 0/47 [00:00<?, ?it/s]
+
+  -  Found 47 images
+Bucket sizes for /app/ai-toolkit/datasets/images:
+512x512: 39 files
+768x768: 7 files
+864x608: 1 files
+3 buckets made
+Caching latents for /app/ai-toolkit/datasets/images
+ - Saving latents to disk
+
+
+Caching text_embeddings for /app/ai-toolkit/datasets/images
+ - Saving text embeddings to disk
+
+
+Caching embeddings and unloading text encoder
+
+***** UNLOADING TEXT ENCODER *****
+Embeddings cached to disk. We dont need the text encoder anymore
+***********************************
+

loss_log.db

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c458df4ee077dc800fab502699c92766a5727ee41dbaff2e7fa45883484b006
+size 2482176

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3f825b0eee730ea333c1974d79d7c8bfe0ae347a73cf8d2d7c8e3009e865090
+size 626683383

pid.txt

@@ -0,0 +1 @@
+504