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

.job_config.json

@@ -0,0 +1,131 @@
+{
+  "job": "extension",
+  "config": {
+    "name": "LTX_BE_v1-1",
+    "process": [
+      {
+        "type": "diffusion_trainer",
+        "training_folder": "/workspace/output",
+        "sqlite_db_path": "/app/ai-toolkit/aitk_db.db",
+        "device": "cuda",
+        "trigger_word": "BR3AST3XPANSION",
+        "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": 200,
+          "max_step_saves_to_keep": 40,
+          "save_format": "diffusers",
+          "push_to_hub": false
+        },
+        "datasets": [
+          {
+            "folder_path": "/workspace/datasets/be_ltx_v1",
+            "mask_path": null,
+            "mask_min_value": 0.1,
+            "default_caption": "sudden BR3AST3XPANSION",
+            "caption_ext": "txt",
+            "caption_dropout_rate": 0.05,
+            "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,
+            "do_i2v": true,
+            "fps": 24,
+            "auto_frame_count": true
+          }
+        ],
+        "train": {
+          "batch_size": 1,
+          "bypass_guidance_embedding": false,
+          "steps": 1500,
+          "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": 0.0003,
+          "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",
+          "audio_loss_multiplier": 1
+        },
+        "logging": {
+          "log_every": 1,
+          "use_ui_logger": true
+        },
+        "model": {
+          "name_or_path": "Lightricks/LTX-2.3/ltx-2.3-22b-dev.safetensors",
+          "quantize": false,
+          "qtype": "qfloat8",
+          "quantize_te": false,
+          "qtype_te": "qfloat8",
+          "arch": "ltx2.3",
+          "low_vram": false,
+          "model_kwargs": {},
+          "compile": false,
+          "layer_offloading": false,
+          "layer_offloading_text_encoder_percent": 1,
+          "layer_offloading_transformer_percent": 1
+        },
+        "sample": {
+          "sampler": "flowmatch",
+          "sample_every": 250,
+          "sample_start_step": 0,
+          "width": 768,
+          "height": 768,
+          "samples": [],
+          "neg": "",
+          "seed": 42,
+          "walk_seed": true,
+          "guidance_scale": 4,
+          "sample_steps": 30,
+          "num_frames": 121,
+          "fps": 24
+        }
+      }
+    ]
+  },
+  "meta": {
+    "name": "[name]",
+    "version": "1.0"
+  }
+}

LTX_BE_v1-1.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0313821c456c435863e33e6cb522b96608fee9e20cf3e5927458d9b9b9240d12
+size 674249640

LTX_BE_v1-1_000000200.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f32a6d008b7036dfbb53daf9366d572437678ae148340a37af0637c7e286b70b
+size 674249640

LTX_BE_v1-1_000000340.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abbadda58cfb867005f8dfaccba95554fa020d8a785b93d9df9186f3e843ab49
+size 674249640

LTX_BE_v1-1_000000400.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3eebc9ae336e6b62222d0c7fd5a6e33841451e25955e2e2912378a0403ee01ed
+size 674249640

LTX_BE_v1-1_000000505.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0b160be942b10db46d1b18a7a2d9309154544319a1cf50c5ef66d8e4f763a1f
+size 674249640

LTX_BE_v1-1_000000600.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea1037f641de2c782976c008a309694382d844666e6a6129ba4d78a0d7d7641f
+size 674249640

LTX_BE_v1-1_000000800.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8c3a227ca2ecdf7bb65e3e577759f1db0fff64ebe1fbd728bcb107f053563dc
+size 674249640

LTX_BE_v1-1_000000910.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14d9b7dfe26cfc22857e15066deb24989c465d8aba5d706bbf8a15480a69c289
+size 674249640

LTX_BE_v1-1_000001000.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea5c959af5efb1d1e23d3cb68f3b6cbcb55173d6ead014764b89c3f4fcba7b60
+size 674249640

LTX_BE_v1-1_000001104.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:255ec356ef41600e3f67cf55c2580a22b1eadc99860426f7efa9dd118a6eebed
+size 674249640

LTX_BE_v1-1_000001200.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5930c768667e82166b7a505a6f8c06a591946d16cd72ac1dcc0d0330a14a54e
+size 674249640

LTX_BE_v1-1_000001314.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb0cf605d7664b19fb14da190cad17321754ee2d1e6357c4c5b85d3a5d8fcf5b
+size 674249640

LTX_BE_v1-1_000001400.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8101aa5ad5e687ac6e6ed8f95c9798a222f7f2669272eb06f701188d90829b4
+size 674249640

config.yaml

@@ -0,0 +1,111 @@
+job: extension
+config:
+  name: LTX_BE_v1-1
+  process:
+  - type: diffusion_trainer
+    training_folder: /workspace/output
+    sqlite_db_path: /app/ai-toolkit/aitk_db.db
+    device: cuda
+    trigger_word: BR3AST3XPANSION
+    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: 200
+      max_step_saves_to_keep: 40
+      save_format: diffusers
+      push_to_hub: false
+    datasets:
+    - folder_path: /workspace/datasets/be_ltx_v1
+      mask_path: null
+      mask_min_value: 0.1
+      default_caption: sudden BR3AST3XPANSION
+      caption_ext: txt
+      caption_dropout_rate: 0.05
+      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
+      do_i2v: true
+      fps: 24
+      auto_frame_count: true
+    train:
+      batch_size: 1
+      bypass_guidance_embedding: false
+      steps: 1500
+      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: 0.0003
+      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
+      audio_loss_multiplier: 1
+    logging:
+      log_every: 1
+      use_ui_logger: true
+    model:
+      name_or_path: Lightricks/LTX-2.3/ltx-2.3-22b-dev.safetensors
+      quantize: false
+      qtype: qfloat8
+      quantize_te: false
+      qtype_te: qfloat8
+      arch: ltx2.3
+      low_vram: false
+      model_kwargs: {}
+      compile: false
+      layer_offloading: false
+      layer_offloading_text_encoder_percent: 1
+      layer_offloading_transformer_percent: 1
+    sample:
+      sampler: flowmatch
+      sample_every: 250
+      sample_start_step: 0
+      width: 768
+      height: 768
+      samples: []
+      neg: ''
+      seed: 42
+      walk_seed: true
+      guidance_scale: 4
+      sample_steps: 30
+      num_frames: 121
+      fps: 24
+meta:
+  name: LTX_BE_v1-1
+  version: '1.0'

logs/0_log.txt

@@ -0,0 +1,201 @@
+Running 1 job
+{
+    "type": "diffusion_trainer",
+    "training_folder": "/workspace/output",
+    "sqlite_db_path": "/app/ai-toolkit/aitk_db.db",
+    "device": "cuda",
+    "trigger_word": "BR3AST3XPANSION",
+    "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": 200,
+        "max_step_saves_to_keep": 40,
+        "save_format": "diffusers",
+        "push_to_hub": false
+    },
+    "datasets": [
+        {
+            "folder_path": "/workspace/datasets/be_ltx_v1",
+            "mask_path": null,
+            "mask_min_value": 0.1,
+            "default_caption": "sudden BR3AST3XPANSION",
+            "caption_ext": "txt",
+            "caption_dropout_rate": 0.05,
+            "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,
+            "do_i2v": true,
+            "fps": 24,
+            "auto_frame_count": true
+        }
+    ],
+    "train": {
+        "batch_size": 1,
+        "bypass_guidance_embedding": false,
+        "steps": 1500,
+        "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": 0.0003,
+        "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",
+        "audio_loss_multiplier": 1
+    },
+    "logging": {
+        "log_every": 1,
+        "use_ui_logger": true
+    },
+    "model": {
+        "name_or_path": "Lightricks/LTX-2.3/ltx-2.3-22b-dev.safetensors",
+        "quantize": false,
+        "qtype": "qfloat8",
+        "quantize_te": false,
+        "qtype_te": "qfloat8",
+        "arch": "ltx2.3",
+        "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": 768,
+        "height": 768,
+        "samples": [],
+        "neg": "",
+        "seed": 42,
+        "walk_seed": true,
+        "guidance_scale": 4,
+        "sample_steps": 30,
+        "num_frames": 121,
+        "fps": 24
+    }
+}
+Changing sample extention to animated webp
+Using SQLite database at /app/ai-toolkit/aitk_db.db
+Job ID: "b0240487-7f95-4775-a534-492565634543"
+
+#############################################
+# Running job: LTX_BE_v1-1
+#############################################
+
+
+Running  1 process
+Loading LTX2 model
+Loading transformer
+Loading 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: 1632 modules.
+enable LoRA for U-Net
+Dataset: /workspace/datasets/be_ltx_v1
+  -  Preprocessing video dimensions
+
  0%|          | 0/16 [00:00<?, ?it/s]
+  -  Found 16 videos
+Bucket sizes for /workspace/datasets/be_ltx_v1:
+608x416x121f: 2 files
+416x608x97f: 3 files
+416x608x121f: 8 files
+448x576x121f: 1 files
+384x672x121f: 2 files
+5 buckets made
+Caching latents for /workspace/datasets/be_ltx_v1
+ - Saving latents to disk
+
+Caching text_embeddings for /workspace/datasets/be_ltx_v1
+ - Saving text embeddings to disk
+
+Dataset: /workspace/datasets/be_ltx_v1
+  -  Preprocessing video dimensions
+
  0%|          | 0/16 [00:00<?, ?it/s]
+  -  Found 16 videos
+Bucket sizes for /workspace/datasets/be_ltx_v1:
+960x608x121f: 2 files
+608x960x97f: 3 files
+608x960x121f: 4 files
+640x896x121f: 4 files
+672x864x121f: 1 files
+576x1024x121f: 2 files
+6 buckets made
+Caching latents for /workspace/datasets/be_ltx_v1
+ - Saving latents to disk
+
+Caching text_embeddings for /workspace/datasets/be_ltx_v1
+ - 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
+***********************************
+
+Compiled 48 transformer block(s) with torch.compile (mode='default', fullgraph=False, dynamic=True, cache_size_limit=96 (auto)).
+The first forward pass will be slow during compile. This is normal.
+If you are experiencing issues, disable block_compile.
+Skipping first sample due to config setting
+
+========================================
+Job stopped
+========================================

loss_log.db

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2f2af66de38cbaa0cf9caa54cd10b2d8f7c0bafeaa44ce3f035e04456dafb97
+size 294912

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db77d04136bbd2c551b258f7f40fb2f32d0629e643a79a6ac4f0f7636ca8b672
+size 686953195

pid.txt

@@ -0,0 +1 @@
+13094