Upload 183 files

qwen2509_object_removal_512/.job_config.json

@@ -0,0 +1,144 @@
+{
+  "job": "extension",
+  "config": {
+    "name": "qwen2509_object_removal_512",
+    "process": [
+      {
+        "type": "diffusion_trainer",
+        "training_folder": "/mnt/d/Github/ai-toolkit/output/",
+        "sqlite_db_path": "/mnt/d/Github/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": 4,
+          "save_format": "diffusers",
+          "push_to_hub": false
+        },
+        "datasets": [
+          {
+            "folder_path": "/mnt/d/Github/ai-toolkit/datasets/qwen_or/train/target",
+            "mask_path": null,
+            "mask_min_value": 0.1,
+            "default_caption": "Remove Object",
+            "caption_ext": "txt",
+            "caption_dropout_rate": 0.05,
+            "cache_latents_to_disk": true,
+            "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,
+            "control_path_1": "/mnt/d/Github/ai-toolkit/datasets/qwen_or/train/with_object",
+            "control_path_2": "/mnt/d/Github/ai-toolkit/datasets/qwen_or/train/mask",
+            "control_path_3": "/mnt/d/Github/ai-toolkit/datasets/qwen_or/train/mae_output"
+          }
+        ],
+        "train": {
+          "batch_size": 1,
+          "bypass_guidance_embedding": false,
+          "steps": 13582,
+          "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": 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": "Qwen/Qwen-Image-Edit-2509",
+          "quantize": true,
+          "qtype": "uint3|ostris/accuracy_recovery_adapters/qwen_image_edit_2509_torchao_uint3.safetensors",
+          "quantize_te": true,
+          "qtype_te": "uint4",
+          "arch": "qwen_image_edit_plus",
+          "low_vram": true,
+          "model_kwargs": {
+            "match_target_res": true
+          },
+          "layer_offloading": true,
+          "layer_offloading_text_encoder_percent": 0,
+          "layer_offloading_transformer_percent": 1
+        },
+        "sample": {
+          "sampler": "flowmatch",
+          "sample_every": 250,
+          "width": 512,
+          "height": 512,
+          "samples": [
+            {
+              "prompt": "Remove Object",
+              "ctrl_img_1": "/mnt/d/Github/ai-toolkit/data/images/8184cef5-9303-484b-bc7c-fd3d2e865e24.jpg",
+              "ctrl_img_2": "/mnt/d/Github/ai-toolkit/data/images/74de8410-0630-41b7-bf80-747bdc03df50.jpg",
+              "ctrl_img_3": "/mnt/d/Github/ai-toolkit/data/images/4b3a523f-8bd2-4db2-b734-ebe0b629f17a.jpg"
+            },
+            {
+              "prompt": "Remove Object",
+              "ctrl_img_1": "/mnt/d/Github/ai-toolkit/data/images/66a6d4bc-7c71-40f3-a8b7-55719a0d0596.jpg",
+              "ctrl_img_2": "/mnt/d/Github/ai-toolkit/data/images/3f7e34c1-54d0-4095-b4ed-ec7f8f3ed475.jpg",
+              "ctrl_img_3": "/mnt/d/Github/ai-toolkit/data/images/17521be8-a7fe-4240-9340-da1657874313.jpg"
+            },
+            {
+              "prompt": "Remove Object",
+              "ctrl_img_1": "/mnt/d/Github/ai-toolkit/data/images/dba76474-f415-4e8b-a410-caa17c1ea158.jpg",
+              "ctrl_img_2": "/mnt/d/Github/ai-toolkit/data/images/47b8f626-147d-41da-a8c0-6c21382ae206.jpg",
+              "ctrl_img_3": "/mnt/d/Github/ai-toolkit/data/images/7dfc0f6d-6c7f-4f09-b855-248f6f39614a.jpg"
+            }
+          ],
+          "neg": "",
+          "seed": 42,
+          "walk_seed": true,
+          "guidance_scale": 4,
+          "sample_steps": 25,
+          "num_frames": 1,
+          "fps": 1
+        }
+      }
+    ]
+  },
+  "meta": {
+    "name": "[name]",
+    "version": "1.0"
+  }
+}

qwen2509_object_removal_512/config.yaml

@@ -0,0 +1,117 @@
+job: extension
+config:
+  name: qwen2509_object_removal_512
+  process:
+  - type: diffusion_trainer
+    training_folder: /mnt/d/Github/ai-toolkit/output/
+    sqlite_db_path: /mnt/d/Github/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: 4
+      save_format: diffusers
+      push_to_hub: false
+    datasets:
+    - folder_path: /mnt/d/Github/ai-toolkit/datasets/qwen_or/train/target
+      mask_path: null
+      mask_min_value: 0.1
+      default_caption: Remove Object
+      caption_ext: txt
+      caption_dropout_rate: 0.05
+      cache_latents_to_disk: true
+      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
+      control_path_1: /mnt/d/Github/ai-toolkit/datasets/qwen_or/train/with_object
+      control_path_2: /mnt/d/Github/ai-toolkit/datasets/qwen_or/train/mask
+      control_path_3: /mnt/d/Github/ai-toolkit/datasets/qwen_or/train/mae_output
+    train:
+      batch_size: 1
+      bypass_guidance_embedding: false
+      steps: 13582
+      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: 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: Qwen/Qwen-Image-Edit-2509
+      quantize: true
+      qtype: uint3|ostris/accuracy_recovery_adapters/qwen_image_edit_2509_torchao_uint3.safetensors
+      quantize_te: true
+      qtype_te: uint4
+      arch: qwen_image_edit_plus
+      low_vram: true
+      model_kwargs:
+        match_target_res: true
+      layer_offloading: true
+      layer_offloading_text_encoder_percent: 0
+      layer_offloading_transformer_percent: 1
+    sample:
+      sampler: flowmatch
+      sample_every: 250
+      width: 512
+      height: 512
+      samples:
+      - prompt: Remove Object
+        ctrl_img_1: /mnt/d/Github/ai-toolkit/data/images/8184cef5-9303-484b-bc7c-fd3d2e865e24.jpg
+        ctrl_img_2: /mnt/d/Github/ai-toolkit/data/images/74de8410-0630-41b7-bf80-747bdc03df50.jpg
+        ctrl_img_3: /mnt/d/Github/ai-toolkit/data/images/4b3a523f-8bd2-4db2-b734-ebe0b629f17a.jpg
+      - prompt: Remove Object
+        ctrl_img_1: /mnt/d/Github/ai-toolkit/data/images/66a6d4bc-7c71-40f3-a8b7-55719a0d0596.jpg
+        ctrl_img_2: /mnt/d/Github/ai-toolkit/data/images/3f7e34c1-54d0-4095-b4ed-ec7f8f3ed475.jpg
+        ctrl_img_3: /mnt/d/Github/ai-toolkit/data/images/17521be8-a7fe-4240-9340-da1657874313.jpg
+      - prompt: Remove Object
+        ctrl_img_1: /mnt/d/Github/ai-toolkit/data/images/dba76474-f415-4e8b-a410-caa17c1ea158.jpg
+        ctrl_img_2: /mnt/d/Github/ai-toolkit/data/images/47b8f626-147d-41da-a8c0-6c21382ae206.jpg
+        ctrl_img_3: /mnt/d/Github/ai-toolkit/data/images/7dfc0f6d-6c7f-4f09-b855-248f6f39614a.jpg
+      neg: ''
+      seed: 42
+      walk_seed: true
+      guidance_scale: 4
+      sample_steps: 25
+      num_frames: 1
+      fps: 1
+meta:
+  name: qwen2509_object_removal_512
+  version: '1.0'

qwen2509_object_removal_512/logs/0_log.txt

@@ -0,0 +1,317 @@
+Running 1 job
+{
+    "type": "diffusion_trainer",
+    "training_folder": "D:\\Github\\ai-toolkit\\output",
+    "sqlite_db_path": "/mnt/d/Github/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": 4,
+        "save_format": "diffusers",
+        "push_to_hub": false
+    },
+    "datasets": [
+        {
+            "folder_path": "D:\\Github\\ai-toolkit\\datasets\\qwen_or\\train/mae_output",
+            "mask_path": null,
+            "mask_min_value": 0.1,
+            "default_caption": "Remove Object",
+            "caption_ext": "txt",
+            "caption_dropout_rate": 0.05,
+            "cache_latents_to_disk": true,
+            "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,
+            "control_path_1": "D:\\Github\\ai-toolkit\\datasets\\qwen_or\\train/with_object",
+            "control_path_2": "D:\\Github\\ai-toolkit\\datasets\\qwen_or\\train/mask",
+            "control_path_3": "D:\\Github\\ai-toolkit\\datasets\\qwen_or\\train/mae_output"
+        }
+    ],
+    "train": {
+        "batch_size": 1,
+        "bypass_guidance_embedding": false,
+        "steps": 13582,
+        "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": 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": "Qwen/Qwen-Image-Edit-2509",
+        "quantize": true,
+        "qtype": "uint3|ostris/accuracy_recovery_adapters/qwen_image_edit_2509_torchao_uint3.safetensors",
+        "quantize_te": true,
+        "qtype_te": "uint4",
+        "arch": "qwen_image_edit_plus",
+        "low_vram": true,
+        "model_kwargs": {
+            "match_target_res": true
+        },
+        "layer_offloading": true,
+        "layer_offloading_text_encoder_percent": 0,
+        "layer_offloading_transformer_percent": 1
+    },
+    "sample": {
+        "sampler": "flowmatch",
+        "sample_every": 250,
+        "width": 512,
+        "height": 512,
+        "samples": [
+            {
+                "prompt": "Remove Object",
+                "ctrl_img_1": "D:\\Github\\ai-toolkit\\data\\images\\7dd1fedd-6445-465d-a53b-4e351946420a.jpg",
+                "ctrl_img_2": "D:\\Github\\ai-toolkit\\data\\images\\1e1341a1-6079-44bb-9eb3-aac41fa2c07c.jpg",
+                "ctrl_img_3": "D:\\Github\\ai-toolkit\\data\\images\\f50ebe43-94e4-4b5a-a243-3ffec9f98542.jpg"
+            },
+            {
+                "prompt": "Remove Object",
+                "ctrl_img_1": "D:\\Github\\ai-toolkit\\data\\images\\a772832e-8670-40d8-ae54-3acdc19f5491.jpg",
+                "ctrl_img_2": "D:\\Github\\ai-toolkit\\data\\images\\77783712-d7fb-4ed4-b958-f12b26ce2fb0.jpg",
+                "ctrl_img_3": "D:\\Github\\ai-toolkit\\data\\images\\dfb20c07-2aef-4325-a855-573468ed0a68.jpg"
+            },
+            {
+                "prompt": "Remove Object",
+                "ctrl_img_1": "D:\\Github\\ai-toolkit\\data\\images\\54207063-d910-4070-9033-019359d11116.jpg",
+                "ctrl_img_2": "D:\\Github\\ai-toolkit\\data\\images\\4a2705bb-f1f1-4576-bb5b-3573b48913a9.jpg",
+                "ctrl_img_3": "D:\\Github\\ai-toolkit\\data\\images\\11bc3d9c-a786-4719-aa57-015677eb8cde.jpg"
+            }
+        ],
+        "neg": "",
+        "seed": 42,
+        "walk_seed": true,
+        "guidance_scale": 4,
+        "sample_steps": 25,
+        "num_frames": 1,
+        "fps": 1
+    }
+}
+Using SQLite database at /mnt/d/Github/ai-toolkit/aitk_db.db
+Job ID: "ab192e4e-2fbc-4fe0-8067-c4de78a005b2"
+
+#############################################
+# Running job: qwen2509_object_removal_512
+#############################################
+
+
+Running  1 process
+Loading Qwen Image model
+Loading transformer
+
+
+Quantizing Transformer
+Grabbing lora from the hub: ostris/accuracy_recovery_adapters/qwen_image_edit_2509_torchao_uint3.safetensors
+create LoRA network. base dim (rank): 16, alpha: 16
+neuron dropout: p=None, rank dropout: p=None, module dropout: p=None
+create LoRA for Text Encoder: 0 modules.
+create LoRA for U-Net: 846 modules.
+enable LoRA for U-Net
+Missing keys: []
+
+
+ - quantizing additional layers
+Moving transformer to CPU
+Text Encoder
+
+
+Quantizing Text Encoder
+Failed to quantize : Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.0: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.0.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.0.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.1: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.1.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.1.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.2: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.2.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.2.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.3: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.3.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.3.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.4: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.4.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.4.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.5: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.5.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.5.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.6: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.6.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.6.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.7: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.7.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.7.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.8: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.8.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.8.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.9: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.9.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.9.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.10: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.10.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.10.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.11: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.11.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.11.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.12: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.12.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.12.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.13: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.13.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.13.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.14: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.14.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.14.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.15: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.15.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.15.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.16: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.16.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.16.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.17: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.17.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.17.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.18: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.18.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.18.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.19: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.19.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.19.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.20: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.20.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.20.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.21: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.21.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.21.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.22: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.22.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.22.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.23: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.23.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.23.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.24: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.24.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.24.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.25: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.25.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.25.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.26: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.26.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.26.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.27: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.27.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.27.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.28: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.28.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.28.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.29: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.29.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.29.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.30: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.30.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.30.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.31: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.31.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.31.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Loading VAE
+Making pipe
+Preparing Model
+Model Loaded
+create LoRA network. base dim (rank): 16, alpha: 16
+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: 840 modules.
+enable LoRA for U-Net
+Error running job: [Errno 2] No such file or directory: 'D:\\Github\\ai-toolkit\\datasets\\qwen_or\\train/mae_output'
+
+========================================
+Result:
+ - 0 completed jobs
+ - 1 failure
+========================================
+Traceback (most recent call last):
+Traceback (most recent call last):
+  File "/mnt/d/Github/ai-toolkit/run.py", line 120, in <module>
+  File "/mnt/d/Github/ai-toolkit/run.py", line 120, in <module>
+        main()main()
+
+  File "/mnt/d/Github/ai-toolkit/run.py", line 108, in main
+  File "/mnt/d/Github/ai-toolkit/run.py", line 108, in main
+        raise eraise e
+
+  File "/mnt/d/Github/ai-toolkit/run.py", line 96, in main
+  File "/mnt/d/Github/ai-toolkit/run.py", line 96, in main
+        job.run()job.run()
+
+  File "/mnt/d/Github/ai-toolkit/jobs/ExtensionJob.py", line 22, in run
+  File "/mnt/d/Github/ai-toolkit/jobs/ExtensionJob.py", line 22, in run
+        process.run()process.run()
+
+  File "/mnt/d/Github/ai-toolkit/jobs/process/BaseSDTrainProcess.py", line 1995, in run
+  File "/mnt/d/Github/ai-toolkit/jobs/process/BaseSDTrainProcess.py", line 1995, in run
+        self.data_loader = get_dataloader_from_datasets(self.datasets, self.train_config.batch_size, self.sd)self.data_loader = get_dataloader_from_datasets(self.datasets, self.train_config.batch_size, self.sd)
+
+                                              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+  File "/mnt/d/Github/ai-toolkit/toolkit/data_loader.py", line 626, in get_dataloader_from_datasets
+  File "/mnt/d/Github/ai-toolkit/toolkit/data_loader.py", line 626, in get_dataloader_from_datasets
+        dataset = AiToolkitDataset(config, batch_size=batch_size, sd=sd)dataset = AiToolkitDataset(config, batch_size=batch_size, sd=sd)
+
+                            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+  File "/mnt/d/Github/ai-toolkit/toolkit/data_loader.py", line 431, in __init__
+  File "/mnt/d/Github/ai-toolkit/toolkit/data_loader.py", line 431, in __init__
+        with open(self.dataset_path, 'r') as f:with open(self.dataset_path, 'r') as f:
+
+                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+FileNotFoundErrorFileNotFoundError: : [Errno 2] No such file or directory: 'D:\\Github\\ai-toolkit\\datasets\\qwen_or\\train/mae_output'[Errno 2] No such file or directory: 'D:\\Github\\ai-toolkit\\datasets\\qwen_or\\train/mae_output'
+

qwen2509_object_removal_512/logs/2_log.txt

@@ -0,0 +1,181 @@
+Running 1 job
+{
+    "type": "diffusion_trainer",
+    "training_folder": "D:\\Github\\ai-toolkit\\output",
+    "sqlite_db_path": "/mnt/d/Github/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": 4,
+        "save_format": "diffusers",
+        "push_to_hub": false
+    },
+    "datasets": [
+        {
+            "folder_path": "/mnt/d/Github/ai-toolkit/datasets/qwen_or/train/target",
+            "mask_path": null,
+            "mask_min_value": 0.1,
+            "default_caption": "Remove Object",
+            "caption_ext": "txt",
+            "caption_dropout_rate": 0.05,
+            "cache_latents_to_disk": true,
+            "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,
+            "control_path_1": "/mnt/d/Github/ai-toolkit/datasets/qwen_or/train/with_object",
+            "control_path_2": "/mnt/d/Github/ai-toolkit/datasets/qwen_or/train/mask",
+            "control_path_3": "/mnt/d/Github/ai-toolkit/datasets/qwen_or/train/mae_output"
+        }
+    ],
+    "train": {
+        "batch_size": 1,
+        "bypass_guidance_embedding": false,
+        "steps": 13582,
+        "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": 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": "Qwen/Qwen-Image-Edit-2509",
+        "quantize": true,
+        "qtype": "uint3|ostris/accuracy_recovery_adapters/qwen_image_edit_2509_torchao_uint3.safetensors",
+        "quantize_te": true,
+        "qtype_te": "uint4",
+        "arch": "qwen_image_edit_plus",
+        "low_vram": true,
+        "model_kwargs": {
+            "match_target_res": true
+        },
+        "layer_offloading": true,
+        "layer_offloading_text_encoder_percent": 0,
+        "layer_offloading_transformer_percent": 1
+    },
+    "sample": {
+        "sampler": "flowmatch",
+        "sample_every": 250,
+        "width": 512,
+        "height": 512,
+        "samples": [
+            {
+                "prompt": "Remove Object",
+                "ctrl_img_1": "/mnt/d/Github/ai-toolkit/data/images/8184cef5-9303-484b-bc7c-fd3d2e865e24.jpg",
+                "ctrl_img_2": "/mnt/d/Github/ai-toolkit/data/images/74de8410-0630-41b7-bf80-747bdc03df50.jpg",
+                "ctrl_img_3": "/mnt/d/Github/ai-toolkit/data/images/4b3a523f-8bd2-4db2-b734-ebe0b629f17a.jpg"
+            },
+            {
+                "prompt": "Remove Object",
+                "ctrl_img_1": "/mnt/d/Github/ai-toolkit/data/images/66a6d4bc-7c71-40f3-a8b7-55719a0d0596.jpg",
+                "ctrl_img_2": "/mnt/d/Github/ai-toolkit/data/images/3f7e34c1-54d0-4095-b4ed-ec7f8f3ed475.jpg",
+                "ctrl_img_3": "/mnt/d/Github/ai-toolkit/data/images/17521be8-a7fe-4240-9340-da1657874313.jpg"
+            },
+            {
+                "prompt": "Remove Object",
+                "ctrl_img_1": "/mnt/d/Github/ai-toolkit/data/images/dba76474-f415-4e8b-a410-caa17c1ea158.jpg",
+                "ctrl_img_2": "/mnt/d/Github/ai-toolkit/data/images/47b8f626-147d-41da-a8c0-6c21382ae206.jpg",
+                "ctrl_img_3": "/mnt/d/Github/ai-toolkit/data/images/7dfc0f6d-6c7f-4f09-b855-248f6f39614a.jpg"
+            }
+        ],
+        "neg": "",
+        "seed": 42,
+        "walk_seed": true,
+        "guidance_scale": 4,
+        "sample_steps": 25,
+        "num_frames": 1,
+        "fps": 1
+    }
+}
+Using SQLite database at /mnt/d/Github/ai-toolkit/aitk_db.db
+Job ID: "ab192e4e-2fbc-4fe0-8067-c4de78a005b2"
+
+#############################################
+# Running job: qwen2509_object_removal_512
+#############################################
+
+
+Running  1 process
+Error running job: Job stopped
+
+========================================
+Result:
+ - 0 completed jobs
+ - 1 failure
+========================================
+Traceback (most recent call last):
+Traceback (most recent call last):
+  File "/mnt/d/Github/ai-toolkit/run.py", line 120, in <module>
+  File "/mnt/d/Github/ai-toolkit/run.py", line 120, in <module>
+        main()main()
+
+  File "/mnt/d/Github/ai-toolkit/run.py", line 108, in main
+  File "/mnt/d/Github/ai-toolkit/run.py", line 108, in main
+        raise eraise e
+
+  File "/mnt/d/Github/ai-toolkit/run.py", line 96, in main
+  File "/mnt/d/Github/ai-toolkit/run.py", line 96, in main
+        job.run()job.run()
+
+  File "/mnt/d/Github/ai-toolkit/jobs/ExtensionJob.py", line 22, in run
+  File "/mnt/d/Github/ai-toolkit/jobs/ExtensionJob.py", line 22, in run
+        process.run()process.run()
+
+  File "/mnt/d/Github/ai-toolkit/jobs/process/BaseSDTrainProcess.py", line 1513, in run
+  File "/mnt/d/Github/ai-toolkit/jobs/process/BaseSDTrainProcess.py", line 1513, in run
+        self.hook_before_model_load()self.hook_before_model_load()
+
+  File "/mnt/d/Github/ai-toolkit/extensions_built_in/sd_trainer/DiffusionTrainer.py", line 269, in hook_before_model_load
+  File "/mnt/d/Github/ai-toolkit/extensions_built_in/sd_trainer/DiffusionTrainer.py", line 269, in hook_before_model_load
+        self.maybe_stop()self.maybe_stop()
+
+  File "/mnt/d/Github/ai-toolkit/extensions_built_in/sd_trainer/DiffusionTrainer.py", line 147, in maybe_stop
+  File "/mnt/d/Github/ai-toolkit/extensions_built_in/sd_trainer/DiffusionTrainer.py", line 147, in maybe_stop
+        raise Exception("Job stopped")raise Exception("Job stopped")
+
+ExceptionException: : Job stoppedJob stopped
+

qwen2509_object_removal_512/logs/3_log.txt

@@ -0,0 +1,761 @@
+Running 1 job
+{
+    "type": "diffusion_trainer",
+    "training_folder": "D:\\Github\\ai-toolkit\\output",
+    "sqlite_db_path": "/mnt/d/Github/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,ten
+        "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": "/mnt/d/Github/ai-toolkit/datasets/qwen_or/train/target",
+            "mask_path": null,
+            "mask_min_value": 0.1,
+            "default_caption": "Remove Object",
+            "caption_ext": "txt",
+            "caption_dropout_rate": 0.05,
+            "cache_latents_to_disk": true,
+            "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,
+            "control_path_1": "/mnt/d/Github/ai-toolkit/datasets/qwen_or/train/with_object",
+            "control_path_2": "/mnt/d/Github/ai-toolkit/datasets/qwen_or/train/mask",
+            "control_path_3": "/mnt/d/Github/ai-toolkit/datasets/qwen_or/train/mae_output"
+        }
+    ],
+    "train": {
+        "batch_size": 1,
+        "bypass_guidance_embedding": false,
+        "steps": 13582,
+        "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": 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": "Qwen/Qwen-Image-Edit-2509",
+        "quantize": true,
+        "qtype": "uint3|ostris/accuracy_recovery_adapters/qwen_image_edit_2509_torchao_uint3.safetensors",
+        "quantize_te": true,
+        "qtype_te": "uint4",
+        "arch": "qwen_image_edit_plus",
+        "low_vram": true,
+        "model_kwargs": {
+            "match_target_res": true
+        },
+        "layer_offloading": true,
+        "layer_offloading_text_encoder_percent": 0,
+        "layer_offloading_transformer_percent": 1
+    },
+    "sample": {
+        "sampler": "flowmatch",
+        "sample_every": 250,
+        "width": 512,
+        "height": 512,
+        "samples": [
+            {
+                "prompt": "Remove Object",
+                "ctrl_img_1": "/mnt/d/Github/ai-toolkit/data/images/8184cef5-9303-484b-bc7c-fd3d2e865e24.jpg",
+                "ctrl_img_2": "/mnt/d/Github/ai-toolkit/data/images/74de8410-0630-41b7-bf80-747bdc03df50.jpg",
+                "ctrl_img_3": "/mnt/d/Github/ai-toolkit/data/images/4b3a523f-8bd2-4db2-b734-ebe0b629f17a.jpg"
+            },
+            {
+                "prompt": "Remove Object",
+                "ctrl_img_1": "/mnt/d/Github/ai-toolkit/data/images/66a6d4bc-7c71-40f3-a8b7-55719a0d0596.jpg",
+                "ctrl_img_2": "/mnt/d/Github/ai-toolkit/data/images/3f7e34c1-54d0-4095-b4ed-ec7f8f3ed475.jpg",
+                "ctrl_img_3": "/mnt/d/Github/ai-toolkit/data/images/17521be8-a7fe-4240-9340-da1657874313.jpg"
+            },
+            {
+                "prompt": "Remove Object",
+                "ctrl_img_1": "/mnt/d/Github/ai-toolkit/data/images/dba76474-f415-4e8b-a410-caa17c1ea158.jpg",
+                "ctrl_img_2": "/mnt/d/Github/ai-toolkit/data/images/47b8f626-147d-41da-a8c0-6c21382ae206.jpg",
+                "ctrl_img_3": "/mnt/d/Github/ai-toolkit/data/images/7dfc0f6d-6c7f-4f09-b855-248f6f39614a.jpg"
+            }
+        ],
+        "neg": "",
+        "seed": 42,
+        "walk_seed": true,
+        "guidance_scale": 4,
+        "sample_steps": 25,
+        "num_frames": 1,
+        "fps": 1
+    }
+}
+Using SQLite database at /mnt/d/Github/ai-toolkit/aitk_db.db
+Job ID: "ab192e4e-2fbc-4fe0-8067-c4de78a005b2"
+
+#############################################
+# Running job: qwen2509_object_removal_512
+#############################################
+
+
+Running  1 process
+Loading Qwen Image model
+Loading transformer
+
+Loading checkpoint shards:   0%|          | 0/5 [00:00<?, ?it/s]
+Loading checkpoint shards:   0%|          | 0/5 [00:00<?, ?it/s]
+Loading checkpoint shards:  20%|##        | 1/5 [00:00<00:00,  9.22it/s]
+Loading checkpoint shards:  20%|##        | 1/5 [00:00<00:00,  9.22it/s]
+Loading checkpoint shards:  40%|####      | 2/5 [00:00<00:00,  9.41it/s]
+Loading checkpoint shards:  40%|####      | 2/5 [00:00<00:00,  9.41it/s]
+Loading checkpoint shards:  60%|######    | 3/5 [00:00<00:00,  9.45it/s]
+Loading checkpoint shards:  60%|######    | 3/5 [00:00<00:00,  9.45it/s]
+Loading checkpoint shards:  80%|########  | 4/5 [00:00<00:00,  9.50it/s]
+Loading checkpoint shards:  80%|########  | 4/5 [00:00<00:00,  9.50it/s]
+Loading checkpoint shards: 100%|##########| 5/5 [00:00<00:00, 11.45it/s]
+Loading checkpoint shards: 100%|##########| 5/5 [00:00<00:00, 11.45it/s]
+
+Quantizing Transformer
+Grabbing lora from the hub: ostris/accuracy_recovery_adapters/qwen_image_edit_2509_torchao_uint3.safetensors
+create LoRA network. base dim (rank): 16, alpha: 16
+neuron dropout: p=None, rank dropout: p=None, module dropout: p=None
+create LoRA for Text Encoder: 0 modules.
+create LoRA for U-Net: 846 modules.
+enable LoRA for U-Net
+Missing keys: []
+
+Attaching quantization:   0%|          | 0/846 [00:00<?, ?it/s]
+Attaching quantization:   0%|          | 0/846 [00:00<?, ?it/s]
+Attaching quantization:   1%|          | 5/846 [00:00<00:31, 26.53it/s]
+Attaching quantization:   1%|          | 5/846 [00:00<00:31, 26.53it/s]
+Attaching quantization:   1%|1         | 12/846 [00:00<00:19, 43.12it/s]
+Attaching quantization:   1%|1         | 12/846 [00:00<00:19, 43.12it/s]
+Attaching quantization:   2%|2         | 17/846 [00:00<00:35, 23.11it/s]
+Attaching quantization:   2%|2         | 17/846 [00:00<00:35, 23.11it/s]
+Attaching quantization:   2%|2         | 21/846 [00:00<00:38, 21.70it/s]
+Attaching quantization:   2%|2         | 21/846 [00:00<00:38, 21.70it/s]
+Attaching quantization:   3%|3         | 28/846 [00:01<00:30, 26.80it/s]
+Attaching quantization:   3%|3         | 28/846 [00:01<00:30, 26.80it/s]
+Attaching quantization:   4%|3         | 32/846 [00:01<00:39, 20.42it/s]
+Attaching quantization:   4%|3         | 32/846 [00:01<00:39, 20.42it/s]
+Attaching quantization:   4%|4         | 35/846 [00:01<00:39, 20.64it/s]
+Attaching quantization:   4%|4         | 35/846 [00:01<00:39, 20.64it/s]
+Attaching quantization:   5%|4         | 42/846 [00:01<00:30, 26.19it/s]
+Attaching quantization:   5%|4         | 42/846 [00:01<00:30, 26.19it/s]
+Attaching quantization:   5%|5         | 45/846 [00:01<00:38, 21.06it/s]
+Attaching quantization:   5%|5         | 45/846 [00:01<00:38, 21.06it/s]
+Attaching quantization:   6%|5         | 48/846 [00:02<00:41, 19.46it/s]
+Attaching quantization:   6%|5         | 48/846 [00:02<00:41, 19.46it/s]
+Attaching quantization:   7%|6         | 55/846 [00:02<00:28, 27.95it/s]
+Attaching quantization:   7%|6         | 55/846 [00:02<00:28, 27.95it/s]
+Attaching quantization:   7%|6         | 59/846 [00:02<00:37, 21.04it/s]
+Attaching quantization:   7%|6         | 59/846 [00:02<00:37, 21.04it/s]
+Attaching quantization:   7%|7         | 62/846 [00:02<00:40, 19.60it/s]
+Attaching quantization:   7%|7         | 62/846 [00:02<00:40, 19.60it/s]
+Attaching quantization:   8%|8         | 69/846 [00:02<00:28, 27.65it/s]
+Attaching quantization:   8%|8         | 69/846 [00:02<00:28, 27.65it/s]
+Attaching quantization:   9%|8         | 73/846 [00:03<00:37, 20.58it/s]
+Attaching quantization:   9%|8         | 73/846 [00:03<00:37, 20.58it/s]
+Attaching quantization:   9%|8         | 76/846 [00:03<00:40, 18.98it/s]
+Attaching quantization:   9%|8         | 76/846 [00:03<00:40, 18.98it/s]
+Attaching quantization:  10%|9         | 83/846 [00:03<00:28, 26.78it/s]
+Attaching quantization:  10%|9         | 83/846 [00:03<00:28, 26.78it/s]
+Attaching quantization:  10%|#         | 87/846 [00:03<00:36, 20.62it/s]
+Attaching quantization:  10%|#         | 87/846 [00:03<00:36, 20.62it/s]
+Attaching quantization:  11%|#         | 90/846 [00:04<00:39, 19.23it/s]
+Attaching quantization:  11%|#         | 90/846 [00:04<00:39, 19.23it/s]
+Attaching quantization:  11%|#1        | 97/846 [00:04<00:27, 26.87it/s]
+Attaching quantization:  11%|#1        | 97/846 [00:04<00:27, 26.87it/s]
+Attaching quantization:  12%|#1        | 101/846 [00:04<00:36, 20.31it/s]
+Attaching quantization:  12%|#1        | 101/846 [00:04<00:36, 20.31it/s]
+Attaching quantization:  12%|#2        | 104/846 [00:04<00:39, 18.90it/s]
+Attaching quantization:  12%|#2        | 104/846 [00:04<00:39, 18.90it/s]
+Attaching quantization:  13%|#3        | 111/846 [00:04<00:27, 26.57it/s]
+Attaching quantization:  13%|#3        | 111/846 [00:04<00:27, 26.57it/s]
+Attaching quantization:  14%|#3        | 115/846 [00:05<00:36, 19.83it/s]
+Attaching quantization:  14%|#3        | 115/846 [00:05<00:36, 19.83it/s]
+Attaching quantization:  14%|#3        | 118/846 [00:05<00:39, 18.56it/s]
+Attaching quantization:  14%|#3        | 118/846 [00:05<00:39, 18.56it/s]
+Attaching quantization:  15%|#4        | 123/846 [00:05<00:31, 23.32it/s]
+Attaching quantization:  15%|#4        | 123/846 [00:05<00:31, 23.32it/s]
+Attaching quantization:  15%|#5        | 127/846 [00:05<00:32, 22.46it/s]
+Attaching quantization:  15%|#5        | 127/846 [00:05<00:32, 22.46it/s]
+Attaching quantization:  15%|#5        | 130/846 [00:05<00:39, 18.30it/s]
+Attaching quantization:  15%|#5        | 130/846 [00:05<00:39, 18.30it/s]
+Attaching quantization:  16%|#5        | 133/846 [00:06<00:38, 18.58it/s]
+Attaching quantization:  16%|#5        | 133/846 [00:06<00:38, 18.58it/s]
+Attaching quantization:  16%|#6        | 139/846 [00:06<00:27, 25.91it/s]
+Attaching quantization:  16%|#6        | 139/846 [00:06<00:27, 25.91it/s]
+Attaching quantization:  17%|#6        | 143/846 [00:06<00:36, 19.13it/s]
+Attaching quantization:  17%|#6        | 143/846 [00:06<00:36, 19.13it/s]
+Attaching quantization:  17%|#7        | 146/846 [00:06<00:39, 17.94it/s]
+Attaching quantization:  17%|#7        | 146/846 [00:06<00:39, 17.94it/s]
+Attaching quantization:  18%|#8        | 153/846 [00:06<00:26, 26.17it/s]
+Attaching quantization:  18%|#8        | 153/846 [00:06<00:26, 26.17it/s]
+Attaching quantization:  19%|#8        | 157/846 [00:07<00:35, 19.57it/s]
+Attaching quantization:  19%|#8        | 157/846 [00:07<00:35, 19.57it/s]
+Attaching quantization:  19%|#8        | 160/846 [00:07<00:39, 17.39it/s]
+Attaching quantization:  19%|#8        | 160/846 [00:07<00:39, 17.39it/s]
+Attaching quantization:  20%|#9        | 166/846 [00:07<00:29, 23.38it/s]
+Attaching quantization:  20%|#9        | 166/846 [00:07<00:29, 23.38it/s]
+Attaching quantization:  20%|##        | 170/846 [00:07<00:33, 19.95it/s]
+Attaching quantization:  20%|##        | 170/846 [00:07<00:33, 19.95it/s]
+Attaching quantization:  20%|##        | 173/846 [00:08<00:38, 17.43it/s]
+Attaching quantization:  20%|##        | 173/846 [00:08<00:38, 17.43it/s]
+Attaching quantization:  21%|##1       | 180/846 [00:08<00:26, 25.22it/s]
+Attaching quantization:  21%|##1       | 180/846 [00:08<00:26, 25.22it/s]
+Attaching quantization:  22%|##1       | 184/846 [00:08<00:31, 21.18it/s]
+Attaching quantization:  22%|##1       | 184/846 [00:08<00:31, 21.18it/s]
+Attaching quantization:  22%|##2       | 187/846 [00:08<00:37, 17.53it/s]
+Attaching quantization:  22%|##2       | 187/846 [00:08<00:37, 17.53it/s]
+Attaching quantization:  23%|##2       | 194/846 [00:08<00:26, 25.05it/s]
+Attaching quantization:  23%|##2       | 194/846 [00:08<00:26, 25.05it/s]
+Attaching quantization:  23%|##3       | 198/846 [00:09<00:30, 21.28it/s]
+Attaching quantization:  23%|##3       | 198/846 [00:09<00:30, 21.28it/s]
+Attaching quantization:  24%|##3       | 201/846 [00:09<00:35, 18.27it/s]
+Attaching quantization:  24%|##3       | 201/846 [00:09<00:35, 18.27it/s]
+Attaching quantization:  25%|##4       | 208/846 [00:09<00:25, 25.45it/s]
+Attaching quantization:  25%|##4       | 208/846 [00:09<00:25, 25.45it/s]
+Attaching quantization:  25%|##5       | 212/846 [00:09<00:31, 20.17it/s]
+Attaching quantization:  25%|##5       | 212/846 [00:09<00:31, 20.17it/s]
+Attaching quantization:  25%|##5       | 215/846 [00:10<00:37, 17.03it/s]
+Attaching quantization:  25%|##5       | 215/846 [00:10<00:37, 17.03it/s]
+Attaching quantization:  26%|##6       | 222/846 [00:10<00:25, 24.60it/s]
+Attaching quantization:  26%|##6       | 222/846 [00:10<00:25, 24.60it/s]
+Attaching quantization:  27%|##6       | 226/846 [00:10<00:31, 19.76it/s]
+Attaching quantization:  27%|##6       | 226/846 [00:10<00:31, 19.76it/s]
+Attaching quantization:  27%|##7       | 229/846 [00:10<00:36, 16.73it/s]
+Attaching quantization:  27%|##7       | 229/846 [00:10<00:36, 16.73it/s]
+Attaching quantization:  28%|##7       | 236/846 [00:10<00:25, 24.13it/s]
+Attaching quantization:  28%|##7       | 236/846 [00:10<00:25, 24.13it/s]
+Attaching quantization:  28%|##8       | 240/846 [00:11<00:29, 20.20it/s]
+Attaching quantization:  28%|##8       | 240/846 [00:11<00:29, 20.20it/s]
+Attaching quantization:  29%|##8       | 243/846 [00:11<00:35, 16.99it/s]
+Attaching quantization:  29%|##8       | 243/846 [00:11<00:35, 16.99it/s]
+Attaching quantization:  29%|##9       | 248/846 [00:11<00:27, 21.66it/s]
+Attaching quantization:  29%|##9       | 248/846 [00:11<00:27, 21.66it/s]
+Attaching quantization:  30%|##9       | 252/846 [00:11<00:25, 23.16it/s]
+Attaching quantization:  30%|##9       | 252/846 [00:11<00:25, 23.16it/s]
+Attaching quantization:  30%|###       | 255/846 [00:12<00:33, 17.60it/s]
+Attaching quantization:  30%|###       | 255/846 [00:12<00:33, 17.60it/s]
+Attaching quantization:  30%|###       | 258/846 [00:12<00:35, 16.34it/s]
+Attaching quantization:  30%|###       | 258/846 [00:12<00:35, 16.34it/s]
+Attaching quantization:  31%|###1      | 265/846 [00:12<00:23, 24.55it/s]
+Attaching quantization:  31%|###1      | 265/846 [00:12<00:23, 24.55it/s]
+Attaching quantization:  32%|###1      | 269/846 [00:12<00:31, 18.24it/s]
+Attaching quantization:  32%|###1      | 269/846 [00:12<00:31, 18.24it/s]
+Attaching quantization:  32%|###2      | 272/846 [00:12<00:33, 17.03it/s]
+Attaching quantization:  32%|###2      | 272/846 [00:12<00:33, 17.03it/s]
+Attaching quantization:  33%|###2      | 279/846 [00:13<00:22, 24.78it/s]
+Attaching quantization:  33%|###2      | 279/846 [00:13<00:22, 24.78it/s]
+Attaching quantization:  33%|###3      | 283/846 [00:13<00:30, 18.48it/s]
+Attaching quantization:  33%|###3      | 283/846 [00:13<00:30, 18.48it/s]
+Attaching quantization:  34%|###3      | 286/846 [00:13<00:34, 16.17it/s]
+Attaching quantization:  34%|###3      | 286/846 [00:13<00:34, 16.17it/s]
+Attaching quantization:  35%|###4      | 292/846 [00:13<00:24, 22.37it/s]
+Attaching quantization:  35%|###4      | 292/846 [00:13<00:24, 22.37it/s]
+Attaching quantization:  35%|###4      | 296/846 [00:14<00:33, 16.38it/s]
+Attaching quantization:  35%|###4      | 296/846 [00:14<00:33, 16.38it/s]
+Attaching quantization:  35%|###5      | 299/846 [00:14<00:42, 12.91it/s]
+Attaching quantization:  35%|###5      | 299/846 [00:14<00:42, 12.91it/s]
+Attaching quantization:  36%|###6      | 305/846 [00:14<00:29, 18.43it/s]
+Attaching quantization:  36%|###6      | 305/846 [00:14<00:29, 18.43it/s]
+Attaching quantization:  37%|###6      | 309/846 [00:14<00:29, 18.28it/s]
+Attaching quantization:  37%|###6      | 309/846 [00:14<00:29, 18.28it/s]
+Attaching quantization:  37%|###6      | 312/846 [00:15<00:37, 14.36it/s]
+Attaching quantization:  37%|###6      | 312/846 [00:15<00:37, 14.36it/s]
+Attaching quantization:  37%|###7      | 315/846 [00:15<00:37, 14.21it/s]
+Attaching quantization:  37%|###7      | 315/846 [00:15<00:37, 14.21it/s]
+Attaching quantization:  38%|###7      | 318/846 [00:15<00:32, 16.36it/s]
+Attaching quantization:  38%|###7      | 318/846 [00:15<00:32, 16.36it/s]
+Attaching quantization:  38%|###8      | 322/846 [00:15<00:30, 17.08it/s]
+Attaching quantization:  38%|###8      | 322/846 [00:15<00:30, 17.08it/s]
+Attaching quantization:  38%|###8      | 325/846 [00:16<00:39, 13.09it/s]
+Attaching quantization:  38%|###8      | 325/846 [00:16<00:39, 13.09it/s]
+Attaching quantization:  39%|###8      | 327/846 [00:16<00:51,  9.99it/s]
+Attaching quantization:  39%|###8      | 327/846 [00:16<00:51,  9.99it/s]
+Attaching quantization:  39%|###9      | 333/846 [00:16<00:32, 15.95it/s]
+Attaching quantization:  39%|###9      | 333/846 [00:16<00:32, 15.95it/s]
+Attaching quantization:  40%|###9      | 336/846 [00:16<00:33, 15.32it/s]
+Attaching quantization:  40%|###9      | 336/846 [00:16<00:33, 15.32it/s]
+Attaching quantization:  40%|####      | 339/846 [00:18<01:16,  6.65it/s]
+Attaching quantization:  40%|####      | 339/846 [00:18<01:16,  6.65it/s]
+Attaching quantization:  40%|####      | 341/846 [00:18<01:36,  5.24it/s]
+Attaching quantization:  40%|####      | 341/846 [00:18<01:36,  5.24it/s]
+Attaching quantization:  41%|####1     | 347/846 [00:18<00:55,  8.94it/s]
+Attaching quantization:  41%|####1     | 347/846 [00:18<00:55,  8.94it/s]
+Attaching quantization:  41%|####1     | 350/846 [00:19<00:51,  9.64it/s]
+Attaching quantization:  41%|####1     | 350/846 [00:19<00:51,  9.64it/s]
+Attaching quantization:  42%|####1     | 353/846 [00:19<01:06,  7.36it/s]
+Attaching quantization:  42%|####1     | 353/846 [00:19<01:06,  7.36it/s]
+Attaching quantization:  42%|####1     | 355/846 [00:21<01:53,  4.32it/s]
+Attaching quantization:  42%|####1     | 355/846 [00:21<01:53,  4.32it/s]
+Attaching quantization:  43%|####2     | 360/846 [00:21<01:09,  6.95it/s]
+Attaching quantization:  43%|####2     | 360/846 [00:21<01:09,  6.95it/s]
+Attaching quantization:  43%|####3     | 364/846 [00:23<01:58,  4.06it/s]
+Attaching quantization:  43%|####3     | 364/846 [00:23<01:58,  4.06it/s]
+Attaching quantization:  43%|####3     | 366/846 [00:23<02:03,  3.90it/s]
+Attaching quantization:  43%|####3     | 366/846 [00:23<02:03,  3.90it/s]
+Attaching quantization:  43%|####3     | 368/846 [00:23<01:49,  4.38it/s]
+Attaching quantization:  43%|####3     | 368/846 [00:23<01:49,  4.38it/s]
+Attaching quantization:  44%|####3     | 370/846 [00:24<01:42,  4.67it/s]
+Attaching quantization:  44%|####3     | 370/846 [00:24<01:42,  4.67it/s]
+Attaching quantization:  44%|####4     | 376/846 [00:24<00:55,  8.51it/s]
+Attaching quantization:  44%|####4     | 376/846 [00:24<00:55,  8.51it/s]
+Attaching quantization:  45%|####4     | 379/846 [00:24<01:00,  7.66it/s]
+Attaching quantization:  45%|####4     | 379/846 [00:24<01:00,  7.66it/s]
+Attaching quantization:  45%|####5     | 381/846 [00:25<01:19,  5.82it/s]
+Attaching quantization:  45%|####5     | 381/846 [00:25<01:19,  5.82it/s]
+Attaching quantization:  45%|####5     | 383/846 [00:26<01:39,  4.65it/s]
+Attaching quantization:  45%|####5     | 383/846 [00:26<01:39,  4.65it/s]
+Attaching quantization:  46%|####5     | 388/846 [00:26<00:59,  7.75it/s]
+Attaching quantization:  46%|####5     | 388/846 [00:26<00:59,  7.75it/s]
+Attaching quantization:  46%|####6     | 392/846 [00:26<00:51,  8.84it/s]
+Attaching quantization:  46%|####6     | 392/846 [00:26<00:51,  8.84it/s]
+Attaching quantization:  47%|####6     | 394/846 [00:27<01:00,  7.50it/s]
+Attaching quantization:  47%|####6     | 394/846 [00:27<01:00,  7.50it/s]
+Attaching quantization:  47%|####6     | 396/846 [00:27<01:00,  7.40it/s]
+Attaching quantization:  47%|####6     | 396/846 [00:27<01:00,  7.40it/s]
+Attaching quantization:  47%|####7     | 398/846 [00:27<01:06,  6.76it/s]
+Attaching quantization:  47%|####7     | 398/846 [00:27<01:06,  6.76it/s]
+Attaching quantization:  48%|####7     | 402/846 [00:27<00:43, 10.13it/s]
+Attaching quantization:  48%|####7     | 402/846 [00:27<00:43, 10.13it/s]
+Attaching quantization:  48%|####7     | 406/846 [00:28<00:39, 11.07it/s]
+Attaching quantization:  48%|####7     | 406/846 [00:28<00:39, 11.07it/s]
+Attaching quantization:  48%|####8     | 408/846 [00:28<00:52,  8.31it/s]
+Attaching quantization:  48%|####8     | 408/846 [00:28<00:52,  8.31it/s]
+Attaching quantization:  48%|####8     | 410/846 [00:29<01:08,  6.40it/s]
+Attaching quantization:  48%|####8     | 410/846 [00:29<01:08,  6.40it/s]
+Attaching quantization:  49%|####8     | 412/846 [00:29<01:08,  6.38it/s]
+Attaching quantization:  49%|####8     | 412/846 [00:29<01:08,  6.38it/s]
+Attaching quantization:  49%|####9     | 417/846 [00:29<00:40, 10.71it/s]
+Attaching quantization:  49%|####9     | 417/846 [00:29<00:40, 10.71it/s]
+Attaching quantization:  50%|####9     | 420/846 [00:29<00:40, 10.41it/s]
+Attaching quantization:  50%|####9     | 420/846 [00:29<00:40, 10.41it/s]
+Attaching quantization:  50%|####9     | 422/846 [00:30<00:53,  7.90it/s]
+Attaching quantization:  50%|####9     | 422/846 [00:30<00:53,  7.90it/s]
+Attaching quantization:  50%|#####     | 424/846 [00:30<00:56,  7.50it/s]
+Attaching quantization:  50%|#####     | 424/846 [00:30<00:56,  7.50it/s]
+Attaching quantization:  50%|#####     | 426/846 [00:31<00:58,  7.14it/s]
+Attaching quantization:  50%|#####     | 426/846 [00:31<00:58,  7.14it/s]
+Attaching quantization:  51%|#####1    | 432/846 [00:31<00:32, 12.92it/s]
+Attaching quantization:  51%|#####1    | 432/846 [00:31<00:32, 12.92it/s]
+Attaching quantization:  51%|#####1    | 435/846 [00:31<00:39, 10.35it/s]
+Attaching quantization:  51%|#####1    | 435/846 [00:31<00:39, 10.35it/s]
+Attaching quantization:  52%|#####1    | 437/846 [00:31<00:46,  8.84it/s]
+Attaching quantization:  52%|#####1    | 437/846 [00:31<00:46,  8.84it/s]
+Attaching quantization:  52%|#####1    | 439/846 [00:32<00:54,  7.43it/s]
+Attaching quantization:  52%|#####1    | 439/846 [00:32<00:54,  7.43it/s]
+Attaching quantization:  53%|#####2    | 445/846 [00:32<00:30, 12.95it/s]
+Attaching quantization:  53%|#####2    | 445/846 [00:32<00:30, 12.95it/s]
+Attaching quantization:  53%|#####2    | 448/846 [00:32<00:31, 12.63it/s]
+Attaching quantization:  53%|#####2    | 448/846 [00:32<00:31, 12.63it/s]
+Attaching quantization:  53%|#####3    | 451/846 [00:33<00:38, 10.28it/s]
+Attaching quantization:  53%|#####3    | 451/846 [00:33<00:38, 10.28it/s]
+Attaching quantization:  54%|#####3    | 453/846 [00:33<00:47,  8.30it/s]
+Attaching quantization:  54%|#####3    | 453/846 [00:33<00:47,  8.30it/s]
+Attaching quantization:  54%|#####4    | 459/846 [00:33<00:27, 13.83it/s]
+Attaching quantization:  54%|#####4    | 459/846 [00:33<00:27, 13.83it/s]
+Attaching quantization:  55%|#####4    | 462/846 [00:34<00:29, 13.09it/s]
+Attaching quantization:  55%|#####4    | 462/846 [00:34<00:29, 13.09it/s]
+Attaching quantization:  55%|#####4    | 465/846 [00:34<00:36, 10.48it/s]
+Attaching quantization:  55%|#####4    | 465/846 [00:34<00:36, 10.48it/s]
+Attaching quantization:  55%|#####5    | 467/846 [00:34<00:41,  9.10it/s]
+Attaching quantization:  55%|#####5    | 467/846 [00:34<00:41,  9.10it/s]
+Attaching quantization:  56%|#####5    | 473/846 [00:34<00:25, 14.73it/s]
+Attaching quantization:  56%|#####5    | 473/846 [00:34<00:25, 14.73it/s]
+Attaching quantization:  56%|#####6    | 476/846 [00:35<00:25, 14.48it/s]
+Attaching quantization:  56%|#####6    | 476/846 [00:35<00:25, 14.48it/s]
+Attaching quantization:  57%|#####6    | 479/846 [00:35<00:33, 10.95it/s]
+Attaching quantization:  57%|#####6    | 479/846 [00:35<00:33, 10.95it/s]
+Attaching quantization:  57%|#####6    | 481/846 [00:35<00:38,  9.41it/s]
+Attaching quantization:  57%|#####6    | 481/846 [00:35<00:38,  9.41it/s]
+Attaching quantization:  57%|#####7    | 486/846 [00:36<00:25, 14.10it/s]
+Attaching quantization:  57%|#####7    | 486/846 [00:36<00:25, 14.10it/s]
+Attaching quantization:  58%|#####7    | 490/846 [00:36<00:24, 14.78it/s]
+Attaching quantization:  58%|#####7    | 490/846 [00:36<00:24, 14.78it/s]
+Attaching quantization:  58%|#####8    | 493/846 [00:36<00:30, 11.53it/s]
+Attaching quantization:  58%|#####8    | 493/846 [00:36<00:30, 11.53it/s]
+Attaching quantization:  59%|#####8    | 495/846 [00:37<00:35,  9.82it/s]
+Attaching quantization:  59%|#####8    | 495/846 [00:37<00:35,  9.82it/s]
+Attaching quantization:  59%|#####9    | 501/846 [00:37<00:22, 15.68it/s]
+Attaching quantization:  59%|#####9    | 501/846 [00:37<00:22, 15.68it/s]
+Attaching quantization:  60%|#####9    | 504/846 [00:37<00:22, 15.21it/s]
+Attaching quantization:  60%|#####9    | 504/846 [00:37<00:22, 15.21it/s]
+Attaching quantization:  60%|#####9    | 507/846 [00:37<00:29, 11.32it/s]
+Attaching quantization:  60%|#####9    | 507/846 [00:37<00:29, 11.32it/s]
+Attaching quantization:  60%|######    | 509/846 [00:38<00:35,  9.55it/s]
+Attaching quantization:  60%|######    | 509/846 [00:38<00:35,  9.55it/s]
+Attaching quantization:  61%|######    | 515/846 [00:38<00:21, 15.45it/s]
+Attaching quantization:  61%|######    | 515/846 [00:38<00:21, 15.45it/s]
+Attaching quantization:  61%|######1   | 518/846 [00:38<00:21, 15.17it/s]
+Attaching quantization:  61%|######1   | 518/846 [00:38<00:21, 15.17it/s]
+Attaching quantization:  62%|######1   | 521/846 [00:38<00:26, 12.43it/s]
+Attaching quantization:  62%|######1   | 521/846 [00:38<00:26, 12.43it/s]
+Attaching quantization:  62%|######1   | 523/846 [00:39<00:30, 10.68it/s]
+Attaching quantization:  62%|######1   | 523/846 [00:39<00:30, 10.68it/s]
+Attaching quantization:  63%|######2   | 529/846 [00:39<00:18, 17.06it/s]
+Attaching quantization:  63%|######2   | 529/846 [00:39<00:18, 17.06it/s]
+Attaching quantization:  63%|######2   | 532/846 [00:39<00:18, 17.08it/s]
+Attaching quantization:  63%|######2   | 532/846 [00:39<00:18, 17.08it/s]
+Attaching quantization:  63%|######3   | 535/846 [00:39<00:23, 13.34it/s]
+Attaching quantization:  63%|######3   | 535/846 [00:39<00:23, 13.34it/s]
+Attaching quantization:  63%|######3   | 537/846 [00:40<00:27, 11.27it/s]
+Attaching quantization:  63%|######3   | 537/846 [00:40<00:27, 11.27it/s]
+Attaching quantization:  64%|######4   | 543/846 [00:40<00:16, 17.83it/s]
+Attaching quantization:  64%|######4   | 543/846 [00:40<00:16, 17.83it/s]
+Attaching quantization:  65%|######4   | 546/846 [00:40<00:17, 17.16it/s]
+Attaching quantization:  65%|######4   | 546/846 [00:40<00:17, 17.16it/s]
+Attaching quantization:  65%|######4   | 549/846 [00:40<00:22, 13.24it/s]
+Attaching quantization:  65%|######4   | 549/846 [00:40<00:22, 13.24it/s]
+Attaching quantization:  65%|######5   | 551/846 [00:41<00:26, 11.21it/s]
+Attaching quantization:  65%|######5   | 551/846 [00:41<00:26, 11.21it/s]
+Attaching quantization:  66%|######5   | 557/846 [00:41<00:16, 17.56it/s]
+Attaching quantization:  66%|######5   | 557/846 [00:41<00:16, 17.56it/s]
+Attaching quantization:  66%|######6   | 560/846 [00:41<00:16, 17.58it/s]
+Attaching quantization:  66%|######6   | 560/846 [00:41<00:16, 17.58it/s]
+Attaching quantization:  67%|######6   | 563/846 [00:41<00:20, 13.72it/s]
+Attaching quantization:  67%|######6   | 563/846 [00:41<00:20, 13.72it/s]
+Attaching quantization:  67%|######6   | 565/846 [00:41<00:25, 11.12it/s]
+Attaching quantization:  67%|######6   | 565/846 [00:41<00:25, 11.12it/s]
+Attaching quantization:  67%|######7   | 570/846 [00:42<00:17, 16.12it/s]
+Attaching quantization:  67%|######7   | 570/846 [00:42<00:17, 16.12it/s]
+Attaching quantization:  68%|######7   | 574/846 [00:42<00:16, 16.29it/s]
+Attaching quantization:  68%|######7   | 574/846 [00:42<00:16, 16.29it/s]
+Attaching quantization:  68%|######8   | 577/846 [00:42<00:20, 12.89it/s]
+Attaching quantization:  68%|######8   | 577/846 [00:42<00:20, 12.89it/s]
+Attaching quantization:  68%|######8   | 579/846 [00:42<00:23, 11.23it/s]
+Attaching quantization:  68%|######8   | 579/846 [00:42<00:23, 11.23it/s]
+Attaching quantization:  69%|######9   | 584/846 [00:43<00:16, 16.32it/s]
+Attaching quantization:  69%|######9   | 584/846 [00:43<00:16, 16.32it/s]
+Attaching quantization:  70%|######9   | 588/846 [00:43<00:15, 16.71it/s]
+Attaching quantization:  70%|######9   | 588/846 [00:43<00:15, 16.71it/s]
+Attaching quantization:  70%|######9   | 591/846 [00:43<00:20, 12.62it/s]
+Attaching quantization:  70%|######9   | 591/846 [00:43<00:20, 12.62it/s]
+Attaching quantization:  70%|#######   | 593/846 [00:44<00:23, 10.76it/s]
+Attaching quantization:  70%|#######   | 593/846 [00:44<00:23, 10.76it/s]
+Attaching quantization:  71%|#######   | 598/846 [00:44<00:15, 15.80it/s]
+Attaching quantization:  71%|#######   | 598/846 [00:44<00:15, 15.80it/s]
+Attaching quantization:  71%|#######1  | 602/846 [00:44<00:14, 17.22it/s]
+Attaching quantization:  71%|#######1  | 602/846 [00:44<00:14, 17.22it/s]
+Attaching quantization:  72%|#######1  | 605/846 [00:44<00:18, 13.22it/s]
+Attaching quantization:  72%|#######1  | 605/846 [00:44<00:18, 13.22it/s]
+Attaching quantization:  72%|#######1  | 607/846 [00:44<00:21, 11.30it/s]
+Attaching quantization:  72%|#######1  | 607/846 [00:44<00:21, 11.30it/s]
+Attaching quantization:  72%|#######2  | 613/846 [00:45<00:13, 17.87it/s]
+Attaching quantization:  72%|#######2  | 613/846 [00:45<00:13, 17.87it/s]
+Attaching quantization:  73%|#######2  | 616/846 [00:45<00:12, 18.11it/s]
+Attaching quantization:  73%|#######2  | 616/846 [00:45<00:12, 18.11it/s]
+Attaching quantization:  73%|#######3  | 619/846 [00:45<00:16, 13.54it/s]
+Attaching quantization:  73%|#######3  | 619/846 [00:45<00:16, 13.54it/s]
+Attaching quantization:  74%|#######3  | 622/846 [00:45<00:18, 12.40it/s]
+Attaching quantization:  74%|#######3  | 622/846 [00:45<00:18, 12.40it/s]
+Attaching quantization:  74%|#######4  | 628/846 [00:46<00:11, 18.62it/s]
+Attaching quantization:  74%|#######4  | 628/846 [00:46<00:11, 18.62it/s]
+Attaching quantization:  75%|#######4  | 631/846 [00:46<00:13, 16.13it/s]
+Attaching quantization:  75%|#######4  | 631/846 [00:46<00:13, 16.13it/s]
+Attaching quantization:  75%|#######4  | 634/846 [00:46<00:16, 12.90it/s]
+Attaching quantization:  75%|#######4  | 634/846 [00:46<00:16, 12.90it/s]
+Attaching quantization:  75%|#######5  | 636/846 [00:46<00:16, 12.43it/s]
+Attaching quantization:  75%|#######5  | 636/846 [00:46<00:16, 12.43it/s]
+Attaching quantization:  76%|#######6  | 644/846 [00:47<00:10, 18.61it/s]
+Attaching quantization:  76%|#######6  | 644/846 [00:47<00:10, 18.61it/s]
+Attaching quantization:  76%|#######6  | 647/846 [00:47<00:13, 14.90it/s]
+Attaching quantization:  76%|#######6  | 647/846 [00:47<00:13, 14.90it/s]
+Attaching quantization:  77%|#######6  | 649/846 [00:47<00:16, 11.90it/s]
+Attaching quantization:  77%|#######6  | 649/846 [00:47<00:16, 11.90it/s]
+Attaching quantization:  78%|#######7  | 657/846 [00:47<00:09, 20.19it/s]
+Attaching quantization:  78%|#######7  | 657/846 [00:47<00:09, 20.19it/s]
+Attaching quantization:  78%|#######8  | 661/846 [00:48<00:19,  9.35it/s]
+Attaching quantization:  78%|#######8  | 661/846 [00:48<00:19,  9.35it/s]
+Attaching quantization:  78%|#######8  | 664/846 [00:49<00:18,  9.58it/s]
+Attaching quantization:  78%|#######8  | 664/846 [00:49<00:18,  9.58it/s]
+Attaching quantization:  79%|#######9  | 672/846 [00:49<00:12, 14.36it/s]
+Attaching quantization:  79%|#######9  | 672/846 [00:49<00:12, 14.36it/s]
+Attaching quantization:  80%|#######9  | 675/846 [00:49<00:13, 12.92it/s]
+Attaching quantization:  80%|#######9  | 675/846 [00:49<00:13, 12.92it/s]
+Attaching quantization:  80%|########  | 677/846 [00:50<00:14, 11.82it/s]
+Attaching quantization:  80%|########  | 677/846 [00:50<00:14, 11.82it/s]
+Attaching quantization:  81%|########  | 684/846 [00:50<00:08, 18.50it/s]
+Attaching quantization:  81%|########  | 684/846 [00:50<00:08, 18.50it/s]
+Attaching quantization:  81%|########1 | 688/846 [00:50<00:09, 16.36it/s]
+Attaching quantization:  81%|########1 | 688/846 [00:50<00:09, 16.36it/s]
+Attaching quantization:  82%|########1 | 691/846 [00:50<00:10, 14.66it/s]
+Attaching quantization:  82%|########1 | 691/846 [00:50<00:10, 14.66it/s]
+Attaching quantization:  83%|########2 | 700/846 [00:50<00:06, 22.45it/s]
+Attaching quantization:  83%|########2 | 700/846 [00:50<00:06, 22.45it/s]
+Attaching quantization:  83%|########3 | 704/846 [00:51<00:07, 17.98it/s]
+Attaching quantization:  83%|########3 | 704/846 [00:51<00:07, 17.98it/s]
+Attaching quantization:  84%|########3 | 707/846 [00:51<00:07, 18.42it/s]
+Attaching quantization:  84%|########3 | 707/846 [00:51<00:07, 18.42it/s]
+Attaching quantization:  84%|########4 | 714/846 [00:51<00:05, 24.22it/s]
+Attaching quantization:  84%|########4 | 714/846 [00:51<00:05, 24.22it/s]
+Attaching quantization:  85%|########4 | 717/846 [00:51<00:06, 19.63it/s]
+Attaching quantization:  85%|########4 | 717/846 [00:51<00:06, 19.63it/s]
+Attaching quantization:  85%|########5 | 720/846 [00:52<00:06, 18.26it/s]
+Attaching quantization:  85%|########5 | 720/846 [00:52<00:06, 18.26it/s]
+Attaching quantization:  86%|########6 | 728/846 [00:52<00:04, 25.30it/s]
+Attaching quantization:  86%|########6 | 728/846 [00:52<00:04, 25.30it/s]
+Attaching quantization:  86%|########6 | 731/846 [00:52<00:05, 20.12it/s]
+Attaching quantization:  86%|########6 | 731/846 [00:52<00:05, 20.12it/s]
+Attaching quantization:  87%|########6 | 734/846 [00:52<00:06, 18.49it/s]
+Attaching quantization:  87%|########6 | 734/846 [00:52<00:06, 18.49it/s]
+Attaching quantization:  88%|########7 | 742/846 [00:52<00:04, 25.14it/s]
+Attaching quantization:  88%|########7 | 742/846 [00:52<00:04, 25.14it/s]
+Attaching quantization:  88%|########8 | 745/846 [00:53<00:05, 20.19it/s]
+Attaching quantization:  88%|########8 | 745/846 [00:53<00:05, 20.19it/s]
+Attaching quantization:  88%|########8 | 748/846 [00:53<00:05, 18.40it/s]
+Attaching quantization:  88%|########8 | 748/846 [00:53<00:05, 18.40it/s]
+Attaching quantization:  89%|########9 | 756/846 [00:53<00:03, 25.60it/s]
+Attaching quantization:  89%|########9 | 756/846 [00:53<00:03, 25.60it/s]
+Attaching quantization:  90%|########9 | 759/846 [00:53<00:04, 20.21it/s]
+Attaching quantization:  90%|########9 | 759/846 [00:53<00:04, 20.21it/s]
+Attaching quantization:  90%|######### | 762/846 [00:54<00:04, 18.54it/s]
+Attaching quantization:  90%|######### | 762/846 [00:54<00:04, 18.54it/s]
+Attaching quantization:  91%|#########1| 770/846 [00:54<00:03, 25.33it/s]
+Attaching quantization:  91%|#########1| 770/846 [00:54<00:03, 25.33it/s]
+Attaching quantization:  91%|#########1| 773/846 [00:54<00:03, 20.17it/s]
+Attaching quantization:  91%|#########1| 773/846 [00:54<00:03, 20.17it/s]
+Attaching quantization:  92%|#########1| 776/846 [00:54<00:03, 18.28it/s]
+Attaching quantization:  92%|#########1| 776/846 [00:54<00:03, 18.28it/s]
+Attaching quantization:  93%|#########2| 784/846 [00:54<00:02, 24.91it/s]
+Attaching quantization:  93%|#########2| 784/846 [00:54<00:02, 24.91it/s]
+Attaching quantization:  93%|#########3| 787/846 [00:55<00:02, 19.93it/s]
+Attaching quantization:  93%|#########3| 787/846 [00:55<00:02, 19.93it/s]
+Attaching quantization:  93%|#########3| 790/846 [00:55<00:03, 18.37it/s]
+Attaching quantization:  93%|#########3| 790/846 [00:55<00:03, 18.37it/s]
+Attaching quantization:  94%|#########4| 798/846 [00:55<00:01, 25.35it/s]
+Attaching quantization:  94%|#########4| 798/846 [00:55<00:01, 25.35it/s]
+Attaching quantization:  95%|#########4| 801/846 [00:55<00:02, 20.28it/s]
+Attaching quantization:  95%|#########4| 801/846 [00:55<00:02, 20.28it/s]
+Attaching quantization:  95%|#########5| 804/846 [00:56<00:02, 18.52it/s]
+Attaching quantization:  95%|#########5| 804/846 [00:56<00:02, 18.52it/s]
+Attaching quantization:  96%|#########5| 812/846 [00:56<00:01, 25.59it/s]
+Attaching quantization:  96%|#########5| 812/846 [00:56<00:01, 25.59it/s]
+Attaching quantization:  96%|#########6| 815/846 [00:56<00:01, 20.46it/s]
+Attaching quantization:  96%|#########6| 815/846 [00:56<00:01, 20.46it/s]
+Attaching quantization:  97%|#########6| 818/846 [00:56<00:01, 18.82it/s]
+Attaching quantization:  97%|#########6| 818/846 [00:56<00:01, 18.82it/s]
+Attaching quantization:  98%|#########7| 826/846 [00:56<00:00, 26.21it/s]
+Attaching quantization:  98%|#########7| 826/846 [00:56<00:00, 26.21it/s]
+Attaching quantization:  98%|#########7| 829/846 [00:57<00:00, 20.73it/s]
+Attaching quantization:  98%|#########7| 829/846 [00:57<00:00, 20.73it/s]
+Attaching quantization:  98%|#########8| 832/846 [00:57<00:00, 19.06it/s]
+Attaching quantization:  98%|#########8| 832/846 [00:57<00:00, 19.06it/s]
+Attaching quantization:  99%|#########9| 840/846 [00:57<00:00, 26.15it/s]
+Attaching quantization:  99%|#########9| 840/846 [00:57<00:00, 26.15it/s]
+Attaching quantization: 100%|#########9| 843/846 [00:57<00:00, 20.53it/s]
+Attaching quantization: 100%|#########9| 843/846 [00:57<00:00, 20.53it/s]
+Attaching quantization: 100%|##########| 846/846 [00:57<00:00, 21.00it/s]
+Attaching quantization: 100%|##########| 846/846 [00:57<00:00, 21.00it/s]
+Attaching quantization: 100%|##########| 846/846 [00:57<00:00, 14.62it/s]
+Attaching quantization: 100%|##########| 846/846 [00:57<00:00, 14.62it/s]
+
+ - quantizing additional layers
+Moving transformer to CPU
+Text Encoder
+
+Loading checkpoint shards:   0%|          | 0/4 [00:00<?, ?it/s]
+Loading checkpoint shards:   0%|          | 0/4 [00:00<?, ?it/s]
+Loading checkpoint shards:  50%|#####     | 2/4 [00:00<00:00, 15.73it/s]
+Loading checkpoint shards:  50%|#####     | 2/4 [00:00<00:00, 15.73it/s]
+Loading checkpoint shards: 100%|##########| 4/4 [00:00<00:00, 24.39it/s]
+Loading checkpoint shards: 100%|##########| 4/4 [00:00<00:00, 24.39it/s]
+
+Quantizing Text Encoder
+Failed to quantize : Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.0: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.0.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.0.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.1: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.1.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.1.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.2: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.2.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.2.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.3: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.3.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.3.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.4: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.4.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.4.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.5: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.5.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.5.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.6: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.6.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.6.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.7: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.7.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.7.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.8: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.8.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.8.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.9: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.9.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.9.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.10: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.10.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.10.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.11: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.11.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.11.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.12: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.12.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.12.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.13: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.13.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.13.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.14: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.14.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.14.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.15: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.15.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.15.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.16: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.16.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.16.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.17: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.17.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.17.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.18: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.18.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.18.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.19: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.19.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.19.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.20: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.20.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.20.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.21: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.21.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.21.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.22: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.22.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.22.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.23: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.23.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.23.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.24: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.24.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.24.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.25: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.25.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.25.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.26: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.26.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.26.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.27: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.27.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.27.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.28: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.28.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.28.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.29: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.29.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.29.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.30: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.30.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.30.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.31: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.31.mlp: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Failed to quantize model.visual.blocks.31.mlp.down_proj: Expecting input size at 1 dimension: 3420 to be divisible by block_size at 1 dimension: 64
+Loading VAE
+Making pipe
+Preparing Model
+Model Loaded
+create LoRA network. base dim (rank): 16, alpha: 16
+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: 840 modules.
+enable LoRA for U-Net
+#### IMPORTANT RESUMING FROM D:\Github\ai-toolkit\output/qwen2509_object_removal_512/qwen2509_object_removal_512_000000750.safetensors ####
+Loading from D:\Github\ai-toolkit\output/qwen2509_object_removal_512/qwen2509_object_removal_512_000000750.safetensors
+Missing keys: []
+Found step 750 in metadata, starting from there
+Loading optimizer state from D:\Github\ai-toolkit\output/qwen2509_object_removal_512/optimizer.pt
+Updating optimizer LR from params
+Error running job: Job stopped
+
+========================================
+Result:
+ - 0 completed jobs
+ - 1 failure
+========================================
+Traceback (most recent call last):
+Traceback (most recent call last):
+  File "/mnt/d/Github/ai-toolkit/run.py", line 120, in <module>
+  File "/mnt/d/Github/ai-toolkit/run.py", line 120, in <module>
+        main()main()
+
+  File "/mnt/d/Github/ai-toolkit/run.py", line 108, in main
+  File "/mnt/d/Github/ai-toolkit/run.py", line 108, in main
+        raise eraise e
+
+  File "/mnt/d/Github/ai-toolkit/run.py", line 96, in main
+  File "/mnt/d/Github/ai-toolkit/run.py", line 96, in main
+        job.run()job.run()
+
+  File "/mnt/d/Github/ai-toolkit/jobs/ExtensionJob.py", line 22, in run
+  File "/mnt/d/Github/ai-toolkit/jobs/ExtensionJob.py", line 22, in run
+        process.run()process.run()
+
+  File "/mnt/d/Github/ai-toolkit/jobs/process/BaseSDTrainProcess.py", line 1992, in run
+  File "/mnt/d/Github/ai-toolkit/jobs/process/BaseSDTrainProcess.py", line 1992, in run
+        self.before_dataset_load()self.before_dataset_load()
+
+  File "/mnt/d/Github/ai-toolkit/extensions_built_in/sd_trainer/DiffusionTrainer.py", line 275, in before_dataset_load
+  File "/mnt/d/Github/ai-toolkit/extensions_built_in/sd_trainer/DiffusionTrainer.py", line 275, in before_dataset_load
+        self.maybe_stop()self.maybe_stop()
+
+  File "/mnt/d/Github/ai-toolkit/extensions_built_in/sd_trainer/DiffusionTrainer.py", line 147, in maybe_stop
+  File "/mnt/d/Github/ai-toolkit/extensions_built_in/sd_trainer/DiffusionTrainer.py", line 147, in maybe_stop
+        raise Exception("Job stopped")raise Exception("Job stopped")
+
+ExceptionException: : Job stoppedJob stopped
+

qwen2509_object_removal_512/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66d380506dabbab2fab6dffacf79f38c03c7557b5156a74035504fc15bf31f4b
+size 300280909

qwen2509_object_removal_512/pid.txt

@@ -0,0 +1 @@
+3351

qwen2509_object_removal_512/qwen2509_object_removal_512.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:973d76f618896db942e1e1c49785741df67eaceec9e20d7f79f0a56c8ab47ee0
+size 295146200

qwen2509_object_removal_512/qwen2509_object_removal_512_000012750.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f19528b6c3c5fe30f2bff99b8589734b965efc981b89e09291fc702f61c2a97
+size 295146200

qwen2509_object_removal_512/qwen2509_object_removal_512_000013000.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59838fd0c9f737f6ed33991f351cd2401b5ac37658182f6166481a4b8456ca7d
+size 295146200

qwen2509_object_removal_512/qwen2509_object_removal_512_000013250.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f958e9778697f488be284f531a94498dfbcf38a9fc47d751c098f858e66bba1
+size 295146200

qwen2509_object_removal_512/qwen2509_object_removal_512_000013500.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:768f71dab2d75343b4877b5a0d202186e4bb94ae4eb6076ed377e44d576053c3
+size 295146200