| The cache for model files in Transformers v4.22.0 has been updated. Migrating your old cache. This is a one-time only operation. You can interrupt this and resume the migration later on by calling `transformers.utils.move_cache()`. | |
| Running 1 job | |
| 0it [00:00, ?it/s] 0it [00:00, ?it/s] | |
| /usr/local/lib/python3.10/dist-packages/controlnet_aux/mediapipe_face/mediapipe_face_common.py:7: UserWarning: The module 'mediapipe' is not installed. The package will have limited functionality. Please install it using the command: pip install 'mediapipe' | |
| warnings.warn( | |
| /usr/local/lib/python3.10/dist-packages/controlnet_aux/segment_anything/modeling/tiny_vit_sam.py:654: UserWarning: Overwriting tiny_vit_5m_224 in registry with controlnet_aux.segment_anything.modeling.tiny_vit_sam.tiny_vit_5m_224. This is because the name being registered conflicts with an existing name. Please check if this is not expected. | |
| return register_model(fn_wrapper) | |
| /usr/local/lib/python3.10/dist-packages/controlnet_aux/segment_anything/modeling/tiny_vit_sam.py:654: UserWarning: Overwriting tiny_vit_11m_224 in registry with controlnet_aux.segment_anything.modeling.tiny_vit_sam.tiny_vit_11m_224. This is because the name being registered conflicts with an existing name. Please check if this is not expected. | |
| return register_model(fn_wrapper) | |
| /usr/local/lib/python3.10/dist-packages/controlnet_aux/segment_anything/modeling/tiny_vit_sam.py:654: UserWarning: Overwriting tiny_vit_21m_224 in registry with controlnet_aux.segment_anything.modeling.tiny_vit_sam.tiny_vit_21m_224. This is because the name being registered conflicts with an existing name. Please check if this is not expected. | |
| return register_model(fn_wrapper) | |
| /usr/local/lib/python3.10/dist-packages/controlnet_aux/segment_anything/modeling/tiny_vit_sam.py:654: UserWarning: Overwriting tiny_vit_21m_384 in registry with controlnet_aux.segment_anything.modeling.tiny_vit_sam.tiny_vit_21m_384. This is because the name being registered conflicts with an existing name. Please check if this is not expected. | |
| return register_model(fn_wrapper) | |
| /usr/local/lib/python3.10/dist-packages/controlnet_aux/segment_anything/modeling/tiny_vit_sam.py:654: UserWarning: Overwriting tiny_vit_21m_512 in registry with controlnet_aux.segment_anything.modeling.tiny_vit_sam.tiny_vit_21m_512. This is because the name being registered conflicts with an existing name. Please check if this is not expected. | |
| return register_model(fn_wrapper) | |
| You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers | |
| { | |
| "type": "sd_trainer", | |
| "training_folder": "output", | |
| "device": "cuda:0", | |
| "network": { | |
| "type": "lora", | |
| "linear": 16, | |
| "linear_alpha": 16 | |
| }, | |
| "save": { | |
| "dtype": "float16", | |
| "save_every": 500, | |
| "max_step_saves_to_keep": 4, | |
| "push_to_hub": false | |
| }, | |
| "datasets": [ | |
| { | |
| "folder_path": "/workspace/ai-toolkit/images", | |
| "caption_ext": "txt", | |
| "caption_dropout_rate": 0.05, | |
| "shuffle_tokens": false, | |
| "cache_latents_to_disk": true, | |
| "resolution": [ | |
| 512, | |
| 768, | |
| 1024 | |
| ] | |
| } | |
| ], | |
| "train": { | |
| "batch_size": 1, | |
| "steps": 3000, | |
| "gradient_accumulation_steps": 1, | |
| "train_unet": true, | |
| "train_text_encoder": false, | |
| "gradient_checkpointing": true, | |
| "noise_scheduler": "flowmatch", | |
| "optimizer": "adamw8bit", | |
| "lr": 0.0001, | |
| "ema_config": { | |
| "use_ema": true, | |
| "ema_decay": 0.99 | |
| }, | |
| "dtype": "bf16" | |
| }, | |
| "model": { | |
| "name_or_path": "black-forest-labs/FLUX.1-dev", | |
| "is_flux": true, | |
| "quantize": true | |
| }, | |
| "sample": { | |
| "sampler": "flowmatch", | |
| "sample_every": 500, | |
| "width": 1024, | |
| "height": 1024, | |
| "prompts": [ | |
| "woman with red hair, playing chess at the park, bomb going off in the background", | |
| "a woman holding a coffee cup, in a beanie, sitting at a cafe", | |
| "a horse is a DJ at a night club, fish eye lens, smoke machine, lazer lights, holding a martini", | |
| "a man showing off his cool new t shirt at the beach, a shark is jumping out of the water in the background", | |
| "a bear building a log cabin in the snow covered mountains", | |
| "woman playing the guitar, on stage, singing a song, laser lights, punk rocker", | |
| "hipster man with a beard, building a chair, in a wood shop", | |
| "photo of a man, white background, medium shot, modeling clothing, studio lighting, white backdrop", | |
| "a man holding a sign that says, 'this is a sign'", | |
| "a bulldog, in a post apocalyptic world, with a shotgun, in a leather jacket, in a desert, with a motorcycle" | |
| ], | |
| "neg": "", | |
| "seed": 42, | |
| "walk_seed": true, | |
| "guidance_scale": 4, | |
| "sample_steps": 20 | |
| }, | |
| "trigger_word": "p3r5on" | |
| } | |
| Using EMA | |
| ############################################# | |
| # Running job: my_first_flux_lora_v1 | |
| ############################################# | |
| Running 1 process | |
| Loading Flux model | |
| Loading transformer | |
| Quantizing transformer | |
| Loading vae | |
| Loading t5 | |
| Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:26<00:26, 26.58s/it] Downloading shards: 100%|██████████| 2/2 [00:48<00:00, 23.78s/it] Downloading shards: 100%|██████████| 2/2 [00:48<00:00, 24.20s/it] | |
| Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 5.41it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 6.00it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 5.90it/s] | |
| Quantizing T5 | |
| Loading clip | |
| making pipe | |
| preparing | |
| 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: 494 modules. | |
| enable LoRA for U-Net | |
| Dataset: /workspace/ai-toolkit/images | |
| - Preprocessing image dimensions | |
| 0%| | 0/11 [00:00<?, ?it/s] 100%|██████████| 11/11 [00:00<00:00, 414.98it/s] | |
| - Found 11 images | |
| Bucket sizes for /workspace/ai-toolkit/images: | |
| 448x576: 11 files | |
| 1 buckets made | |
| Caching latents for /workspace/ai-toolkit/images | |
| - Saving latents to disk | |
| Caching latents to disk: 0%| | 0/11 [00:00<?, ?it/s] Caching latents to disk: 9%|▉ | 1/11 [00:00<00:03, 2.65it/s] Caching latents to disk: 27%|██▋ | 3/11 [00:00<00:01, 6.49it/s] Caching latents to disk: 45%|████▌ | 5/11 [00:00<00:00, 8.75it/s] Caching latents to disk: 64%|██████▎ | 7/11 [00:00<00:00, 10.24it/s] Caching latents to disk: 82%|████████▏ | 9/11 [00:00<00:00, 11.33it/s] Caching latents to disk: 100%|██████████| 11/11 [00:01<00:00, 12.11it/s] Caching latents to disk: 100%|██████████| 11/11 [00:01<00:00, 9.80it/s] | |
| Dataset: /workspace/ai-toolkit/images | |
| - Preprocessing image dimensions | |
| 0%| | 0/11 [00:00<?, ?it/s] 100%|██████████| 11/11 [00:00<00:00, 42719.76it/s] | |
| - Found 11 images | |
| Bucket sizes for /workspace/ai-toolkit/images: | |
| 640x832: 11 files | |
| 1 buckets made | |
| Caching latents for /workspace/ai-toolkit/images | |
| - Saving latents to disk | |
| Caching latents to disk: 0%| | 0/11 [00:00<?, ?it/s] Caching latents to disk: 9%|▉ | 1/11 [00:00<00:01, 6.85it/s] Caching latents to disk: 18%|█▊ | 2/11 [00:00<00:01, 7.43it/s] Caching latents to disk: 27%|██▋ | 3/11 [00:00<00:00, 8.13it/s] Caching latents to disk: 36%|███▋ | 4/11 [00:00<00:00, 8.52it/s] Caching latents to disk: 45%|████▌ | 5/11 [00:00<00:00, 8.78it/s] Caching latents to disk: 55%|█████▍ | 6/11 [00:00<00:00, 8.90it/s] Caching latents to disk: 64%|██████▎ | 7/11 [00:00<00:00, 9.01it/s] Caching latents to disk: 73%|███████▎ | 8/11 [00:00<00:00, 9.03it/s] Caching latents to disk: 82%|████████▏ | 9/11 [00:01<00:00, 9.02it/s] Caching latents to disk: 91%|█████████ | 10/11 [00:01<00:00, 9.11it/s] Caching latents to disk: 100%|██████████| 11/11 [00:01<00:00, 8.66it/s] Caching latents to disk: 100%|██████████| 11/11 [00:01<00:00, 8.64it/s] | |
| Dataset: /workspace/ai-toolkit/images | |
| - Preprocessing image dimensions | |
| 0%| | 0/11 [00:00<?, ?it/s] 100%|██████████| 11/11 [00:00<00:00, 35710.02it/s] | |
| - Found 11 images | |
| Bucket sizes for /workspace/ai-toolkit/images: | |
| 832x1152: 11 files | |
| 1 buckets made | |
| Caching latents for /workspace/ai-toolkit/images | |
| - Saving latents to disk | |
| Caching latents to disk: 0%| | 0/11 [00:00<?, ?it/s] Caching latents to disk: 9%|▉ | 1/11 [00:00<00:01, 5.11it/s] Caching latents to disk: 18%|█▊ | 2/11 [00:00<00:01, 5.29it/s] Caching latents to disk: 27%|██▋ | 3/11 [00:00<00:01, 5.41it/s] Caching latents to disk: 36%|███▋ | 4/11 [00:00<00:01, 5.48it/s] Caching latents to disk: 45%|████▌ | 5/11 [00:00<00:01, 5.29it/s] Caching latents to disk: 55%|█████▍ | 6/11 [00:01<00:00, 5.42it/s] Caching latents to disk: 64%|██████▎ | 7/11 [00:01<00:00, 5.53it/s] Caching latents to disk: 73%|███████▎ | 8/11 [00:01<00:00, 5.57it/s] Caching latents to disk: 82%|████████▏ | 9/11 [00:01<00:00, 5.52it/s] Caching latents to disk: 91%|█████████ | 10/11 [00:01<00:00, 5.51it/s] Caching latents to disk: 100%|██████████| 11/11 [00:02<00:00, 5.56it/s] Caching latents to disk: 100%|██████████| 11/11 [00:02<00:00, 5.48it/s] | |
| Generating baseline samples before training | |
| Generating Images: 0%| | 0/10 [00:00<?, ?it/s] Generating Images: 10%|█ | 1/10 [01:26<12:56, 86.27s/it] Generating Images: 20%|██ | 2/10 [02:04<07:44, 58.03s/it] Generating Images: 30%|███ | 3/10 [02:43<05:44, 49.28s/it] Generating Images: 40%|████ | 4/10 [03:22<04:31, 45.27s/it] Generating Images: 50%|█████ | 5/10 [04:01<03:35, 43.08s/it] Generating Images: 60%|██████ | 6/10 [04:40<02:46, 41.73s/it] Generating Images: 70%|███████ | 7/10 [05:19<02:02, 40.85s/it] Generating Images: 80%|████████ | 8/10 [05:58<01:20, 40.23s/it] Generating Images: 90%|█████████ | 9/10 [06:37<00:39, 39.82s/it] Generating Images: 100%|██████████| 10/10 [07:16<00:00, 39.53s/it] my_first_flux_lora_v1: 0%| | 0/3000 [00:00<?, ?it/s] my_first_flux_lora_v1: 0%| | 0/3000 [00:04<?, ?it/s, lr: 1.0e-04 loss: 4.015e-01] my_first_flux_lora_v1: 0%| | 0/3000 [00:04<?, ?it/s, lr: 1.0e-04 loss: 4.015e-01] my_first_flux_lora_v1: 0%| | 0/3000 [00:10<?, ?it/s, lr: 1.0e-04 loss: 4.988e-01] my_first_flux_lora_v1: 0%| | 1/3000 [00:10<4:56:11, 5.93s/it, lr: 1.0e-04 loss: 4.988e-01] |