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": 1000, "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": [ "portrait photograph, a man standing, wearing a TOK black hoodie, background is slightly out of focus, strong color contrast", "A portrait of a man standing on a bustling city street at night, wearing a TOK black hoodie. Neon lights illuminate the background, creating a strong color contrast, with a slightly out-of-focus backdrop of blurred car lights and urban scenery.", "A portrait of a man standing on a serene forest path, wearing a TOK black hoodie. The green foliage creates a lush and vibrant backdrop, slightly out of focus, with the dappled sunlight creating a strong color contrast against the dark hoodie.", "A portrait of a man standing on a modern urban rooftop at sunset, wearing a TOK black hoodie. The background showcases a city skyline with glowing buildings, slightly out of focus, emphasizing the contrast between the warm sunset hues and the dark clothing.", "A portrait of a man standing inside an industrial warehouse, wearing a TOK black hoodie. The background features metal beams and machinery, with a gritty, slightly out-of-focus look that contrasts sharply with the dark hoodie.", "A portrait of a man standing at a dimly lit subway station, wearing a TOK black hoodie. The background shows blurred trains and station signs, slightly out of focus, creating a strong color contrast between the artificial lighting and the dark hoodie." ], "neg": "", "seed": 42, "walk_seed": true, "guidance_scale": 4, "sample_steps": 20 }, "trigger_word": "TOK" } 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