Ccannot run Space on wsl2 docker

Beginners
1

i have tried to run this space many times and the same issue pops up.
this is the command i used:

docker run -it -p 7860:7860 --platform=linux/amd64 --gpus all \
	-e HF_TOKEN="YOUR_VALUE_HERE" \
	registry.hf.space/damarjati-flux-1-realismlora:latest python app.py

it prints out this error message:


> docker run -it -p 7860:7860 --platform=linux/amd64 --gpus all -e HF_TOKEN="" registry.hf.space/damarjati-flux-1-realismlora:latest python app.py

> 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()`.`

> 0it [00:00, ?it/s]

> model_index.json: 100%|██████████████████████████████████████████████| 536/536 [00:00<00:00, 4.24MB/s]

> scheduler/scheduler_config.json: 100%|███████████████████████████████| 273/273 [00:00<00:00, 2.03MB/s]

> text_encoder/config.json: 100%|██████████████████████████████████████| 613/613 [00:00<00:00, 4.54MB/s]

> model.safetensors: 100%|██████████████████████████████████████████▉| 246M/246M [00:20<00:00, 12.2MB/s]

> text_encoder_2/config.json: 100%|████████████████████████████████████| 782/782 [00:00<00:00, 4.88MB/s]

> model-00001-of-00002.safetensors: 100%|█████████████████████████▉| 4.99G/4.99G [05:09<00:00, 16.1MB/s]

> model-00002-of-00002.safetensors: 100%|█████████████████████████▉| 4.53G/4.53G [02:47<00:00, 27.0MB/s]

> (…)t_encoder_2/model.safetensors.index.json: 100%|███████████████| 19.9k/19.9k [00:00<00:00, 9.16MB/s]

> tokenizer/merges.txt: 100%|████████████████████████████████████████| 525k/525k [00:00<00:00, 1.42MB/s]

> tokenizer/special_tokens_map.json: 100%|█████████████████████████████| 588/588 [00:00<00:00, 4.63MB/s]

> tokenizer/tokenizer_config.json: 100%|███████████████████████████████| 705/705 [00:00<00:00, 5.28MB/s]

> tokenizer/vocab.json: 100%|██████████████████████████████████████| 1.06M/1.06M [00:00<00:00, 1.39MB/s]

> tokenizer_2/special_tokens_map.json: 100%|███████████████████████| 2.54k/2.54k [00:00<00:00, 21.9MB/s]

> spiece.model: 100%|████████████████████████████████████████████████| 792k/792k [00:00<00:00, 1.83MB/s]

> tokenizer_2/tokenizer.json: 100%|████████████████████████████████| 2.42M/2.42M [00:00<00:00, 5.80MB/s]

> tokenizer_2/tokenizer_config.json: 100%|█████████████████████████| 20.8k/20.8k [00:00<00:00, 1.43MB/s]

> transformer/config.json: 100%|███████████████████████████████████████| 378/378 [00:00<00:00, 3.60MB/s]

> (…)pytorch_model-00001-of-00003.safetensors: 100%|██████████████▉| 9.98G/9.98G [09:31<00:00, 17.5MB/s]

> (…)pytorch_model-00002-of-00003.safetensors: 100%|██████████████▉| 9.95G/9.95G [10:10<00:00, 16.3MB/s]

> (…)pytorch_model-00003-of-00003.safetensors: 100%|██████████████▉| 3.87G/3.87G [05:46<00:00, 11.2MB/s]

> (…)ion_pytorch_model.safetensors.index.json: 100%|██████████████████| 121k/121k [00:00<00:00, 609kB/s]

> vae/config.json: 100%|███████████████████████████████████████████████| 820/820 [00:00<00:00, 6.30MB/s]

> diffusion_pytorch_model.safetensors: 100%|████████████████████████▉| 168M/168M [00:19<00:00, 8.48MB/s]diffusion_pytorch_model.safetensors: 100%|████████████████████████▉| 168M/168M [00:19<00:00, 10.7MB/sYou set \add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers00:00<?, ?it/s]`

> Loading checkpoint shards: 100%|████████████████████████████████████████| 2/2 [00:00<00:00, 4.66it/s]

> Loading pipeline components...: 100%|███████████████████████████████████| 7/7 [00:02<00:00, 2.92it/s]

> lora.safetensors: 100%|██████████████████████████████████████████| 22.4M/22.4M [00:02<00:00, 10.9MB/s]

> Traceback (most recent call last):████████▋ | 10.5M/22.4M [00:01<00:01, 9.69MB/s]

> File "/home/user/app/app.py", line 20, in <module>

> pipe.to("cuda")

> File "/usr/local/lib/python3.10/site-packages/diffusers/pipelines/pipeline_utils.py", line 431, in to

> module.to(device, dtype)

> File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1174, in to

> return self._apply(convert)

> File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 780, in _apply

> module._apply(fn)

> File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 780, in _apply

> module._apply(fn)

> File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 780, in _apply

> module._apply(fn)

> [Previous line repeated 1 more time]

> File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 805, in _apply

> param_applied = fn(param)

> File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1160, in convert

> return t.to(

> torch.OutOfMemoryError: CUDA out of memory. Tried to allocate 18.00 MiB. GPU 0 has a total capacity of 10.00 GiB of which 0 bytes is free. Including non-PyTorch memory, this process has 17179869184.00 GiB memory in use. Of the allocated memory 16.56 GiB is allocated by PyTorch, and 9.42 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management
1 Like
2

torch.OutOfMemoryError: CUDA out of memory. Tried to allocate 18.00 MiB. GPU 0 has a total capacity of 10.00 GiB of which 0 bytes is free.

There seems to be a lack of VRAM. I would suggest quantizing the model you use or using a higher GPU. I think there are means to find a smaller model.
I thought, but this is Flux’s LoRA space…it’s hard to quantize with LoRA applied…
Anyway, if you want to run Flux, you’ll need at least 30GB of VRAM.

# Initialize the base model and specific LoRA
base_model = "black-forest-labs/FLUX.1-dev"
pipe = DiffusionPipeline.from_pretrained(base_model, torch_dtype=torch.bfloat16) # it requires around 30GB of VRAM

lora_repo = "XLabs-AI/flux-RealismLora"
trigger_word = ""  # Leave trigger_word blank if not used.
pipe.load_lora_weights(lora_repo)
3

ok thank you

1 Like