Instructions to use furusu/LCM-Acertainty with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use furusu/LCM-Acertainty with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("furusu/LCM-Acertainty", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
Debug:TypeError: unhashable type: 'dict'
/root/miniconda3/envs/ip/lib/python3.9/site-packages/huggingface_hub/file_download.py:659: FutureWarning: 'cached_download' is the legacy way to download files from the HF hub, please consider upgrading to 'hf_hub_download'
warnings.warn(
Downloading (…)nsistency_txt2img.py: 33.2kB [00:00, 435kB/s]
Loading pipeline components...: 0%| | 0/6 [00:00<?, ?it/s]
Traceback (most recent call last):
File "/dfs/comicai/songtao.tian/LCM_Acertainty.py", line 4, in
pipe = DiffusionPipeline.from_pretrained("/dfs/comicai/songtao.tian/models/LCM-Acertainty", custom_pipeline="latent_consistency_txt2img", custom_revision="main")
File "/root/miniconda3/envs/ip/lib/python3.9/site-packages/diffusers/pipelines/pipeline_utils.py", line 1254, in from_pretrained
loaded_sub_model = load_sub_model(
File "/root/miniconda3/envs/ip/lib/python3.9/site-packages/diffusers/pipelines/pipeline_utils.py", line 507, in load_sub_model
loaded_sub_model = load_method(os.path.join(cached_folder, name), **loading_kwargs)
File "/root/miniconda3/envs/ip/lib/python3.9/site-packages/transformers/tokenization_utils_base.py", line 2017, in from_pretrained
return cls._from_pretrained(
File "/root/miniconda3/envs/ip/lib/python3.9/site-packages/transformers/tokenization_utils_base.py", line 2242, in _from_pretrained
init_kwargs[key] = added_tokens_map.get(init_kwargs[key], init_kwargs[key])
TypeError: unhashable type: 'dict'