Open wx331406 opened 3 months ago
Can you provide a reproducible script?
if this is what you used, can you try to use from_single_file
instead?
pipe = DiffusionPipeline.from_pretrained("LCM_Dreamshaper_v7_4k.safetensors")
And also, please prefer translating the issue to English so that other maintainers of the library can also comment if necessary.
Describe the bug
发生异常: ValueError Pipeline <class 'diffusers.pipelines.latent_consistency_models.pipeline_latent_consistency_text2img.LatentConsistencyModelPipeline'> expected {'tokenizer', 'text_encoder', 'unet', 'vae', 'feature_extractor', 'safety_checker', 'scheduler'}, but only {'tokenizer', 'text_encoder', 'unet', 'vae', 'feature_extractor', 'safety_checker'} were passed. File "D:\local_gradio\app.py", line 25, in
pipe = DiffusionPipeline.from_pretrained("LCM_Dreamshaper_v7_4k.safetensors")
ValueError: Pipeline <class 'diffusers.pipelines.latent_consistency_models.pipeline_latent_consistency_text2img.LatentConsistencyModelPipeline'> expected {'tokenizer', 'text_encoder', 'unet', 'vae', 'feature_extractor', 'safety_checker', 'scheduler'}, but only {'tokenizer', 'text_encoder', 'unet', 'vae', 'feature_extractor', 'safety_checker'} were passed.
Reproduction
我非常确定文件是存在的,然而总是报错无法识别
Logs
System Info
(D:\conda_envs\lcm_env) D:>diffusers-cli env
Copy-and-paste the text below in your GitHub issue and FILL OUT the two last points.
Who can help?
莉莉娅