scheduler文件无法识别

[wx331406]

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

日志五任何提示

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.

• 🤗 Diffusers version: 0.28.0
• Platform: Windows-10-10.0.19044-SP0
• Running on a notebook?: No
• Running on Google Colab?: No
• Python version: 3.8.19
• PyTorch version (GPU?): 2.3.0+cpu (False)
• Flax version (CPU?/GPU?/TPU?): not installed (NA)
• Jax version: not installed
• JaxLib version: not installed
• Huggingface_hub version: 0.23.2
• Transformers version: 4.41.1
• Accelerate version: 0.30.1
• PEFT version: not installed
• Bitsandbytes version: not installed
• Safetensors version: 0.4.3
• xFormers version: not installed
• Accelerator: NVIDIA GeForce GTX 1080 Ti, 11264 MiB VRAM
• Using GPU in script?:
• Using distributed or parallel set-up in script?:

Who can help?

莉莉娅

[yiyixuxu]

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")

[sayakpaul]

And also, please prefer translating the issue to English so that other maintainers of the library can also comment if necessary.