huggingface / huggingface/diffusers
how to disable safty_checker in FlaxStableDiffusionPipeline
- Lingua principale
- Python
- Stelle
- 34.5k
- Fork
- 7.3k
- Merge medio
- 3g 3h
- PR unite (30g)
- 91
Descrizione
### Describe the bug
```
! python3 -m pip install -U tensorflow-cpu
import diffusers, os
pipeline = diffusers.StableDiffusionPipeline.from_single_file('https://huggingface.co/chaowenguo/pal/blob/main/chilloutMix-Ni.safetensors')
pipeline.save_pretrained('chilloutMix', safe_serialization=False)
pipeline, params = diffusers.FlaxStableDiffusionPipeline.from_pretrained('./chilloutMix', from_pt=True)
```
I always complains
```
Pipeline expected {'text_encoder', 'unet', 'scheduler', 'safety_checker', 'feature_extractor', 'vae', 'tokenizer'}, but only {'text_encoder', 'unet', 'scheduler', 'feature_extractor', 'vae', 'tokenizer'} were passed.
```
I want to know how to disable safety_checker in FlaxStableDiffusionPipeline
I try:
pipeline, params = diffusers.FlaxStableDiffusionPipeline.from_pretrained('./chilloutMix', from_pt=True, safety_checker=None)
Not working
### Reproduction
N/A
### Logs
_No response_
### System Info
kaggle tpu vm
### Who can help?
_No response_
Guida per i contributori
Apri la guida per i contributori
Direzione di ricerca
Start with the reported FlaxStableDiffusionPipeline.from_pretrained call and compare the required components with those loaded from ./chilloutMix. Reproduce the missing safety_checker error using the issue's snippet; done means the documented or supported way to disable safety_checker works for this pipeline.
Scritto dal modello di indicizzazione a partire dal testo della issue.
Valutazione
- Stack tecnologico
- python, tensorflow
- Ambito
- machine-learning
- Tipo di issue
- Bug
- Difficoltà
- 3/5
- Tempo stimato
- 1-2 giorni
- Stato di attività
- Ferma
- Chiarezza
- Da chiarire
- Idoneità per principianti
- 25/100