Instructions to use diffusers/stable-diffusion-xl-1.0-inpainting-0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use diffusers/stable-diffusion-xl-1.0-inpainting-0.1 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("diffusers/stable-diffusion-xl-1.0-inpainting-0.1", 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
Comfyui Error - no attribute none
Not sure if this is your bailiwick or not but I'm getting a model has no attribute type 'none' error when trying to use this in comfyui - when loading the unet, clips, and vae seperately, and when using the diffusers loader node, in both fp16 and reegular modes, not sure if this is a model issue or a comfy thing since other diffusers models work fine for me.
Not sure if this is your bailiwick or not but I'm getting a model has no attribute type 'none' error when trying to use this in comfyui - when loading the unet, clips, and vae seperately, and when using the diffusers loader node, in both fp16 and reegular modes, not sure if this is a model issue or a comfy thing since other diffusers models work fine for me.
Did you get it to work?
Did not get it to work unfortunately. I've tried loading the unet and clips and vae separately and tried mixing the above with elements from different models and can't get anything useful