Instructions to use segmind/small-sd with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use segmind/small-sd with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("segmind/small-sd", 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 Settings
- Draw Things
- DiffusionBee
Is it possible to use it on an Inpainting task?
#1
by Bikesuffer - opened
I am wondering is it possible to use the unet to replace the unet of the inpainting task?
Yeah, Our Model is compatible with the Pipelines of the diffusers module, You can simply put our Model Card (segmind/small-sd) while loading and it will work. For Details on how to use an Inpainting Pipeline, Please refer to this guide, https://huggingface.co/docs/diffusers/using-diffusers/inpaint
Warlord-K changed discussion status to closed
Actually I test small-sd for inpainting. But the result seems not correct(the generated area is not related to the non-masked area). I am wondering is there a way that I can train the small-sd unet to work on inpainting task.