Instructions to use OFA-Sys/small-stable-diffusion-v0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use OFA-Sys/small-stable-diffusion-v0 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("OFA-Sys/small-stable-diffusion-v0", 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
Model at lower resultion like 256x256?
#9
by saddxzcy - opened
Is there any model support 256x256 or 224x224 image-to-image generation? The current model seems to only support 512x512 image input, and 256x256 input will cause the generated image to become all noise. And the main problem is with the unet, the other modules seem to work fine. Is there any unet trained on 256x256?
@saddxzcy i really loved how this model fit my fine-tuning use-case: https://huggingface.co/lambdalabs/miniSD-diffusers
I'm wondering the opposite β if there is a model that is trained on the same data like miniSD, but 512x512