Instructions to use shuttleai/shuttle-3-diffusion-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use shuttleai/shuttle-3-diffusion-GGUF with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("shuttleai/shuttle-3-diffusion-GGUF", 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
how use it in comfyui??
how use it in comfyui??can you give me a workflow for comfyui??
You should be able to use any pre-existing flux workflow, just replace the node to load the model with a Unet Loader (GGUF) node from https://github.com/city96/ComfyUI-GGUF
I have published a workflow for using this model with comfyui. It makes use of the quantized version of this model, which is what I would suggest to use on consumer grade GPU's. Have fun :)
https://openart.ai/workflows/deathdev/shuttle-diffusion-3/bgdb6tWMNdUtSTWo6qVV
I have published a workflow for using this model with comfyui. It makes use of the quantized version of this model, which is what I would suggest to use on consumer grade GPU's. Have fun :)
https://openart.ai/workflows/deathdev/shuttle-diffusion-3/bgdb6tWMNdUtSTWo6qVV
Thanks but it leads to "Sorry, page not found!"
I also get the same error. Can you please post the link again? This would be very useful
I have published a workflow for using this model with comfyui. It makes use of the quantized version of this model, which is what I would suggest to use on consumer grade GPU's. Have fun :)
https://openart.ai/workflows/deathdev/shuttle-diffusion-3/bgdb6tWMNdUtSTWo6qVV