Instructions to use shuttleai/shuttle-3-diffusion with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use shuttleai/shuttle-3-diffusion 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", dtype=torch.bfloat16, device_map="cuda") prompt = "Venus floating market at dawn, fantasy digital art, highly detailed, atmospheric lighting with film-like light leaks, impressive background, studio photo style, cinematic, intricate details." image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
unet only in GGUF ?
would you upload the unet in gguf q8 please ?
if you give me like 10 minutes maybe
there's literally not even any other way to do it whyd you specify specifically the unet xD
anyways, https://huggingface.co/shuttleai/shuttle-3-diffusion-GGUF
thanks a lot
it's a transformer, not a unet
well the proper term would probably be diffusion backbone or something if we were really being picky, but yea its a DiT
okie, those kinds of responses including the one where you suggested a user to use ComfyUI or Forge instead of helping them with the Diffusers code example in a different forum topic, are coming across as unprofessional and unhelpful.
:/ apologies, i didnt mean to come off mean, was just trying to be as helpful as i could (and i wasnt aware personally of if you could load pre-quanted fp8 weights in diffusers)