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
How much VRAM?
#5
by fawogin598 - opened
The safetensor file is 23.8GB so I guess you need more than 24GB VRAM, right?
@fawogin598 Yeah, it might barely fit with sequential offload and if your on a headless device but probably not. I would recommend use the q8 gguf version which will fit in 16gb vram with basically no quality loss.
@fawogin598 Yeah, it might barely fit with sequential offload and if your on a headless device but probably not. I would recommend use the q8 gguf version which will fit in 16gb vram with basically no quality loss.
How would you load the q8 version for use? I am having a bit of trouble with it
i ran FP8 on 16gb