Instructions to use nitrosocke/Future-Diffusion with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use nitrosocke/Future-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("nitrosocke/Future-Diffusion", 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
Just getting noise
I recall nitro stating the need to update the diffusers and some dependencies but I have no idea what are those. Perhaps here under Requirements: https://github.com/Stability-AI/stablediffusion
@Lindsey You get that brown noise when you loaded the V-Model configuration files. The 512 Base model (which Future Diffusion is trained on) needs the non v model config.
I haven't used the Ui yet so I can't say how you would change it inside of there.
What do you mean with the non v model and v model? What does it refer too? I get brown noise too, what do I need to change to fix it?
@Koningsbruggen you can use the yaml file I provided in the repository. Place it in the same folder as the model ckpt file and it should work as intended.
