Instructions to use nitrosocke/Nitro-Diffusion with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use nitrosocke/Nitro-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/Nitro-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 Settings
- Draw Things
- DiffusionBee
Commit History
-
Add `clip_sample=False` to scheduler to make model compatible with DDIM.
Hey nitrosocke 👋, Your model repository seems to contain a stable diffusion checkpoint. We have noticed that your scheduler config currently does not correctly work with the [DDIMScheduler](https://huggingface.co/docs/diffusers/main/en/api/schedulers#diffusers.DDIMScheduler) because `clip_sample` is not set to False and will therefore [incorrectly default to True](https://github.com/huggingface/diffusers/blob/3ce6380d3a2ec5c3e3f4f48889d380d657b151bc/src/diffusers/schedulers/scheduling_ddim.py#L127). The official stable diffusion checkpoints have `clip_sample=False` so that the scheduler config works will **all** schedulers, see: https://huggingface.co/stabilityai/stable-diffusion-2-1-base/blob/main/scheduler/scheduler_config.json#L7. We strongly recommend that you merge this PR to make sure your model works correctly with DDIM. Diffusingly, Patrick.361be75
-
Correct `sample_size` of Stable Diffusion 1's unet to have correct width and height default (#10)
- Correct `sample_size` of Stable Diffusion 1's unet to have correct width and height default (6384847645fe08d08a5b8b69161afdfb55a79355) Co-authored-by: Patrick von Platen <patrickvonplaten@users.noreply.huggingface.co>fe450ed
-
Update README.md
79e0535
-
Add Diffusers weights (#8)
- Add Diffusers weights (e39f3cf9f2c5435a3877a8ef38b151c960e426e5) Co-authored-by: Guizmus <Guizmus@users.noreply.huggingface.co>62e5f2c
-
add gradio demo link (#7)
- add gradio demo link (2fda2a98677a1f7a057caf77e9aa2a8095bdeda8) Co-authored-by: Ahsen Khaliq <akhaliq@users.noreply.huggingface.co>f23b332
-
Update README tags to detect properly that this is a `diffusers` model to enable the free widget inference. (#3)
- Update README tags to detect properly that this is a `diffusers` model to enable the free widget inference. (ea92155c0dbdb123979ecba4a4e4fdf9ed68e7b4) Co-authored-by: Nicolas Patry <Narsil@users.noreply.huggingface.co>9552844 -
Add a diffusers checkpoint (#4)
- Add a diffusers checkpoint (0ea24749bb659700f97e8a99639ba5dab3a74c61) Co-authored-by: Anton Lozhkov <anton-l@users.noreply.huggingface.co>516c17f -
Update README.md
972cd6b
-
Upload nitro-diff-samples-03.jpg
a7b1b60 -
Update README.md
3d81886 -
Upload 2 files
48b9a66 -
Update README.md
7e6f33c -
Update README.md
7c4ba8f -
Upload 2 files
0982502 -
Upload nitroDiffusion-v1.ckpt
5df6141 -
initial commit
d93a8af