Text-to-Image
Diffusers
English
StableDiffusionPipeline
stable-diffusion
stable-diffusion-diffusers
Avatar
Avatar The Way of Water
film
James Cameron
Instructions to use riccardogiorato/avatar-diffusion with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use riccardogiorato/avatar-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("riccardogiorato/avatar-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
-
Fix deprecation warning by changing `CLIPFeatureExtractor` to `CLIPImageProcessor`.
Hey riccardogiorato 👋, Your model repository seems to contain logic to load a feature extractor that is deprecated, which you should notice by seeing the warning: ``` transformers/models/clip/feature_extraction_clip.py:28: FutureWarning: The class CLIPFeatureExtractor is deprecated and will be removed in version 5 of Transformers. Please use CLIPImageProcessor instead. warnings.warn( ``` when running `pipe = DiffusionPipeline.from_pretrained(riccardogiorato/avatar-diffusion)`.This PR makes sure that the warning does not show anymore by replacing `CLIPFeatureExtractor` with `CLIPImageProcessor`. This will certainly not change or break your checkpoint, but onlymake sure that everything is up to date. Best, the 🧨 Diffusers team.3262037
-
Correct `sample_size` of Stable Diffusion 1's unet to have correct width and height default (#3)
- Correct `sample_size` of Stable Diffusion 1's unet to have correct width and height default (ece7e001c983c4a5f77e47d15f43dc98aa241397) Co-authored-by: Patrick von Platen <patrickvonplaten@users.noreply.huggingface.co>c39ee62 -
Add `clip_sample=False` to scheduler to make model compatible with DDIM. (#4)
- Add `clip_sample=False` to scheduler to make model compatible with DDIM. (8133ec0efd4f7f14b1ba48557b21e094c009286c) Co-authored-by: Patrick von Platen <patrickvonplaten@users.noreply.huggingface.co>380ac1e
-
Update README.md
c53eb8b -
add diffusers (#1)
- Add Diffusers weights for (83a829d2b86ea5093ef98165ab22308f5c814507)065f184
-
Update README.md
Riccardo Giorato6f98c71 -
Update README.md
Riccardo Gioratob913f4e -
add weights ckpt
Riccardo Giorato186c498 -
update README
Riccardo Giorato7bbf784 -
initial commit
a1b8790