Instructions to use CompVis/stable-diffusion-v1-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use CompVis/stable-diffusion-v1-2 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("CompVis/stable-diffusion-v1-2", 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 deprecated float16/fp16 variant loading through new `version` API.
Hey CompVis 👋, Your model repository seems to contain a [`fp16` branch](https://huggingface.co/CompVis/stable-diffusion-v1-2/tree/fp16) to load the model in float16 precision. Loading `fp16` versions from a branch instead of the main branch is deprecated and will eventually be forbidden. Instead, we strongly recommend to save `fp16` versions of the model under `.fp16.` version files directly on the 'main' branch as enabled through this PR.This PR makes sure that your model repository allows the user to correctly download float16 precision model weights by adding `fp16` model weights in both safetensors and PyTorch bin format: ```py pipe = DiffusionPipeline.from_pretrained(CompVis/stable-diffusion-v1-2, torch_dtype=torch.float16, variant='fp16') ``` For more information please have a look at: https://huggingface.co/docs/diffusers/using-diffusers/loading#checkpoint-variants. We made sure you that you can safely merge this pull request. Best, the 🧨 Diffusers team.bb17c77
-
Fix deprecation warning by changing `CLIPFeatureExtractor` to `CLIPImageProcessor`. (#7)
- Fix deprecation warning by changing `CLIPFeatureExtractor` to `CLIPImageProcessor`. (9e715019572d227261859c7f0416c95bde68deba)d23f189
-
Update README.md
19fc41b -
Update README.md
6cf1aef
-
Update README.md
eb73ff2
-
Update scheduler/scheduler_config.json
8585f2f
-
Update scheduler/scheduler_config.json
82cf394
-
Update license metadata to link to actual `creativeml-openrail-m` license (#3)
- Update license metadata to link to actual `creativeml-openrail-m` license (21cb0abe0e3292981aaec713ef500a5e19ab3bed)f0e77de
-
Update README.md
f00a847 -
Updating gated access wording. (#1)
- Updating gated access wording. (2c78c94031b7ac75b7a29be0a52e0734fa38f7d6) Co-authored-by: Margaret Mitchell <meg@users.noreply.huggingface.co>2acc6cb
-
Update README.md
9b0dffe -
Update README.md
3cad578 -
Update README.md
da4e4ae
-
Update README.md
69692b2 -
Update README.md
6d1b34d -
Update README.md
d6b863c -
Update README.md
2baddba -
Update README.md
d8017ac -
Update README.md
4404b79 -
Update README.md
aa33413 -
Update README.md
1553695 -
Update README.md
9a24dd0 -
Update README.md
08a7981 -
Update README.md
c15a211 -
Upload v1-variants-scores.jpg
56bf7e3
-
Update README.md
1bf31e0 -
Create README.md
55fe5cd
-
add weights
169381c -
initial commit
bfafd9d