Update README.md

This commit is contained in:
Johannes Stelzer 2024-01-09 21:16:10 +01:00 committed by GitHub
parent 6e138c54a2
commit 4501d80044
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 4 additions and 0 deletions

View File

@ -3,6 +3,10 @@
Latent blending enables video transitions with incredible smoothness between prompts, computed within seconds. Powered by [stable diffusion XL](https://stability.ai/stable-diffusion), this method involves specific mixing of intermediate latent representations to create a seamless transition with users having the option to fully customize the transition directly in high-resolution. The new version also supports SDXL Turbo, allowing to generate transitions faster than they are typically played back! Latent blending enables video transitions with incredible smoothness between prompts, computed within seconds. Powered by [stable diffusion XL](https://stability.ai/stable-diffusion), this method involves specific mixing of intermediate latent representations to create a seamless transition with users having the option to fully customize the transition directly in high-resolution. The new version also supports SDXL Turbo, allowing to generate transitions faster than they are typically played back!
```python ```python
from diffusers import AutoPipelineForText2Image
from latentblending.blending_engine import BlendingEngine
from latentblending.diffusers_holder import DiffusersHolder
pipe = AutoPipelineForText2Image.from_pretrained("stabilityai/sdxl-turbo", torch_dtype=torch.float16, variant="fp16").to("cuda") pipe = AutoPipelineForText2Image.from_pretrained("stabilityai/sdxl-turbo", torch_dtype=torch.float16, variant="fp16").to("cuda")
dh = DiffusersHolder(pipe) dh = DiffusersHolder(pipe)
be = BlendingEngine(dh) be = BlendingEngine(dh)