Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Create butter-smooth transitions between prompts, powered by stable diffusion
| Date | Stars |
|---|---|
| 2026-07-24 | 366 |
| 2026-07-25 | 366 |
| 2026-07-28 | 366 |
| 2026-07-30 | 366 |
| 2026-07-31 | 365 |
| 2026-08-06 | 365 |
Today
— stars today
This week
-1 stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Quickstart
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
import torch
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")
be = BlendingEngine(pipe)
be.set_prompt1("photo of underwater landscape, fish, und the sea, incredible detail, high resolution")
be.set_prompt2("rendering of an alien planet, strange plants, strange creatures, surreal")
be.set_negative_prompt("blurry, ugly, pale")
# Run latent blending
be.run_transition()
# Save movie
be.write_movie_transition('movie_example1.mp4', duration_transition=12)
```
# Installation
```commandline
pip install git+https://github.com/lunarring/latentblending
```
# Extra speedup with stable_fast compile
Install https://github.com/chengzeyi/stable-fast
Then enable pipe compilation by setting *do_compile=True*
```python
be = BlendingEngine(pipe, do_compile=True)
```
## Gradio UI
We can launch the a user-interface version with:
```commandline
python latentblending/gradio_ui.py
```
With the UI, you can iteratively generate your desired keyframes, and then render the movie with latent blending it at the end.
## Example 1: Simple transition
To run a simple transition between two prompts, see `examples/single_trans.py`, or [check this volcano eruption ](https://youtu.be/O_2fpWHdnm4).
## Example 2: Multi transition
To run multiple transition between K prompts, resulting in a stitched video, see `examples/multi_trans.py`.
[View a longer example video here.](https://youtu.be/RLF-yW5dR_Q)
# Customization
### Change the height/width
```python
size_output = (1024, 768)
be.set_dimensions(size_output)
```
### Change the number of diffusion steps (set_num_inference_steps)
```python
be.set_num_inference_steps(50)
```
For SDXL this is set as default=30, for SDXL Turbo a value of 4 is taken.
### Change the guidance scale
```python
be.set_guidance_scale(3.0)
```
For SDXL this is set as default=4.0, for SDXL Turbo a value of 0 is taken.
### Change the branching paramters
```python
depth_strength = 0.5
nmb_max_branches = 15
be.set_branching(depth_strength=depth_strength, t_compute_max_allowed=None, nmb_max_branches=None)
```
* depth_strength: The strength of the diffusion iterations determines when the blending process will begin. A value close to zero results in more creative and intricate outcomes, while a value closer to one indicates a simpler alpha blending. However, low values may also bring about the introduction of additional objects and motion.
* t_compute_max_allowed: maximum time allowed for computation. Higher values give better results but take longer. Either provide t_compute_max_allowed or nmb_max_branches. Does not work for SDXL Turbo.
* nmb_max_branches: The maximum number of branches to be computed. Higher values give better results. Use this if you want to have controllable results independent of your hardware. Either provide t_compute_max_allowed or nmb_max_branches.
## Most relevant parameters
You can find the [most relevant parameters here.](parameters.md)
### Change guidance scale
```python
be.set_guidance_scale(5.0)
```
### Crossfeeding to the last image.
Cross-feeding latents is a key feature of latent blending. Here, you can set how much the first image branch influences the very last one. In the animation below, these are the blue arrowExcerpt of 8,066 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:c9da735eb9022b6f, topic:stable-diffusion, desc:stable diffusion, readme:stable diffusion
matched fp:c9da735eb9022b6f, topic:animation