technicalkiwi
/
latentblending
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Merge branch 'main' of github.com:lunarring/latentblending

This commit is contained in:
lunar 2022-12-02 12:18:56 +00:00
parent d53eebaa96 1b77553346
commit 18e05675c1
1 changed files with 15 additions and 27 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

42
README.md
View File

@ -1,6 +1,6 @@
# What is latent blending? # What is latent blending?
Latent blending allows you to generate smooth video transitions between two prompts. It is based on (stable diffusion 2.0)[https://stability.ai/blog/stable-diffusion-v2-release] and remixes the latent reprensetation using spherical linear interpolations. This results in imperceptible transitions, where one image slowly turns into another one. Latent blending allows you to generate smooth video transitions between two prompts. It is based on [stable diffusion 2.0](https://stability.ai/blog/stable-diffusion-v2-release) and remixes the latent reprensetation using spherical linear interpolations. This results in imperceptible transitions, where one image slowly turns into another one.
# Example 1: simple transition # Example 1: simple transition
(mp4), code (mp4), code
@ -17,40 +17,28 @@ Latent blending allows you to generate smooth video transitions between two prom
# Installation # Installation
#### Packages #### Packages
```commandline ```commandline
pip install -r requirements.txt pip install -r requirements.txt
``` ```
#### Models #### Download Models from Huggingface
[Download the Stable Diffusion 2.0 Standard Model](https://huggingface.co/stabilityai/stable-diffusion-2) [Download the Stable Diffusion 2.0 Standard Model](https://huggingface.co/stabilityai/stable-diffusion-2)
[Download the Stable Diffusion 2.0 Inpainting Model (optional)](https://huggingface.co/stabilityai/stable-diffusion-2-inpainting) [Download the Stable Diffusion 2.0 Inpainting Model (optional)](https://huggingface.co/stabilityai/stable-diffusion-2-inpainting)
#### xformers efficient attention [(copied from stability)](https://github.com/Stability-AI/stablediffusion) #### Install [Xformers](https://github.com/facebookresearch/xformers)
For more efficiency and speed on GPUs, With xformers, stable diffusion 2 will run much faster. The recommended way of installation is via the supplied binaries (Linux).
we highly recommended installing the [xformers](https://github.com/facebookresearch/xformers)
library.
Tested on A100 with CUDA 11.4.
Installation needs a somewhat recent version of nvcc and gcc/g++, obtain those, e.g., via
```commandline
export CUDA_HOME=/usr/local/cuda-11.4
conda install -c nvidia/label/cuda-11.4.0 cuda-nvcc
conda install -c conda-forge gcc
conda install -c conda-forge gxx_linux-64=9.5.0
```
Then, run the following (compiling takes up to 30 min).
```commandline ```commandline
cd .. conda install xformers -c xformers/label/dev
git clone https://github.com/facebookresearch/xformers.git ```
cd xformers
git submodule update --init --recursive Alternatively, you can build it from source:
pip install -r requirements.txt ```commandline
pip install -e . # (Optional) Makes the build much faster
cd ../stable-diffusion pip install ninja
# Set TORCH_CUDA_ARCH_LIST if running and building on different GPU types
pip install -v -U git+https://github.com/facebookresearch/xformers.git@main#egg=xformers
# (this can take dozens of minutes)
``` ```
Upon successful installation, the code will automatically default to [memory efficient attention](https://github.com/facebookresearch/xformers)
for the self- and cross-attention layers in the U-Net and autoencoder.
# How does it work # How does it work
![](animation.gif) ![](animation.gif)