1580158
/
sd-webui-animatediff
mirror of https://github.com/continue-revolution/sd-webui-animatediff.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Better language

pull/330/head
Chengsong Zhang 2023-11-17 05:14:36 -06:00 committed by GitHub
parent 4cd270d556
commit 8ba4e297dd
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
README.md
View File

@ -231,16 +231,16 @@ FP8 requires torch >= 2.1.0 and WebUI [test-fp8](https://github.com/AUTOMATIC111
1. Add `--opt-unet-fp8-storage` to your command line arguments and launch WebUI. 1. Add `--opt-unet-fp8-storage` to your command line arguments and launch WebUI.
### LCM ### LCM
[Latent Consistency Model](https://github.com/luosiallen/latent-consistency-model) is a recent breakthrough in Stable Diffusion community. I provide a "gift" to everyone who update this extension to >= [v1.12.1](https://github.com/continue-revolution/sd-webui-animatediff/releases/tag/v1.12.1) that you will find `LCM` sampler in the normal place that you choose samplers in WebUI. You can generate images / videos within 6-8 steps if you [Latent Consistency Model](https://github.com/luosiallen/latent-consistency-model) is a recent breakthrough in Stable Diffusion community. I provide a "gift" to everyone who update this extension to >= [v1.12.1](https://github.com/continue-revolution/sd-webui-animatediff/releases/tag/v1.12.1) - you will find `LCM` sampler in the normal place you select samplers in WebUI. You can generate images / videos within 6-8 steps if you
- choose `Euler A` / `LCM` sampler - select `Euler A` / `LCM` sampler (other samplers may also work, subject to further experiments)
- use [LCM LoRA](https://civitai.com/models/195519/lcm-lora-weights-stable-diffusion-acceleration-module) - use [LCM LoRA](https://civitai.com/models/195519/lcm-lora-weights-stable-diffusion-acceleration-module)
- use a low CFG denoising strength (1-2 is recommended) - use a low CFG denoising strength (1-2 is recommended)
Note that LCM sampler is still under experiment and subject to change adhering to the [original author](https://github.com/luosiallen)'s wish. Note that LCM sampler is still under experiment and subject to change adhering to [@luosiallen](https://github.com/luosiallen)'s wish.
Benefits of using this extension instead of [sd-webui-lcm](https://github.com/0xbitches/sd-webui-lcm) are Benefits of using this extension instead of [sd-webui-lcm](https://github.com/0xbitches/sd-webui-lcm) are
- you do not need to install diffusers - you do not need to install diffusers
- you can use LCM with any other extensions, including ControlNet and AnimateDiff - you can use LCM sampler with any other extensions, such as ControlNet and AnimateDiff
### Others ### Others
- Remove any VRAM heavy arguments such as `--no-half`. These arguments can significantly increase VRAM usage and reduce speed. - Remove any VRAM heavy arguments such as `--no-half`. These arguments can significantly increase VRAM usage and reduce speed.