OPENGIT/stable-diffusion-webui
1
0
Fork 0
mirror of https://github.com/AUTOMATIC1111/stable-diffusion-webui.git synced 2025-02-12 00:22:55 +08:00
Code Issues Packages Projects Releases Wiki Activity

move links to the top

ClashSAN 2023-07-29 00:38:03 -04:00
parent a60925601b
commit d6d13a3f14
1 changed files with 12 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
Features.md

@ -4,19 +4,23 @@ All examples are non-cherrypicked unless specified otherwise.
# SD-XL
## Downloading:
1. [sd_xl_base_1.0_0.9vae](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/sd_xl_base_1.0_0.9vae.safetensors)
[[PR]](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/11757) | [[Stability-AI Github]](https://github.com/Stability-AI/generative-models)
2. [sd_xl_refiner_1.0_0.9vae](https://huggingface.co/stabilityai/stable-diffusion-xl-refiner-1.0/blob/main/sd_xl_refiner_1.0_0.9vae.safetensors)
## Downloading:
Two models are available. The first is the primary model.
- [sd_xl_base_1.0_0.9vae](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/sd_xl_base_1.0_0.9vae.safetensors)
- [sd_xl_refiner_1.0_0.9vae](https://huggingface.co/stabilityai/stable-diffusion-xl-refiner-1.0/blob/main/sd_xl_refiner_1.0_0.9vae.safetensors)
These models are recommended for generating, merging and training.
>They have a built-in trained vae by https://github.com/madebyollin which fixes NaN infinity calculations running in fp16. ([Vae](https://huggingface.co/madebyollin/sdxl-vae-fp16-fix/blob/main/sdxl_vae.safetensors) ) for reference
>They have a built-in trained vae by https://github.com/madebyollin which fixes NaN infinity calculations running in fp16. ([VAE](https://huggingface.co/madebyollin/sdxl-vae-fp16-fix/blob/main/sdxl_vae.safetensors)) for reference
## SD-XL BASE
[[PR]](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/11757) | [[Stability-AI Github]](https://github.com/Stability-AI/generative-models)
### Info
>NOTE: Initial loading of these models require those with 24gb cpu memory (RAM) and under to setup a large pagefile. This may change in the future.
This is a model designed for generating quality `1024×1024`-sized images. It is **not** meant to generate good pictures at `512×512`.
@ -39,16 +43,13 @@ It's tested to produce same (or very close) images as Stability-AI's repo (need
- works at minimum 4gb gpu (30XX)
```
>NOTE: Initial loading of these models require those with 24gb cpu memory (RAM) and under to setup a large pagefile. This may change in the future .
## SD-XL REFINER
This secondary model is **designed** to process the `1024×1024` SD-XL image **near completion***, to further enhance and refine details in your final output picture. You could use it to refine finished pictures in the img2img tab as well.
To try this kind of generation, you can use this extension - https://github.com/wcde/sd-webui-refiner
*To try this kind of generation, you can use this extension - [wcde/sd-webui-refiner](https://github.com/wcde/sd-webui-refiner)
You will want 6gb minimum as `--lowvram` currently isn't supported.
(You will want 6gb minimum as `--lowvram` currently isn't supported.)
# SD2 Variation Models
[PR](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/8958), ([more info.](https://github.com/Stability-AI/stablediffusion/blob/main/doc/UNCLIP.MD))