kamp/IOPaint
1
0
Fork 0
Code Issues Pull Requests Releases 1 Activity

update readme

Browse Source
This commit is contained in:
Qing 2022-10-20 21:03:43 +08:00
parent 6ccb6cd291
commit 2ecccb6290
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

@ -32,7 +32,7 @@
1. [ZITS](https://github.com/DQiaole/ZITS_inpainting)
1. [MAT](https://github.com/fenglinglwb/MAT)
1. [FcF](https://github.com/SHI-Labs/FcF-Inpainting)
1. [SD1.4](https://github.com/CompVis/stable-diffusion)
1. [SD1.5](https://github.com/runwayml/stable-diffusion)
- Support CPU & GPU
- Various inpainting [strategy](#inpainting-strategy)
- Run as a desktop APP
@ -87,7 +87,7 @@ Available command line arguments:
| Name | Description | Default |
| -------------------- | ----------------------------------------------------------------------------------------------------------------------------- | -------- |
| --model | lama/ldm/zits/mat/fcf/sd1.4 See details in [Inpaint Model](#inpainting-model) | lama |
| --model | lama/ldm/zits/mat/fcf/sd1.5 See details in [Inpaint Model](#inpainting-model) | lama |
| --hf_access_token | stable-diffusion(sd) model need [huggingface access token](https://huggingface.co/docs/hub/security-tokens) to download model | |
| --sd-run-local | Once the model as downloaded, you can pass this arg and remove `--hf_access_token` | |
| --sd-disable-nsfw | Disable stable-diffusion NSFW checker. | |
@ -109,7 +109,7 @@ Available command line arguments:
| ZITS | :+1: Better holistic structures compared with previous methods <br/> :neutral_face: Wireframe module is **very** slow on CPU | `Wireframe`: Enable edge and line detect |
| MAT | TODO | |
| FcF | :+1: Better structure and texture generation <br/> :neutral_face: Only support fixed size (512x512) input | |
| SD1.4 | :+1: SOTA text-to-image diffusion model | |
| SD1.5 | :+1: SOTA text-to-image diffusion model | |
<details>
<summary> See model comparison detail</summary>
@ -184,7 +184,7 @@ so you don't have to download the model every time you start the container.
The cache directories for different models correspond as follows:
- lama/ldm/zits/mat/fcf: /root/.cache/torch
- sd1.4: /root/.cache/huggingface
- sd1.5: /root/.cache/huggingface
### Run Docker (cpu)