added img2prompt clip interrogator.

Signed-off-by: Georg Zoeller <georgzoeller@users.noreply.github.com>
This commit is contained in:
Georg Zoeller 2022-09-05 22:27:47 +08:00 committed by GitHub
parent 454e0d20e8
commit 425d582f87
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23

View File

@ -85,8 +85,7 @@ Prompts are the inputs used with diffusion models to manipulate their output.
* 🖊️[Phraser](https://phraser.tech/) - A visual prompt builder drawing on a database of examples. (Requires account creation)
* [ai-art.com/modifiers](https://www.the-ai-art.com/modifiers) - A visual reference guide to keywords.
* [pharmapsychotic/clip-interrogator](https://github.com/pharmapsychotic/clip-interrogator) - Jupiter Notebook for reverse engineering prompts from images.
### Misc/Other
* [img2prompt](https://replicate.com/methexis-inc/img2prompt) - Upload image, get possible prompts for similar results (clip interrogator)
* [rom1504/clip-retrieval](https://github.com/rom1504/clip-retrieval) - Reverse searches prompt keywords into the image dataset used by Stable Diffusion and other models. [Online GUI](https://rom1504.github.io/clip-retrieval/) available.