clipseg VS unprompted

Following the comments to this old post, I tried to use in-painting with manual mask selection. I didn't get beautiful results but I'm sure with some tweaking, I could make it better. The main problem I had was having to manually select the area where I wanted to place the logo and trying to resize my logo mask to the fit the segment. I tried some automatic segmentation tools (Clipseg and Segment Anything). I couldn't tell the segmentation models to find a good area to for logo placement (i.e. some small flat surface). Given the complexity of what I was dealing with, I think there could be a better way (XY problem).

The addon utilizes clipseg for region masking, which was trained on "an extended version of the PhraseCut dataset" (many thousands of images.)

You'll also need to make sure to update your clipseg repo. The script won't do this for you. Namely you just need to update this models/clipseg.py file to ensure your clipseg has support for the new model.

For localisation at search time I ended up using OWL-ViT. This worked really well. I did not try Detic or CLIPseg but would be interested to hear if anyone else has tried these?

clipseg is an image segmentation method used to find a mask for an image from a prompt. I implemented it as an executor for dalle-flow and added it to my bot yasd-discord-bot.

Automated Replacement (txt2mask) by clipseg

I'm pleased to announce the release of Unprompted v10.0.0, the Swiss Army knife extension for A1111. This is a major update that brings a number of new features and improvements, including:

Unprompted: https://github.com/ThereforeGames/unprompted

you can get the same effect with unprompted zoom enhance feature. just paste this into the prompt field.

It's been a while since my last Unprompted post, so I wanted to share some of the new things you can do with this extension. 🙂

Also if you're curious, check out the Unprompted extension's implementation of img2pez for a1111 in img2img. Basic gist is that it uses machine learning to examine the image and tries to find tokens that would likely produce that image. I've found it to be pretty far off the mark most the time, but the terms it gives you can actually be quite useful.

There's a feature in unprompted that does this.

One thing to consider: there is an extension that will let you write some scripts as prompts, and it extends what you can do with wildcards. https://github.com/ThereforeGames/unprompted.git

Solution for 9.2.0: Use modified https://github.com/ThereforeGames/unprompted/issues/84 you posted. This made a stitch image in %TEMP% and had the modified image displayed in Auto1111 GUI. Only reason I am @ing is because if I had this issue on 9.2.0 I'm sure others are. I had to use FULL shortcode in wizard zoom enhance section; I had to use FULL shortcode in wizard zoom enhance section; [if batch_index=0][after][zoom_enhance show_original mask='face' replacement='[insert prompt]' mask_sort_method='left-to-right' upscale_method='Nearest Neighbor' downscale_method='Lanczos' blur_size=0.03 cfg_scale_min=3.0 denoising_max=0.65 mask_size_max=0.3 mask_method='clipseg' sharpen_amount=1.0 color_correct_method='none' color_correct_timing='pre' color_correct_strength=1.0 min_area=50.0 contour_padding=0.0 upscale_width=512.0 upscale_height=512.0 hires_size_max=1024.0][/after][/if]

It was a long time ago I used it but I think it takes some learning I would suggest reading the starter guide the short code relates to the extra detail but you need to learn how to write it I'm pretty sure there is a built in helper sorry I haven't used it extensively there must be a video guide on YouTube too there is for almost all of this ai stuff https://github.com/ThereforeGames/unprompted/blob/main/docs/GUIDE.md

And the updated extension here: https://github.com/ThereforeGames/unprompted