- Dec 23, 2018
- 752
- 575
You definitely can, use colab or replicate or whatever. Look, clip interrogation with blip2-2.7b, with sdxl prompt mode.
And you can use your own dictionary for questioning, it can help.
Last edited:
And you can use your own dictionary for questioning, it can help.
I did see the BLIP-2 but I am guessing that nearly any CLIP model won't fit into my VRAM with BLIP-2, but it looks like an interesting tool and I wasn't aware of it, I might try it later. (EDIT: I could probably run it FP8 assuming some of the 15GB FP32 Model was offloaded when not in use)
Time wise I can run BLIP-2 and append with WD-14 on 332 2k images in a few hours....
If my times are the same as yours then it would be 11 hours to run on the program.
EDIT: I'd be curious to see what the image attached is tagged as using that program if you wanted to test run it:
BLIP-2 with WD-14 (Onyx) appended -1girl
a woman sitting on a bench in a white tank top and red shorts with her hands on her hips, solo, long hair, breasts, looking at viewer, skirt, jewelry, medium breasts, sitting, purple hair, outdoors, pussy, choker, day, spread legs, miniskirt, clothes lift, mole, lips, uncensored, no panties, red skirt, skirt lift, sunglasses, tank top, lifted by self, building, mole on breast, watch, wristwatch, white choker
Last edited:
- Dec 23, 2018
- 752
- 575
Heh, I don't know why violet tanktop.
With this prompt and your aspect ratio, I got this from realvisxl, so it catches some vibe.
Thanks for the test, my thoughts:
I am fighting anchor fallacy here but I also am one of those people that pulls the beta or nightly builds and then spends hours rebuilding the version I just came from....(I really should keep to VENV's)
Your description had Spain and full round face which I felt was accurate.
But I felt the natural language was lacking if you compare the two:
a woman sitting on a bench in a white tank top and red shorts with her hands on her hips
a woman sitting on a bench with her legs bare
The shorts part was wrong so it could be a wash but the WD14 caught the clothes lift, no panties, skirt lift, and lifted by self,
Of course this is just one image, and it would be poor to judge based off just one image, I know I had some badly described images in the mix, one or two that where completely wrong.
I think CLIP interrogation is more beneficial for trying to reproduce an image that a model has been trained on, rather then providing data to train a model on.
- Dec 23, 2018
- 752
- 575
The first sentence is just an output of the first launch of the blip2, before the loop of the interrogation. There're other default parameters in my build, to make it faster or smth, and it can be changed to be equal to your output, I think.
Anyway, I had more success with training character loras using for captioning the output of the interrogator (however, not the full one) than with blip+tagger. But there're different specifics, I guess. If you want to work with poses and fetishes, etc., not with making most similar faces, then the tagger is better - or maybe you need to experiment with custom dictionaries for the interrogator.
Yeah I didn't mess with number of beams all that, I think the default settings where tested over a large group of images and then used a scale to not over describe or get the repeating terms. (Based of one article I read, I haven't played around at all with it)
I'm not sure what quality I am running at, I would guess FP8 or at best 16 as my card is not able to fit 15GB but with bitsandbytes it might actually be running at FP32 as my understanding is it doesn't need to load the whole model in unless training.
Last edited:
- Dec 23, 2018
- 752
- 575
- Jan 31, 2022
- 225
- 663
What program did you use for the blip 2 captioning?
I used Kohya to caption 768 images and it took about 3 minutes, since yours took so long was it more detailed captions or something?
You have an amazing computer if you where parsing 4.5ish 2k images a second.
(Or the model is oversized for me and causing major slowdowns)
I can get those times on the 373MB WD-Vit tagger with oynx but not the 15GB BLIP 2 model
Last edited:
It automatically pulls the one off
You must be registered to see the links
Based of other users that can get 10-15IT's per second on SDXL I am at a solid 1IT per second.
You must be registered to see the links
- Jan 31, 2022
- 225
- 663
If you want to save time in the future I'll run blip for you as long as we can find a place to upload the images to pass to each other.
You must be registered to see the links
Trained to convergence on 332 images with Natural Language and captioning that has been checked by hand and edited on 70% of the BLIP-2 Captions.
WD-14 tagging is a custom dictionary with manual appending.
- Avoid using "nude" if possible.
- Use -Large Breasts when using small breasts or flat chest
You must be registered to see the links
Last edited:
- Jun 1, 2020
- 149
- 539
Hello everyone i’d like to make similar arts like a guy on twitter Philon (Philonai95). So can someone please make similar of his works and share information about prompts/lora/tools you used to achieve it. Nothing on civitai looks the same. Known information: Forge, pony xl v6, concept art twilight.
Last edited:
- Dec 23, 2018
- 752
- 575
Well, I clearly see a mix of the styles of Cutesexyrobutts, Sabudenego and Krys Decker.
Start from there.
You must be registered to see the links
- Mar 3, 2024
- 15
- 63
Based off of the distortion in the signature I would guess that is a post effect, it looks like a wave distortion and some kind of guassian blur
- Jun 1, 2020
- 149
- 539
It could be matte painting made in photoshop since it’s mentioned on his twitter. I’m also curious about perfect hands, eyes, feet he makes in his works, is it adetailer or something else
A 3D sourced image you can blend elements together, AI does hair, 3D does hands and feet as well as posing.