Can't get rid of tights when use controlnet on
I try on negative or no on positive
it's still coming back like 9/10 img
I try on negative or no on positive
it's still coming back like 9/10 img
I'm trying to get Stable to create a face image without eyelashes. It's the one thing keeping me from getting the perfect face texture for a Daz Face Transfer (it draws the eyelashes on the eyelids). Even when I use Img2Img with a really low denoiser, it still adds the eyelashes. I've tried to use eyelashes in negative prompts. Any suggestions?
- Dec 31, 2016
- 316
- 708
considering eyelashes is a very natural and common thing for a face to have, you might need to remove tags that are linked to having "normal features", tag such as "disfigured" and/or "mutilated" (and similar) in negative might be fighting/preventing it. Even a simple "ugly" might be causing it.
- Dec 31, 2016
- 316
- 708
what are you using controlnet for, what "image" is being used for it.
Does the image contain the tights or are they showing up just because of generating. If they already are in the image used for controlnet you might just need to find another image with that pose/scene. Reducing the importance of controlnet and making prompt more important could work as well. There should be an option for which is given "priority", 3 option along the lines of balanced, controlnet or prompt
Lora Test WIP (PNG Prompts Embedded)
Testing out a chubby LORA I have been training thought I would share the prompts.
Working Title Do not try in Egypt you will face a serious punishment.
Testing out a chubby LORA I have been training thought I would share the prompts.
Working Title Do not try in Egypt you will face a serious punishment.
every image... nude leg to just me drawing from scratch
every single option of controlnet depth line art etc
every checkpoint like 10+ of them that I experiment
the tights just always popup sometimes somehow
ahh... sorry, I would never bring any question on
My work just too much complicate like create porn comic
and it has some specific cloth design in it
so there are too many factors to be the problem
thanks anyway
- Jan 24, 2020
- 1,401
- 3,808
Don't forget to try adding weight to the negative prompt. Example: (tights:1.5) .
Are you using any Lora or embedding? That could be the problem. Even if you try many checkpoint models, if all are geared towards anime for instance then it's likely to come from the checkpoint because it's so common in anime. If you want the legs to be bare, use this in the positive prompt. In the negative use "leg wear" . You can also work with the color, if it's always white tights use "white legs" etc.
- Dec 31, 2016
- 316
- 708
if it happens with almost everything it should be possible to great a random image to share so it will be easier to help you figure out what's wrong. We can help figure out if it's with the prompt or coming from a different thing. If you don't want to share what you're specifically working any similarly prompted image where the tights are a problem would work.
Also, by any chance are you using a language translation mod/extension for the prompt? If so that could be causing the confusion, there's a lot of words in languages that have multiple meanings and multiple translations. Just thing of a simple word like "mine" in English which has at least 3 very different meanings: as "ownership" - that thing is mine, a type of weapon/explosive, and gold/silver/coal/etc mine.
To early...nah
For my machine I generate 768x768 batch size of 2 until I find an Image that looks decent
Then in-paint the upscale image (Natively) at 1536x1536 (With the WAS suite upscale)
I have the impact pack and was suite installed to do the full 4k upscale with pipelines and mask and all that but have never bothered to do it.
For a time reference on a 3050 the 2x batch of 768x768 takes 24 seconds
The in-paint of the 1536x1536 takes 70 seconds
For my machine I generate 768x768 batch size of 2 until I find an Image that looks decent
Then in-paint the upscale image (Natively) at 1536x1536 (With the WAS suite upscale)
I have the impact pack and was suite installed to do the full 4k upscale with pipelines and mask and all that but have never bothered to do it.
For a time reference on a 3050 the 2x batch of 768x768 takes 24 seconds
The in-paint of the 1536x1536 takes 70 seconds
Daz render (model uses textures created in Stable Diffusion), then putting the frames back through Stable to get the face I really wanted, then used Flow Frames to smooth out the animation a bit. I tried it with Roop, but liked the results without it better. I used a 0.2 denoiser strength.
- May 18, 2018
- 215
- 2,167
- Dec 31, 2016
- 316
- 708
(warning, post potentially horrible at getting the intended intention across)
don't know if it's intentional or due to image compression etc, but quality wise (graphically) it seems very low compared to what we know you can get from AI. It still looks very much like a "low textured daz", if that makes sense. I'm not having a go at the work etc, i'm just not getting the sense that you're getting or taking advantage of the level of detail/quality you could be getting from the AI
- Jan 24, 2020
- 1,401
- 3,808
I tried Clarity, Elegance, Deliberate, Experience. Elegance worked the best for me.
- Sep 26, 2017
- 462
- 768
- Sep 26, 2017
- 462
- 768
- Sep 26, 2017
- 462
- 768