Comments (21)
I have noticed that issue also at the 768x768 resolution. It's possible that is an issue with Stable Diffusion in general being trained on 512x512 but This might have been trained with a different resolution. A temporary solution might be using a lower resolution.
from hentai-diffusion.
I have tried in 512x512 but still get the same result, and 90% of the images are censored like ecchi anime, 5% left like the nipples and other sensitive parts are disappeared
from hentai-diffusion.
Well for one you have censored and mosaic_censoring in your prompt and negative prompt. I assume the main prompt takes precedence in generations which is why you are seeing censorship still. The missing sensitive parts might also be due to the negative prompt removing "bad/poorly drawn" sensitive parts. You can try running with no negative prompt and then just add terms to the negative prompt as you notice issues. More or less sampling steps might also help. I tried running your prompt at 768x768 and the results were mostly fine. Also as a side note, your prompt was a bit too long for my ui so the prompt after "puckered" was cut off so most of mine are missing the more suggestive parts.
Steps: 30, Sampler: k_euler_a, CFG scale: 9.0, Seed: 332250147
My results
from hentai-diffusion.
I also had problems with generating images with 2+ people, it cannot do actions like hug, hold hands, or bent over. Their limbs always got collapse or duplicate
from hentai-diffusion.
Not sure what to tell you about that. I'm not seeing those issues. Have you tried rearranging your prompts? It usually helps to put the most important things near the front of the prompt.
from hentai-diffusion.
I met this errors
from hentai-diffusion.
I just realized this. When I used 512x512 image size, the generated image gets fewer errors and is sometimes cropped like this. But when I changed to the larger size, I met all those errors I mentioned above
from hentai-diffusion.
That's not surprising, the cropping thing is pretty common with Stable Diffusion in general. If you haven't already you can try adding "cropped" to the negative prompt or you can try changing the aspect ratio of the generations to be portrait or wide to better reflect your desired output.
I believe most models are trained at 512x512 so that explains why fewer issues show up when you generate using that resolution.
from hentai-diffusion.
I can use 512x512 for now, but is there any way to get more detailed body parts? Like n*pple,*ss or b**bs.
from hentai-diffusion.
In theory you could try generating just thing you want to be in high detail by itself and then use image editing software to replace the less detailed parts. Terms like "highly detailed" might also help(I haven't done extensive testing on this) or you can try using img2img with masking but I can't give you too many tips on img2img, I'm still trying to figure out a good process for that one myself.
from hentai-diffusion.
I also think the generated images are gloomy. Is there any way to make them bright? I had tried to add prompts like "contrast, vibrant" but it didn't help
from hentai-diffusion.
I met this errors
how do you even get this high resolution results. Mine are very low. I've tried getting the same results as you with the seed / input but I keep getting different results
from hentai-diffusion.
I met this errors
how do you even get this high resolution results. Mine are very low. I've tried getting the same results as you with the seed / input but I keep getting different results
try to add "highres, absurdres" to the prompt
from hentai-diffusion.
I tried, not much improvement. Even if I try exactly the same promt you added in the first post I get different results :(
from hentai-diffusion.
I tried, not much improvement. Even if I try exactly the same promt you added in the first post I get different results :(
I used this setting :v try
Steps: 150, Sampler: Euler a, CFG scale: 20
from hentai-diffusion.
I also think the generated images are gloomy. Is there any way to make them bright? I had tried to add prompts like "contrast, vibrant" but it didn't help
You can try adding terms like "happy, bright, joy" Those should adjust the "mood" of an image. I uploaded some examples to the gallery.
from hentai-diffusion.
I tried, not much improvement. Even if I try exactly the same promt you added in the first post I get different results :(
Just FYI those were done at 768x768 resolution. I think the default for most tools is 512x512. Not sure if you were talking actual resolution or perceived resolution as @LuongPhuHoa was describing.
from hentai-diffusion.
@Kuroseji is k_euler_a just the default Euler a? I'm using the latest Stable Diffusion and HD-17. Getting different results weird with the readme negative propt / negative promt of @LuongPhuHoa
from hentai-diffusion.
k_euler_a should be the default Euler a, my ui is isn't the automatic one most people use. Good catch on the negative prompt, I don't use the readme negative prompt. It had a lot of duplicate terms and things I didn't necessarily want excluded so I built my own.
My UI doesn't save the negative prompts with the positive one but I think this is the correct one
"bad anatomy, blurry, disfigured, poorly drawn face, mutation, mutated, poorly drawn hands, extra_limb*, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, artist name"
from hentai-diffusion.
@Kuroseji Is there any way to adjust the character's emotions? I tried "ahegao,horny" but it didn't work much
from hentai-diffusion.
"smile, embarrassed, evil smile, serious, blush" have all worked for me and I assume other terms work. If possible try going to one of the boorus the model is based on and researching tags. Also if possible rearrange your prompt to put the more important terms closer to the front.
from hentai-diffusion.
Related Issues (20)
- AttributeError: 'NoneType' HOT 9
- Comparison between HD-18 and HD-17? HOT 1
- KeyError: 'state_dict' with HD-18 HOT 3
- Help needed HOT 1
- Where to change share to true?
- KeyError: 'state_dict' Cannot load model
- Automatic brown "grayscaling" HOT 2
- HD 18 does not install on Diffusionbee HOT 1
- OS Error winerror 127 HOT 2
- Guide for mastering the prompt HOT 1
- HD 18 Out of memory error on webui, safetensors, pruning
- Is there a way to do a keyword search to see what prompts the model has been trained on? HOT 3
- Bruh the website doesn't work HOT 1
- can't find "lauch( )" HOT 4
- no xformers, do I need it? (HD-22) HOT 1
- Training HD-22 with LoRA/Dreambooth and contributing to project
- help what is this and what do i do?
- Pip version 23.1.2 Not being Recognized HOT 3
- I keep getting this error "LayerNormKernellmpl" HOT 5
- Tutorial sucks
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from hentai-diffusion.