ToonYou - Beta 6 is up!
Silly, stylish, and.. kind of cute? 馃槄
A bit of detail with a cartoony feel, it keeps getting better!
With your support, ToonYou has come this far, Thx!
猬嘝lease read the information below馃檹
1锔忊儯Recommended Settings
- VAE is included starting with Alpha2 (840000)
- Clip skip: 2
- CFG scale: 8- Sampler: DPM++ SDE Karras
Sampling Steps : 30+- Upscaler (Hires. fix): R-ESRGAN 4x+ Anime6B
Hires steps: 14
Denoising strength: 0.35
Upscale by: 1.5+- Default prompts
Pos: (best quality, masterpiece), ...
Neg: (worst quality, low quality, letterboxed), ...2锔忊儯Using Adetailer
- Main UI > Extensions > Install from URL
This fixes problems with the character's eyes and face in most situations
The default usage is to simply enable it and leave it alone鉁匩ow you're good to go!
For more information, please continue below
鈩癸笍Why is my image different from yours?
I can't give you any technical help, sorry
Keep your prompts simple and correct
Tag auto complete extension to find the appropriate tags
Tags like 'Realistic, 8k, ...' sometimes ruin an image
Also These tags are often more useless than you might think
Neg Tags like 'mutated arms' are useless than you might think
Neg embedding can have a significant impact on the characteristics of a model
These are not as perfect as you might think
馃挐Contact & Support
鈿狅笍Warning
You are solely responsible for any legal liability resulting from unethical use of this model
Don't use my model as bait to drive people to your paid generation service without permission
For anything other than general personal use, please be sure to contact me
Description
FAQ
Comments (30)
I made significant improvements to the outline in Beta 3, But along the way, the face of the character I thought I had perfected in B2 changed quite a bit 馃え
skin texture effect with the light source is also different from B2, but this is probably a matter of taste.
Sometimes B3 creates images that are closer to 2.5D, which is intentional, if you don't like, add "flat color"
I'll test it enough before deciding to remove it
B2 also has its own advantages, so it'll be interesting to see how they compare
If all goes well, I think the next version will be a full release 馃槏
i still prefer the roughness and imperfection from alpha, i treat each version as each own model.
so im glad that you still keeping the old versions.
@nicetry20010聽Yeah, it's fun to look back at the Alpha days, I miss that feeling too. I was originally trying to evolve the feel of Alpha, but it was really tricky.
I think it would be fun to take the materials from that and evolve it again.
I can't help you if you complain without posting a created image
In order to figure out what's wrong with your prompt, or what's wrong with my model, you need to post an image you don't like
What if I want to complain about how much I like your work? :D
But seriously, I'm really happy to see you sticking to your guns and still working on this little marvel. All of your checkpoints do have a really distinct feel to them, even if they are diverse, it's really great :)
@KarotConCarne聽I appreciate the kind words, but some people always say, "That's weird," and then they never post an image, so I don't get a chance to see the flaws that I've gotten so used to that I've missed. It's a shame.
looks like only male characters have normal eyes, big eyes otherwise. Any way, any config, any keyword we can use to make no anime eyes with your model(s)? thanks.
Well, I don't know, the big eyes are a tradition from Alpha, as you can see. But B3 is a little bit too big 馃
Great model! The only thing I'm not feeling would be the hands, but I love the style.
Great style! Could you release a lora of it trained on NAI?
The concept of my work is to provide complete packaging, which is why I don't distribute LoRA separately. A bit weird, right?
But the bigger reason is that my data is almost gone! The recipes are still there, but I've lost a lot of my personal LoRAs 馃槀
Love the model and the style but I'm using it to render landscapes and a few animals but it's very hard to avoid having persons in the rendered image. I'm trying with different negative prompts but many times there is a human figure there.
Try using no humans
TY is not good for background generation because it is a biased model.
I'll try to improve it in the next version.
@Bradcatt聽I'm really looking forward to the next version! Your model is seriously amazing. I've tried so many others that create images in a similar style but they failed miserably with deforum (stable diffusion's animation sequencer). Your model stands out and succeeds brilliantly. Congratulations.
I just wished it wasn't so focused on human figures all the time. It'd be awesome if it had more variety of plants, animals, objects, ...
Amazing work. Thank you.
"Use Adetailer for eyes" - would love to know how to do this. I have Adetailer installed. can you share some tips for this part? I always have issues with eyes for anime drawing characters
Adetailer is an extension that works immediately after installation.
It will probably be automatically set to the PT model I wrote down.
Keep in mind that it will have less effect at too low a resolution
@Bradcatt聽I know how to use it for the faces but you said something about the eyes
I'm having a lot of issues trying to have a picture where face is not visible. Even with very heavy prompting positive and negative, part of the face is almost always in the shot
Oh, I haven't tested that one, let me know what prompt you used and I'll look into it.
@Bradcatt聽I've tried basically all I could think of but the people on generated images basically follow stage rules and always have at least their profile in view. I was unable to get them to face entirely away from the viewer even with img2img from a shot, the model gradually warps them to turn back and face the camera or at least have their profiles visible. In essence prompts like "facing away from viewer" or "from behind" or "facing away" don't seem to work at all. It's a great model anyway tho, I've done a lot of really fun pieces with it today. It really struggles with nsfw stuff but I understand it wasn't made with that in mind.
which ia do you use
I've been playing Zelda Totk lately, and I'm having so much fun that I'm running out of time to make models 馃槄
I've uploaded a ToonYou B4 test image to B3. As you can see, there's not much difference, so I'm going to skip it and make B5 (V1).
Looks great, I hope the later iterations keep the more unique characteristics of the model (mostly the face and eyes), I noticed the newer betas start to converge more towards an anime like face.
hi! its great. but issues with hands. what I need to use with that model ?
The colors look so great
versatile ASF !!!!! thank you !!!!
One of my favorite models ! I really like the style the model is going for. The eyes and face are so unique. However I have difficulty with poses and hands, even with negative embeddings. can't wait for the next update ! Keep this uniqueness and it will become one of THE models in Civitai for sure
Poses and hands are probably an eternal problem...
From B5 onwards, I will stop mixing new data and spend my time polishing the existing ones.
Best styled ever! What if I want to generate only a landscape without a human figure? Is there any good prompt idea?
By default, you should use "no humans" and avoid keywords that suggest humans.
However, this model is inherently weak at generating backgrounds, so you have to take that into account.
Details
Files
toonyou_beta3.safetensors
Mirrors
toonyou_beta3.safetensors
toonyou_beta3.safetensors
toonyou_beta3.safetensors
toonyou_beta3.safetensors
toonyou_beta3.safetensors
TY_beta3.safetensors
toonyou_beta3.safetensors
toonyou_beta3.safetensors
toonyou_beta3.safetensors
toonyou_beta3.safetensors
toonyou_beta3.safetensors
toonyou_beta3.safetensors
toonyou_beta3.safetensors
toonyou_beta3.safetensors
toonyou_beta3.safetensors
toonyou_beta3.safetensors
toonyou_beta3.safetensors
toonyou_beta3.safetensors
toonyou_beta3.safetensors
toonyou_beta3.safetensors
toonyou_beta3.safetensors
toonyou_beta3.safetensors
toonyou_beta3.safetensors
toonyou_beta3.safetensors
toonyou_beta3.safetensors
toonyou_beta3.safetensors
toonyou_beta3.safetensors