Available at https://tensor.art/models/597922149832853677 !
Good day, everyone!
Thank you for your interest in my model, this model is based on my previous model "Pika's Animated Mix"
But what's new?
I trained this model on a style which is very close to the style of Niji V5, it has a strong cinematic effect and requires very grammatic input prompt to get quality images!
Also the model is very flexible in style, try it yourself!
The model comes without VAE!
Here are my recommendations:
Sampler: Euler a, DPM2 a Karras, UniPC
Steps: 28-50+
CFG: 4.5-8
VAE: Any Anime VAE you like.
Clip Skip: 1,2
Negative prompt: (easynegative:1.1), (verybadimagenegative_v1.3:1), (low quality:1.2), (worst quality:1.2)
Enjoy using it and be sure to share your results!
P.S: I hope your results are better than mine! :D
Looking forward to your feedback <3
Description
-improved hands
-improved faces
-improved backgrounds
-improved colors
-improved lights and shadows
-more variable
FAQ
Comments (10)
The main thumbnail gives me mesugaki vibe and it annoys me to no end that it is not intentional
You can see in the image information the model with the name GGTEST, do not worry it is the same model, just renamed
有特定触发的提示词吗
CAN ANYONE HELP ME WITH THIS ERROR
A tensor with all NaNs was produced in VAE. Use --disable-nan-check commandline argument to disable this check
Right click webui-user.bat and edit it.
Locate "set COMMANDLINE_ARGS="
Now add these to the line after the = sign. Remove the "".
"--no-half-vae --disable-nan-check"
That should resolve the issue.
I've added you on discord <3
I sadly don't get any result with this model. Using Easy Diffusion 2.5 and using the exact same settings. But the result is always the same purple gray pixelated mess, even with different settings. Also activated beta diffusers to get further setting possibilities, but also didn't help. :(
A very cute anime model, I like it. Good responsiveness and variety, cool neat graphic style, correct anatomy. Everything is in place. Great job! Thank you.
Way ahead of its time. I think this ended up being the best SD 1.5 anime model I had the pleasure of working with. :)
For those struggling w/ compatibility/errors, try Forge Classic UI - that's able to handle it, at least.