Create Colorful Anime Treasure with CAT!
Follow me on X/Twitter for exclusive content: https://x.com/Citron_Legacy 😁
What is Anima? Anima is the first ComfyUI sponsored model! Please read the official announcement from ComfyUI here.
Please check the official repo important details about how to use the new base model: https://huggingface.co/circlestone-labs/Anima
You need
Text Encoder: qwen_3_06b_base.safetensors
VAE: qwen_image_vae.safetensors (Actually I baked in this VAE but I haven't tested without it yet.)
AnimaCAT_v1 - Anima-Preview x (RoxyRibbonStyle_ANIMA_Lora:0.3) x (Unreleased_MoonlightCAT_ANIMA_Lora:0.5)
Legal
The CircleStone Model is licensed by CircleStone Labs LLC under the CircleStone Non-Commercial License. Copyright CircleStone Labs LLC. IN NO EVENT SHALL CIRCLESTONE LABS LLC BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH USE OF THIS MODEL.
Description
FAQ
Comments (32)
Been watching the Anima preview for a hot minute and I'm quite impressed on how it handles.
What does this merge have to offer that stands out? What are the pros and cons of this particular merge?
I'm also really impressed by Anima.
I'm disappointed that the Anima base is not officially uploaded on CivitAI.
Here is a quick comparison of my checkpoint vs the base model: https://civitai.com/posts/26633326/
My merge is stylistic: its made from two of my custom styles
1. Exaggerated lineart and flat colors
2. Smooth shading, Bokeh/Light effects, curvy woman, and lip details
My hope is that it improves lighting and shading, makes colors pop more vividly, and delivers overall aesthetics with less prompting than base Anima.
This merge adds an extra ~1 GB to the base model so we'll see if that helps with details or not!
All my merges are an iterative improvement process. I think its is a good merge I'm not going to claim is better than all the other options. (Although there aren't many options on CivitAI right now away 😛)
Hey, I am not a lawyer as well, but looking into the license there is point 3.b saying:
"b. you must prominently display the following notice alongside the Distribution of the CircleStone Model or Derivative (such as via a “Notice” text file distributed as part of such CircleStone Model or Derivative) (the “Attribution Notice”):
“The CircleStone Model is licensed by CircleStone Labs LLC under the CircleStone Non-Commercial License. Copyright CircleStone Labs LLC. IN NO EVENT SHALL CIRCLESTONE LABS LLC BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH USE OF THIS MODEL.”"
So I'd say better include it in the model description?
Good call out! Thank you! I added it to the bottom of the description.
I think technically this is covered by that tiny link under the model's right side panel that has the license listed. But better safe that sorry! I appreciate all the work they put into the new base model so I'm happy to comply with whatever rules they have.
I guess it is nitpicking, but they are saying you have to make the lincense available AND use this Notice/Disclaimer. Now you are fully covered :D
Yeah, I hope I can try it tomorrow, I am struggling right now to get it working in forge neo (though they added support in recent commit). Only gives my black images :(
@RisingV I dont mind. Putting text in the description is easy and makes it look "more official" lol
Sorry to hear that! I hope you can get it working. I'm always wary of "it works on my machine" but doesnt work for anyone else.
I had to update the newest version of ComfyUI to be able to load the text encoder. Maybe Forge needs updates like that too?
When I try to run Anima and this like a normal checkpoint, instead of a diffusion model, I also got black images.
@CitronLegacy I fixed the issue! It doesn't work, when you use schedule type "automatic" in forge neo, but now I made cute image (though I think my newest lora is not necessary for anima) :D
I'm gonna schedule a post and then try it more tomorrow!
I made a test with different schedule types available in Forge Neo for ER SDE sampler and scheduled a post. I'd rate results by prompt adherence/quality in the following:
best prompt adherence:
Beta
Bong Tangent
good prompt adherence:
Normal
Simple
SGM Uniform
DDIM
FlowMatchEulerDiscrete
ok prompt adherence/some inconsistencies:
Linear Quadratic
KL Optimal
blurry/bad anatomie:
Karras
Exponential
Polyexponential
Align Your Steps
black image:
Uniform
Turbo
For visual quality, see for yourself, but I'd say it is good for the first two categories. Don't use schedule type "Automatic", it gives you a black image (at least for me). Test was done with 30 steps, took 21-23 s for every schedule type, so no big difference. Maybe the schedule types in (blurry/bad anatomie) category need more steps, have not tested that.
Thanks for your diligent testing! Historically I use Karras so it feels a bit weird to switch to something else. I've only used simple but I will give Beta a try!
On a slightly different topic: I'm really impressed by how clean all the images look! Anima seems to have no problem making very detailed shoes and also keeping the rest of the image looking good. Maybe I am biased but Anima just seems a bit more precise than Illustrious.
Also the background on this turned out surprisingly clean https://civitai.com/images/121340625
@CitronLegacy Well, I try to find the best settings for myself, so why not sharing them? ;)
I have been using Euler for some time now with Illustrious and scheduler set to "Automatic" so I don't really know which scheduler it was using.^^
However I think Beta is also the standard for Zimage?
I think I used DMP++ 2M Karras, when starting to make images with pony :D
Yeah the test images look really good (well with some execptions). But I haven't made much more so I can't really tell. I also made another bunch of these images with different samplers this time, but the post seems to have gotten lost^^
Here its is: https://civitai.com/posts/26656302
Maybe the background is so clean bc they also trained on non-anime stuff (LAION-POP)?
Flux 2 sampler gives good result, may be best🤔
@mifink94 Which sampler is the flux 2 sampler? Euler? Or are you reffering to some custom sampler for flux 2?
@RisingV oh, sorry, scheduler... i means scheduler. (Euler a sampler+flux 2 scheduler). SGM Uniform is good too. black image because "automatic" use Karras. Karras not working.
@mifink94 ah, ok. Mmmh, did not try flux2. Maybe I forgot that one?
In my test with ER SDE only Uniform and Turbo schedulers resulted in black images.
@RisingV hmmm, magic, whot interface do you use?
I have tested it and I can say that the baked in vae work..
Awesome! Thank you very much for testing it! I always prefer Checkpoints with baked VAEs so I'm really glad its working.
Oh yeah, also made a vae vs. non-vae test: https://civitai.com/posts/26639478
It's working without, but looks a little different.
@RisingV Thanks for testing! The version with VAE is better, because the see-through sleeves are a nice touch, but yeah they are 90% the same. Thanks for sharing the comparison so we can use it to choose what we prefer.
N/uhh.. I should be the one thanking you for the amazing model , really great work I got really high quality stuff out of it so thanks (really much!!)
Im quite conservative, but this thing pleasantly surprised me.
thenks a lot!
Boss, do you try upscaling images by anima?
Thank you glad you like it!
I haven't tried upscaling but Image to Image is really nice and cleans up images pretty well. I'd bet that upscaling is good.
I wonder when they will release the full model?O_O
May 14, 2026.
What is "Zel image saver"? Why are there so many missing nodes when I try to load generated images?
LOL Sorry!
I have a lot of custom nodes that I made but didn't share.
Zel Image saver is https://github.com/alexopus/ComfyUI-Image-Saver but with some custom modifications. You should be able to copy the generation settings that appear in CivitAI to replicate my images. My nodes are just doing automation or metadata things that wont image the image generation.
Thanks for the info!
Anima Base update pls!
I try ii THIS IS F///////G AWESOME!!!!
HELP PLS!!!!! What values Hires fix should i set for this? Without Hires the image looks great, but with Hires it everything is terrible and blurry + there's a lot of noise.
I've just noticed that this model exists. What needs to be done so this can be used via the on-site generator? :)
Thank you for interest!
Unfortunately CivitAI wont let me bid on it. Its possible that there is a glitch because I uploaded it in February way before CivitAI supported Anima models?
Anyway is based on Anima-Preview-1 so I should remake it for Anima-v1.
Hi @im_new_to_this
Thanks again for your comment! I was thinking about it ever since you said it and I decided to make the Animav1 version of this model right away. I think its close enough to GalenaCAT so I posted it there:
https://civitai.red/models/241844/galena-cat-galena-citron-anime-treasure-illustrious-and-noobai?modelVersionId=3156769
Hopefully it works well for you!