(9/26/2026): Distilled ckpt will not be updated. Use the new standalone acc LoRA here. After v2.4. All versions will be the "base" version (not distilled).
Update log and version info: link.
RDBT [Anima]
A general finetuned base model, better overall quality, better prompt adherence, less artifacts and errors.
Dataset contains ~10k images, handpicked by professional amateur artists, captioned by latest LLM. Accurate body/hands anatomy. Complete background.
Some cover images look ridiculous; they're just for demonstration purposes for corner cases.
There is no overfitted default style. Because the dataset is big enough. It's a feature not a bug. You must specify @style in prompt, or use a style LoRA. Otherwise, you will get random/mixed style.
If you're not good at mixing LoRAs for a pretrained model, I also released a ckpt that merged many useful things, here. Out-of-the-box high quality, 16-step fast generation.
If you're an advanced user and want to minimax everything: RDBT is trained as LoRA natively: link.
16-step Acc LoRA: link.
Usage:
Settings:
Base version: has a suffix "base". CFG 4 and steps 24+ is recommended.
Distilled version (discontinued): CFG: 1. Steps: 16+.
Sampler: Euler (best diversity), Euler a/er_sde etc. (better stability)
Res: 1MP
Prompt:
Always specify @style in prompt, or use a style LoRA. Otherwise, you will get random/mixed style.
Quality tags:
Omit ALL quality tags. The fine-tuning dataset has higher quality than "masterpiece". Thus quality tags don't have effects. Omitting those redundant tokens allows LLM to pay more attention on other words.
FAQ:
Why I won't bake a default style:
If a model has a "default" style (ignores prompt and is always active). We call it "overfitted". Technically, it's not a feature, it's a bug. This means the training dataset is not big enough, and the model has lost its ability to generate other styles.
The goal of RDBT model is to "perfectly" reproduce styles. As some of you know, I use this model to aid in drawing. I need unique textures and details, instead of uniformed 2.5D AI slop style.
This model has excellent compatibility. You can stack any type of Lora on it. After all, it's you who decide what style you want, not me.
RDBT can't remove nor resist overwhelming Al slop effects
Too long, see: link.
My homemade distillation vs Anima official turbo model:
Official turbo: 8 steps. High stability, low entropy. Adds a strong 2D anime filter that will overwrite style and cause style shifting.
My homemade distillation: 16 steps. High diversity, low stability. Minimal style shifting.
Sharing merges using this model is not allowed.
This mode is a free and it will always be free. This "restriction" won't affect anyone. It's only aimed at those who steal others' models to sell.
Known model thieves: NukeA.I (selling this model behind paywall on tensorart).
Because he is such a jerk I wrote a story about it. Also contains a guide for trainers about "how to bake special trigger word into your model".
Description
p1 [fp8]:
fp8 anima preview. Uploaded here for convenience.
More about ComfyUI fp8, see ComfyUI docs TensorCoreFP8Layout.
FAQ
Comments (39)
We might finally have the "Illustrious killer"
Good to see NoobAI's approach of focusing on artist names.
Model is still in training, so results are can suffer from bad anatomy or inconsistency. Also artist names are not an addition like with Illustrious, but almost a requirement to get good results. Use them like @{artist name}.
This model has zero involvement with the NoobAI team!
@NamelessKing2 I know, if I am not mistaken, it is one guy. I am just glad that shizo tagging of PonyXL is not standard
As for now it just feels like much worse, but easier to use and faster newbie image.
it's not bad but a bit disapointing with output quality
Prompt adherence is just insane!
Getting great results ♪(^∇^*). (it's uncensored btw, understands a lot of concepts, better than lumina)
Hope this model gonna hype up, cause it is a potential Illustrious killer.
On my 3080 (12 gb), 30 steps it takes 22 sec per image generation
Uhm... where is the patch? i m missing something?
it is for old GPUs like turing architecture, if have 30 series or newer than you not need to worry about it.
I tried it, and placed the file in this directory: ComfyUI\custom_nodes\anina_fp16_patch.py
@krigeta I have an rtx 2060...so yea
this patch is good for amd gpu's as well
The model is a beast, fast, real good quality even on base res gens without hires, very good prompt adherence, more artist and character knowledge than Illus and nsfw capable with regular language and danbooru tags, and this only the preview model lol.
Thank you. Where do I put the patch file?
I tried it, and placed the file in this directory: ComfyUI\custom_nodes\anina_fp16_patch.py
lora training and controlnet and we got the best anime model right here of 2026.
I dont understand, what are those files? Is circlestone labs released fp16 model?
Hello, can you also add fp16 patch to z image base?
read on comfyui github he did a patch for z-image but can't find it now
@xpnrt that patch no longer works.
@3059714361 no, z image base is way more f**ked up than turbo. Seems they continue training the model, a lot. I guess the "base" mode we see right here, is not the real base model of turbo.
Holy this model is insanely good also MOSTY follow your prompt
The model is great! :3 can't waut to see others use it!
Can someone please explain why I'm getting a mismatch with the suggested text encoder? Despite using Qwen_3_06B_base, I still get "Error(s) in loading state_dict for Qwen3_4B: size mismatch for model.embed_tokens.weight: copying a param with shape torch.Size([151936, 1024]) from checkpoint, the shape in the current model is torch.Size([151936, 2560])."
I've tried both anima_preview and animaFP8_preview, as well as changing the various load clip types (Stable Diffusion, Cosmos, Qwen Image). Thanks in advance for any response.
Update your comfyui?
@ZootAllures9111 Thanks for the reply.
After updating comfyui, everything worked as it should 🤷.
FYI, the FP16 patch will not be faster on 1650 / 1660 series Turing GPUS, they don't have proper FP16 support.
Thank you so much for creating this patch! However, I encountered an issue during sampling: expected mat1 and mat2 to have the same dtype, but got: float != struct c10::BFloat16. > Does this patch only support FP8? I am currently using the original version of Anima. If that’s the case, I will switch to the FP8 version instead. 🥹💕
I initially encountered a similar issue; simply removing the UNET settings in FP16 resolved it.
Perhaps it conflicted with a patch, so restoring the default settings might be necessary.
@dawn66666666 Thank you for your reply! How should I go about deleting the 'fp16 unet setting'? I'm so sorry, I’m not very tech-savvy with this. 🥹
@shigjfg I apologize, I'm not an English user, and I'm not sure if the following translation will be accurate. In my ComfyUI launcher, there's an advanced option called "Calculation Precision Settings," where you can set "fp16, bf16, fp8, or determined by ComfyUI."
@dawn66666666 okay,thank you very much for your answer.❤️
The patch made my anima gens 6x faster, thx man
Thanks, this greatly improved the speed of my Tesla V100; it now takes about 35 seconds.
It used to take 130 seconds.
It's a f***ing amazing model! Know a lot of characters, A LOT of styles/authors, follow the prompt, very fast and lightweight....
Well, my job is done here. Why should I retrain all my styles for ZIT/Klein when this model perfectly replicate almost all of them out of the box, and it's not even a final version?
12/10 for model, and HUGE respect for a company that produced it.
You said it, it's killing creators and you're happy about it 😂🤣
@GlowingGuardianGirl There are still many things that this model lacks, so there is room for improvement. Because booru-dataset contains... mostly very specific artists.
But yes, the ideal model is one that can do everything out of the box and does not require additional training =)
Dumb question,where should I put the patch to apply it?
# How to use:
# Put this file in the ComfyUI "custom_nodes" dir.
# Use "ModelComputeDtype" node and set dtype to "fp16".
# To disable the patch, remove the file, or rename the ".py" suffix, to something
# like ".disable", whatever.