Anima LLM LayerWise (FP8-FP32)
Use this in place of Qwen3_06B it is loaded as CLIP
FP8 VERSION TENDS TO SMOOTH DETAIL COMPARED TO FP32 or BF16/FP16
Anima Artist and Character triggers fully working
Full FP32 Training - Adam not 8BIT
Uncensored LLM can be used for story or text generation
FP8 Model has best of both worlds with 50% weight reduction and FP32 blocks where it counts.
Comfy UI users --fp32-text-enc or --bf16-text-enc can be placed in your launch script to force BF16 or FP32 casting of the LLM
Note: Top rated images where used for prompts as I do not know Anima well.
Description
FAQ
Comments (32)
can you upload the fp32 or if you have fp16 also?
Yes
What this even is? Lora? base model?
It's a text encoder, which Anima uses as CLIP. @Felldude mistakenly set it as checkpoint.
It is loaded by comfy as a CLIP, it is technically an LLM and still works as such - However if set as CLIP or Text Encoder then Civitai does not correctly show what resource it is intended for
@Lizardon1025 aaahhh, Thank you! Got it!
With Anima LLCM LayerWise FP8 the quality is sadly generally slightly worse compared with the standard Qwen 3 0.6B CLIP and the size is only about 11% smaller :/
Anima LLM LayerWise FP8 1MP
Qwen 3 0.6B 1MP
Anima LLM LayerWise FP8 2.4MP
Qwen 3 0.6B 2.4MP
https://huggingface.co/Qwen/Qwen3-0.6B-FP8 would likely have less errors if tested over 1k images seed to seed.
However if used as an LLM the results of that model are also not uncensored, this model is mostly uncensored although hallucinates when asked math questions sometime compared to base.
just tested this model, I am more satisfied with the result when it comes to simple comic.
Thanks
Thx for taking care of Anima. :-)
I've just tested it while in a middle of a generation session and ... It doesn't tokenize "girl" like Pony or Illustrious, but like Flux. i.e. the 6-8 years old girl. This lead to immediate deletion of generated image.
I'll probably need a specific gen session to fully test this beast. ;)
I just wanted to warn other people about the "girl" oups.
This LLM is trained on QWEN chat template and not this dataset. However it likely has some answer to that if you look at when male female, man woman is used vs the WD14 style tags.
I did not have any issues with 1girl in anima base 3 preview - The images mostly came back large breasted anime females
Cant say that this TE is actually a better alternative. Its definitely not worse, its just... different?
Based on my limited testing (on the same seed), the images come out a bit more detailed sometimes.
NL prompt understanding is roughly the same, tag prompts understanding feels a bit worse, nsfw prompts (both nl and nsfw) - kinda the same in terms of expressivity and concept understanding.
Based on my experience - TE was never the problem with the censorship of the diffusion model. Even tho Anima is completely uncesored as well from the beginning.
What exactly is this model, I wonder? Is this just a finetuned qwen3 0.6B?
QWEN never released FP32 variant of 0.6B - as this is a full finetune it likely would train better assuming you tokenized in FP32
It also will return uncensored LLM responses so it could be loaded in comfy and used in think mode to enhance prompts (Not directly)
@Felldude oh, okay, thanks for clarification!
@Felldude how can i utilize it in "think mode" with ComfyUI? Thx.
@PurePrompt It would require a special node, however this model size is very limited in think compared to mistral 8b
更换了这个clip之后我经过测试发现同一组提示词做出来的图片更加多样化了，之前在使用qwen3的时候发现，如果我不更改提示词，做出来的几张图片差别都不是很明显，不管是动作角度还是场景，基本都大同小异，换了这个以后做出来的图片在遵照提示词的前提下，图片内容有了更加自由的表达，我觉得这很好，但是有一个问题是，换了这个clip之后，之前所使用的人物名称方式好像不再能够识别出来了，比如我之前用qwen3的时候，wilhelmina \(brown dust 2\)就可以直接做出来我需要的人物，但是换了这个以后就做不出来了，不知道是不是人物名称的写法需要变更。
而且我发现在使用了这个clip之后，手指的精细程度有所折扣，我在制作一个spread pussy的动作时发现，十张图片里只有一张图片的手指是正确的，其他的都是有问题的。
@yeyebeixin 你是在哪个版本中发现 BF16 和 FP8 存在字符问题的？
@Felldude 我应该下载的是fp16，测试后发现，非常大众的人物还是可以靠名称就能做出来，比如rio和raiden shogun，但是比如我之前说的wilhelmina，就需要加权重后才可能做出来比较还原的，在有些时候做出来还是会出现不太像的问题，之前qwen3就没有这种问题
我認為原來的 Qwen 3 0.6B 是較為優勝 !
但 FP32 對女孩的年齡的理解則更強
I believe the original Qwen 3 0.6B is the better choice !
However, FP32 has a stronger understanding of girls' ages.
why the download file name is similar to one another "animaLLMLayerwiseFP8_v1" ?
I'm not sure what your question is
@Felldude The downloaded file is exactly as I mentioned. Even though FP32, FP16, BF16, and FP8 options are listed, I'm not sure if Civitai is just glitching out, but I'm afraid I didn't get the right version of the CLIP model. For example, if I click download for the FP16 version, the downloaded file name says 'FP8'. This makes me think I didn't get the right file.
@monicalucci It is likely the internal naming Civitai uses - you can open the full drop down list and reference the file size, that would be your best indicator other then checking the block format
How should this model be used in the web UI? In which folder should it be placed?
What I don't like about this CLIP is that it knows less concepts. For example it can't generate Miriam from Bloodstained RotN. Other than that it's a nice jump in quality.