Failed Experiment
12h (on 18) in my training of V1, i had a power outage... so i took a minute to check where i was. Epoch 9... of a failed training. Because, i started the training on the Turbo version of the model instead of the normal one. Let's say it messed up a few things 😅
Not wanting to throw it away, i managed to salvage stuff and here we are. An INT8 Convrot standalone version of this model. It kinda works, but not in the way I wanted. Works like V1, is not AIO but with Turbo. And gives better results with Euler A / Simple.
V1
This model is a finetuning of my previous conversion to ANIMA 2.9B of UnNamedA.
Usage:
/!\ Turbo model: CFG 1~1.5, Steps 8~16
ER SDE / Beta or euler A / sgm uniform
Positive prompt: masterpiece, best quality, highres, realistic, <your prompt>
Negative prompt: worst quality, low quality, blurry, anatomical nonsense, text, watermark, signature (optional: poorly drawn face, mutated face, ugly, cropped, out of frame, 3d, cgi, render)
Flow Shift: 3
HiRes.Fix: denoise 0.3, same CFG, same number of steps has standard pass, 4xNMKD Superscale
AIO: This model contains the VAE and TE
Build:
Unlike classic ANIMA models, UnNamedA also has an heritage from Cosmos 2B which brought some "glitches" when converted (some strange change in the face and a "grain" on the pictures). That's why i de-turboed UnNamedA 2.0, converted it to 2.9B and did a new pass (two actually) of finetuning directly on the 2.9B version using this tool.
After some testing and merging to avoid outliers, i re-merged at 0.7 a new turbo (it really gives better results): the original cosmos2 turbo to avoid bringing anime aesthetic in the mix was converted into 2.9B via this script and then cleaned of incompatible keys.
Here is a quick comparison:
UnNamedA V2.0t-29B
UnNamedA29 V1
The "grain" can be seen all over the hair and skin on the previous version and the teeth where a bit strange.
NB: Yes, I'll do a V2 to further train this model, since i feel it lost a bit of "texture" in the process (and this time, i'll do a proper teacher/student training).
PS: A V1.5 is undergoing training:
GPU goes Brrrr (64 dim LoRA, 1536px resolution, i am nearing what i can train locally)
~8h done, ~10 to go!
Slowly going doooowwwnnnn...
Thanks for reading! 💜
Description
Posted on Civitai, upload found elsewhere are FORBIDDEN and done without the author permission.
FAQ
Comments (3)
I really like all your great Checkpoints and LORAs. Would you consider doing a Turbo version of AnimaYume v1.5 (base) as it's a great anima base fine-tune That is still a 2B parameter size like the original model: "This version was fine-tuned on Anima Base v1.0 using a variety of datasets, including Danbooru, e621, Gelbooru, and Konachan. The dataset used to train this version contains 5 million images (all data collected up to August 6th, 2026), with nearly 25 million captions across different caption types (e.g., tags, natural language, chain-of-thought, etc.) corresponding to those 5 million images. This version was trained for 12 epochs and was just finished on September 5th, 2026, so I haven't had enough time to conduct extensive testing yet . This is currently a base version without any aesthetic tuning". https://civitai.red/models/2385278/animayume?modelVersionId=3300637
The creator duongve13112002 is great to as they've been doing Anima Checkpoints and LORAs ever since preview one.
As much as i can do things with other creators' models, i would rather avoid making stuff instead of them on their own checkpoints. ^^;
You can also ask the original author if they would like me to make an ANIMA 2.9B, All In One version with Turbo included, in INT8-Convrot format. This way, if they are OK with it, i can make it available on Huggingface for them to download and post on Civitai themselves.