There are two files. The bigger one is the AIO, the "pruned" file is the diffusion model (you will need TE and VAE). You can find them on link bellow.
Next Versions
Adding improvements and my style.
-Theta
V1 and my style.
-Alpha
This is my own version, after a training day. Now we don't need use improvements tags.
Still is working as preview, tags or natural lenguage.
Enjoy it and more improvements will come.
-Preview.
Go to the official Anima Huggingface repo
Remember use masterpiece, best quality, score_9 unless
I only merge all to use it like a AIO checkpoint.
Description
Training with my own dataset of all times generations. Now you don't need to use score_9 and more improvements tags
FAQ
Comments (13)
can this go up beyond 2k res ?
The preview version should be used at about 1MP resolution. E.g. 1024x1024, 896x1152, 1152x896, etc.
@frakerkill_ u trained the alpha right ? is it just the same as preview ?
@Seii1 in resolution, yes cause I don't train with bigger pics. I kept same resolution.
@frakerkill_ any updated character ?
@Seii1 probably but random pictures were used
@frakerkill_ i tried using ur workflow but i got error on img saver
[Errno 2] No such file or directory: 'G:\\ComfyUI_windows_portable_nvidia_cu128\\ComfyUI_windows_portable_nvidia\\ComfyUI_windows_portable\\ComfyUI\\output\\sdas\\txt2img-images/2026-02-06\\230832_705999-374425757741297.jpeg'
@Seii1 try a base workflow. If you close all tabs it appears.
@frakerkill_ yea i used a default workflow, ur train its nice so much better consistency for anime style
@frakerkill_ i wish u could just upload the checkpoint seperate instead AIO
@Seii1 uploaded as _df or "pruned" or 3.9GB file
There's a new category for Anima models now.
Thanks 🙏🏻