Download
1 variant available
fp16 SafeTensor
25112201-395k-50.safetensors
Half precision, best balance • 6.46 GB
Verified: 8 months ago
v1.0 • sdxl_vae.safetensors
1040 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
(8)
Dec 21, 2025
0.5 merge between Base Model and Finetuned Model. Naming pattern comes from Evo series.
Reciting the long vertical model stack is bad for calling so I just call her "AK-Evo".
It is better than expected so I decided to release without waiting for the 2EP.
Good for 1024x1024 x2.0 highres fix, or native 1536x1536.
Show more

1090 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
2560 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
License:
Illustrious LicenseAstolfoKarmix: AstolfoMix-XL + Karmix-XL
An experimental merge for mating 2 different base model.
Discord: "Good luck".
Specification
Merge log / receipe: e2e script, log. 2 x 3 models + 1 tie breaker.
Algorithm used: "Read from bottom". "Modded DELLA". Parameter in e2e script.
(Measured in L2 norm) 87.5% NoobAI eps + 12.5% "everything else".
How to use
Karmix: "Another NoobAI / IL merge". You know the drill.
AstolfoMix: Train LoRA / merge on top of it. Tested for realistic model already. Introduced forgotten general contents.
NoobAI eps: Recovered some artist style and NSFW content. It replaced many "conflicted vectors".

