Really tried to make this work, but I'm struggling with low samples and bad quality samples for training...
It works, sometimes. Anyway I think it's fine for now, might re-train in a future, for now I think it's good enough.










You can try any model you want, however I really suggest using AnimagineXL 3.1 checkpoint for XL and AutismMix checkpoint for Pony.
Base model settings:
Steps: <30
Width: 896px
Height: 1132px
Sampler: Euler a
VAE: None
CFG Scale: 5 - 7
Clip skip: 2
Upscaler settings:
Upscaler: Latent (Nearest-Exact)
Upscale by: 1.5x
Denoising strength: 0.55
LoRA settings:
Weight: 0.7 - 1.0
Really tried to make this work, but I'm struggling with low samples and bad quality samples for training...
It works, sometimes. Anyway I think it's fine for now, might re-train in a future, for now I think it's good enough.
1. Os direitos dos modelos repostados pertencem aos criadores originais.
2. Criadores originais que desejam reivindicar seus modelos devem contatar a equipe do SeaArt AI pelos canais oficiais. Clique para reivindicar
