You can try any model you want, however I really suggest using AutismMix Checkpoint

This model was trained using:

• 1024,1024 size images

• 400 images

• 1 step per image

• 20 epochs

• 4 batch

• 2000 steps

LoRA settings:

• Weight: 0.5 - 0.8 (Might be a bit undertrained, if paired with multiple loras with high weight this gives bad results, might fix in a future release. For consistency try to avoid weights of 0.9 - 1.0 and stick to 0.5)

Base model settings:

• Steps: <30

• Width: 896px

• Height: 1132px

• Sampler: Euler a

• VAE: None

• CFG Scale: 3 - 5

• Clip skip: 2

Upscaler settings:

• Upscaler: Latent (Nearest-Exact)

• Upscale by: 1.5x

• Denoising strength: 0.55