Create & Edit Images Instantly with Grok Imagine

Try Grok Imagine
Skip to main content
AingDiffusion - v12 thumbnail

AingDiffusion - V12

by ModelsLab
aingdiffusion-v12
Text to Image Community ModelFree for Premium UsersLLMs.txt

Version 12 is ready faster than I expected.

Improved overall model performance is evident with a more mature look, thanks to the new dataset and advanced merging techniques.

The current VAE integrated into the model is vae-ft-mse-840000-ema-pruned. However, this VAE tends to produce less vibrant colors. It is recommended to switch to color101 VAE for better color pop. Ensure to use hires-fix to correct the blurriness issue associated with color101.

===

Thank you gpt-4-turbo for making the changelog sounds more professional.

API PlaygroundAPI Documentation