Recently loaded
Download
1 variant available
560 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
3610 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
2010 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
(10)
Oct 18, 2026
v1.0 - initial release. Three-way weighted merge, UNet only.
Toon3DMix XL is a three-way checkpoint merge aimed at feature-film 3D cartoons: rounded stylized characters, big expressive eyes, soft global illumination and warm bounce light, while keeping the stable anatomy and prompt following of the Illustrious ecosystem.
Recipe: 0.45 x Pure-Cartoon XL (Pixar 3D, Illustrious) + 0.30 x WAI-illustrious-SDXL v17 + 0.25 x Illustrious-XL-v1.0, applied to the UNet only (VAE and text encoder inherited from the first model).
What you get:
Rounded, appealing character design with film-grade subsurface-looking skin
- Soft studio / golden-hour lighting with clean falloff
- Stylized environments that hold up as full illustration, not just portraits
Great for family-friendly character art, mascots, children's book illustration, 3D-style key art and animated-film concept frames. Add '3d render, pixar style, stylized cartoon, soft global illumination' for the strongest effect.
[Recommended settings] Sampler DPM++ 2M or Euler a, 28-32 steps, CFG 7, 832x1216 (1216x832 for wide shots). Danbooru-style tags work best. Use bf16 where possible - fp16 can soften output.
[License] CreativeML Open RAIL-M, inherited from the base models. Please credit the base models if you redistribute. Part of the merged-checkpoint series.

