FigureMix XL is a three-way anime checkpoint merge tuned to reproduce the look of collectible PVC figures and movable toy models: glossy plastic material, smooth sculpted surfaces, soft studio product lighting and clean display-stand compositions, while keeping the stable anatomy of the Illustrious ecosystem.

Recipe: 0.45 x [PVC Style Model] Movable figure model (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:

• Convincing 3D figure / figurine material and studio lighting from the PVC Style Model

• - Stable composition and strong prompt adherence from WAI-illustrious

• - A balanced, broadly compatible anime base from Illustrious-XL v1.0

Great for figure and toy style renders, collectible product shots, 3D-look character art and merchandise mockups. Add 'figurine, plastic material, studio product photo, soft studio lighting' for the strongest effect.

[Recommended settings] Sampler DPM++ 2M or Euler a, 28-32 steps, CFG 7, 832x1216. 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.