Loaded
Download
1 variant available
fp16 SafeTensor
equinoxmix_v1.safetensors
Half precision, best balance • 6.46 GB
Verified: 13 hours ago
440 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
460 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
(6)
Oct 17, 2026
v1.0 - initial release. Three-way weighted merge, UNet only.

190 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
1880 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
License:
Illustrious LicenseEquinoxMix XL is a three-way anime checkpoint merge built for cinematic semi-realistic results: natural detailed skin, believable lighting and atmospheric depth, with a film-like color grade - while keeping the stable anatomy of the Illustrious ecosystem.
Recipe: 0.45 x [BSS] Equinox (Semi-Realistic, 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:
Semi-realistic faces, skin and cinematic lighting from BSS Equinox
- Stable composition and strong prompt adherence from WAI-illustrious
- A balanced, broadly compatible anime base from Illustrious-XL v1.0
Great for cinematic character shots, moody portraits, film-still compositions and atmospheric scenes. Add 'semi realistic, cinematic lighting, detailed skin, depth of field' 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.


