SnapRef v2a gives the Anima image model a character from one or more reference photos, with a weight for each photo, in ComfyUI
SnapRef is a reference adapter for the Anima anime image model: you give it one or more pictures of a character and the prompt only describes the scene, while hair, eyes and outfit come from the reference. The stable v2a release of 8 November 2026 adds a weight for each reference, two modes and six ComfyUI workflows.
What it does
Each reference photo gets its own weight (1.0 by default, 0 switches it off), so a second view at 0.4 nudges the look instead of taking it over. Character & Style mode carries the reference's rendering over, while Character mode takes only the character so your artist tags and style words decide the look; the simple workflow runs 28 Euler steps at CFG 4.5 and 832x1216.
Worth knowing
The weights follow Anima's CircleStone Labs non-commercial licence (the node code is Apache-2.0). You must load the file with the SnapRef node, not a plain LoraLoader, because it holds two LoRA branches; an FP8 version is 195 MB instead of 382 MB and can give slightly different images. On the authors' own 64-case test, v2a scores level with v1a; the new weights are what changes.