Anima Delta Mix — Furry Edition 3.8B Qwen 0.6B
One bake. No version ladder on this page.
Anima-3.8B chassis, historical 28+12+12. Nova on the floor, Bubba in Gen-1, Animurr in Gen-2.
Anime and illustration first. Ears, muzzles and fur are part of the stack, not a filter on top.
IMPORTANT. Read this first.
This checkpoint is not built for Qwen3.5-4B and not for the expanded adapter.
52-block DiT, text conditioning is native qwen_3_06b_base only.
Inserts after the 28-stem were prepared for that CLIP. Qwen3.5 will look like stock Pro52, not this mix.
Do not use qwen35_4b or Anima-3.8B-expanded_adapter.
Donors are 28-block 2B only. Do not feed 2.9 / 3.8 back into the node as a donor.
Delta Mix
Checkpoint merge on Anima-3.8B (52-block). Use it like a normal Anima model.
Text encoder: qwen_3_06b (native Anima CLIP).
VAE: official Anima / Qwen-Image VAE.
Prompt
Positive starter:
masterpiece, best quality, ultra detailed, absurdres, sharp focus, intricate details, cinematic dramatic lighting, strong chiaroscuro,
Then the scene in tags or natural language, Anima-style. Name the species early when you want it.
Rating tag if you use one (safe / sensitive / explicit).
Recommended
Steps: 30
CFG: 4.0–5.5
Sampler: Euler ancestral
Scheduler: normal
Resolution: same as Anima-3.8B (1024-class and up, as VRAM allows).
Anima 52 LoRA Patch
https://github.com/bestluner-create/ComfyUI-Anima-Delta-Q35-LoRA.git
Start around 0.65.
Credits
Anima Base / Anima-3.8B — original authors
Floor: Nova Furry AM v3.0
Gen-1: Bubba Furry Anima
Gen-2: aniMurr V2
Method: Anima Delta Mix — 2B into 2.9B / 3.8B
License follows Anima (non-commercial). Do not sell the weights.