<h1 id="anima-expanded-2.9b-base-and-aesthetic">Anima-Expanded 2.9B — BASE &amp; Aesthetic</h1>Layer-expanded Anima. 40 DiT blocks, 2.9B params, and it still runs on a completely normal Anima setup - native Qwen3-0.6B encoder, same VAE, no custom nodes. If you already have Anima working, this is a checkpoint swap.Trained on roughly 4.1M images, about 50/50 anime and furry.Two versions in this drop:BASE - the plain expanded model. Neutral, does what you prompt and nothing you didn't ask for. This is the one for stacking your own LoRAs, or for comparing against your usual Anima 2B.Aesthetic — tuned hard on lighting, color and backgrounds. Much stronger look straight out of the box, less neutral. Take this one if you want the model making some decisions for you.Same prompt, same seed, both checkpoints. Fastest way to see what changed.<h2 id="what-i-pushed-on">What I pushed on</h2><ul><li>Furry — species traits that actually read, fur/ears/tails, faces with expression</li><li>NSFW — anatomy and multi-character posing between adults</li><li>Backgrounds — full environments instead of blurred filler behind a character</li><li>Anime — color and expression, compositions that aren't just centered bust shots</li></ul>Backgrounds and furry moved the most in my own testing. Multi-character NSFW is still inconsistent — if you find prompts that land it, post them.<h2 id="comfyui">ComfyUI</h2>Needs a recent ComfyUI with Anima support. No custom nodes for either version.<pre><code>ComfyUI/models/diffusion_models/ BASE or Aesthetic (~5.8 GB, bf16)
ComfyUI/models/text_encoders/ qwen_3_06b_base.safetensors
ComfyUI/models/vae/ qwen_image_vae.safetensors</code></pre><ul><li>Load Diffusion Model → weight dtype <code>default</code></li><li>Load CLIP → type <code>stable_diffusion</code></li><li>Then the normal CLIP Text Encode → KSampler → VAE Decode</li></ul>Switching versions is just the diffusion checkpoint. Encoder and VAE stay put.<h2 id="recommended-settings">Recommended settings</h2><ul><li>Sampler: Euler a (<code>euler_ancestral</code>)</li><li>Scheduler: simple</li><li>Steps: 24</li><li>CFG: 4.0</li><li>Resolution: your usual Anima resolutions</li></ul><h2 id="notes">Notes</h2>Post your gens in the gallery - prompts and seeds if you can, Comments and bug reports welcome, I read them.If you get something good out of it, a review or a like helps more than you'd think.

Anima-Expanded [2.9B]

Aesthetic version was trained at multi res 1024x1024 1536x1536 on a custom high quality dataset.

Files with SHA256: e8ad1216174355221a1e9c191f53ceae22a718dfd88d0a5577d4ec9351b56c23