README.md

metadata

title: Anima Collection
emoji: 📚
colorFrom: red
colorTo: red
sdk: gradio
sdk_version: 6.23.1
python_version: '3.12'
app_file: app.py
pinned: false

Anima Collection

Anima 2B anime text-to-image (Gradio + ComfyUI backend, no custom nodes, ZeroGPU).

Models

File	Source
6 Anima checkpoints (2B + 2.9B bf16 UNets)	circlestone-labs/Anima, Gazingstars123/Anima-2.9B, oai/civitai-collections
3 LoRAs (age_slider, real_skin, wlop-2)	oai/civitai-collections lora/anima/
qwen_3_06b_base.safetensors (text encoder)	circlestone-labs/Anima
qwen_image_vae.safetensors (VAE)	circlestone-labs/Anima

Checkpoints: anima-base-v1.0.safetensors (official base, default), Anima-2.9B-preview-v1.safetensors (40-block layer-expanded finetune), hs-anima-2.0.safetensors, MiaoMiao RealSkin _Anima_v1.1zs_net.safetensors, MiaoMiao_Anima_lh3d_1.0_n.safetensors, One obsession_ anima3D_v1.0.safetensors.

Setup

1. Create a Space with Gradio SDK, hardware ZeroGPU, size large.
2. First cold start downloads ~18 GB and clones ComfyUI; resumes are fast.
3. Optional: HF_TOKEN secret if any repo becomes gated (none are today).
4. Optional: GPU_DURATION env var (default 30s) to tune the ZeroGPU window.

Workflow: image_anima_base_v1.json.

Prompting (from the official Anima README)

• Defaults: 30 steps, CFG 4, er_sde / simple.
• Recommended positive prefix: masterpiece, best quality, score_7, safe,
• Recommended negative: worst quality, low quality, score_1, score_2, score_3, artist name, blurry, jpeg artifacts, chromatic aberration
• Use lowercase Danbooru-style tags, spaces instead of underscores; score tags keep underscores; prefix artist tags with @.