Browser UI + optional LLM → ComfyUI Anima workflow automation. Point-and-click Danbooru prompt builder for anime image generation.
anima_pipeline is a local browser UI that connects to your ComfyUI Anima workflow and handles the tedious parts of anime-style image generation: looking up Danbooru tags, typing character details by hand, and rebuilding prompts from scratch every time.
GitHub (download here): https://tomotto1296.github.io/anima-pipeline/index_en.html
Full guide (Civitai Article): https://civarchive.com/articles/27575
What it does
Point-and-click prompt building — select hair style, hair color, eye color, expression, outfit, pose, and more via buttons. The Danbooru prompt is assembled automatically.
Optional LLM integration — type a character name (e.g. "Reimu Hakurei") and an LLM auto-generates the Danbooru tags. Supports LM Studio (local/free), Gemini free tier, or any OpenAI-compatible API. Works 100% offline without LLM too.
Multi-character — up to 6 characters simultaneously in separate blocks
LoRA injection — card grid with thumbnail preview, up to 4 slots, auto-fetches your ComfyUI LoRA list
Workflow switching — drop any API-format workflow JSON into
workflows/and select from dropdownCharacter presets — save/load configs with thumbnail gallery. Auto-generate from character name + Danbooru Wiki via LLM.
Session auto-save — picks up where you left off
Mobile support — use from phone/tablet on the same Wi-Fi
Requirements
ComfyUI 0.16.4+ with Anima workflow (grab from ComfyUI's Browse Templates)
Anima model files — download from Hugging Face: https://huggingface.co/circlestone-labs/Anima/tree/main/split_files
qwen_3_06b_base.safetensors→models/text_encoders/qwen_image_vae.safetensors→models/vae/anima-preview.safetensors→models/diffusion_models/
Python 3.10+
LLM optional (Gemini free tier recommended for beginners)
Quick start
Download ZIP from GitHub → extract
Get Anima workflow JSON from ComfyUI Browse Templates → Save (API Format) → place in
workflows/Double-click
start_anima_pipeline.bat(Windows) or runpython anima_pipeline.pyOpen
http://localhost:7860
Description
- Module split (core/ + frontend/) for maintainability
- Generation History DB + history re-edit workflow
- Preset hierarchy (chara/scene/camera/quality/lora/composite)
- Named session multi-save
- Anima2 workflow templates added
- LoRA search, favorites, recommended weight persistence
- Theme toggle (Light / Dark / Device)
- Today's Mood random generation flow
- Prompt diff viewer in history modal
- Preset bundle Export/Import (GET /presets_export, POST /presets_import)
- Mobile UI improvements
- ComfyUI Portable launcher support
Full changelog: https://github.com/tomotto1296/anima-pipeline/releases/tag/v1.5.20
v1.5.01 – 2026-03-23
Database-driven generation history + re-editing workflow based on history
Hierarchical presets (character / scene / camera / quality / LORA / composite)
Ability to save multiple named sessions
Setup self-diagnostic UI (/diagnostics)
Support for separate Japanese and English input for character and project names
Automatic configuration completion and stabilization at startup
v1.4.7 – 2026-03-20
Japanese/English UI toggle (OS language auto-detect)
Log system with API key masking + ZIP export
Character preset thumbnail gallery
Bug fixes and stability improvements
Full changelog: https://github.com/tomotto1296/anima-pipeline/releases/tag/v1.4.7