VisionForge
A Tauri 2 app that connects Ollama and ComfyUI through a local prompt-engineering, queue, gallery, and generation-receipt workflow.
Overview
VisionForge is a local image-generation workflow product. It connects local LLMs through Ollama with Stable Diffusion workflows through ComfyUI, turning a rough idea into refined prompts, queued generations, and a searchable gallery.
Architecture
The app is a Tauri 2 desktop system:
- Rust backend
- React/TypeScript frontend
- SQLite metadata store
- Ollama REST API for local LLM stages
- ComfyUI REST and WebSocket API for image generation
- prompt pipeline domain modules
- queue, gallery, AI tagging, configuration, and export modules
The current README describes a five-stage prompt pipeline: Ideator, Composer, Judge, Prompt Engineer, and Reviewer.
Product Surface
VisionForge includes a prompt studio, priority queue, gallery, A/B comparison, seed library, checkpoint knowledge, endpoint health checks, and ZIP export with metadata.
Next Gates
- Canonicalize generation receipts: prompt, model, workflow graph, seed, input refs, and output digest.
- Add reproducibility reports for ComfyUI workflows.
- Keep local model and GPU resource assumptions explicit.
Have questions about VisionForge?
Try asking the AI assistant! Here are some ideas:
Related Projects
Gloss
A local-first desktop knowledge application for grounded chat over personal documents, with notebook-local storage and source-linked answers.
Palisade
A native Linux firewall control surface for nftables with privilege separation, validation, snapshots, and rollback.
Sortarr
A Rust daemon and React UI for organizing self-hosted media libraries with metadata matching, dry-run planning, and review gates.