Skip to main content
Back to projects
activeMay 19, 2026

VisionForge

A Tauri 2 app that connects Ollama and ComfyUI through a local prompt-engineering, queue, gallery, and generation-receipt workflow.

rusttaurireacttypescriptsqliteollamacomfyuiimage-generation
GitHub

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