On the recordRead 12 Oct 202624 facts
modl
On the record
- Agent integrations
- The built-in MCP server connects to Claude Code, Cursor, or any MCP client locally or over SSH.modl.run · read 12 Oct 2026
- Cloud GPU
- Users can rent GPUs through Vast.ai using their own API key; Vast.ai bills for the rented instance until it is destroyed.modl.run · read 12 Oct 2026
- ComfyUI integration
- The documentation says `modl system link` can adopt recognized ComfyUI models into a shared store so both tools use the same files.modl.run · read 12 Oct 2026
- Creator
- The homepage says modl was built with Rust by Pedro and links to his personal site.modl.run · read 12 Oct 2026
- Data handling
- The maker describes its GPU pod flow as having no hosted middleman or cloud storage, with artifacts syncing to the local library over SSH.modl.run · read 12 Oct 2026
- Free and open source
- The maker describes modl as free and open source, and says local use is free forever.modl.run · read 12 Oct 2026
- GPU rental
- Users can rent GPUs through Vast.ai using their own API key, with outputs synced back to their local library over SSH.modl.run · read 12 Oct 2026
- Hardware requirements
- The maker's character LoRA guide calls for an NVIDIA GPU with 10+ GB VRAM and recommends 16–24 GB.modl.run · read 12 Oct 2026
- Image editing
- Yesmodl.run · read 19 Sep 2026
- Image generation
- The CLI generates images from text prompts and edits existing images with natural-language instructions.modl.run · read 12 Oct 2026
- Image tools
- It includes image generation, natural-language editing, LoRA training, upscaling, background removal, segmentation, and ControlNet preprocessing.modl.run · read 12 Oct 2026
- Installation
- The maker provides a shell installer and a Cargo install-from-source option.modl.run · read 12 Oct 2026
- License
- The project is free and open source and is licensed AGPL-3.0.modl.run · read 12 Oct 2026
- Local storage
- The docs say models are stored by SHA256 hash in ~/modl/store/.modl.run · read 12 Oct 2026
- LoRA training
- modl trains LoRAs on users’ images and handles dataset preparation, captioning, parameter selection, and training execution.modl.run · read 12 Oct 2026
- Models
- The maker’s model page lists support for models including FLUX, Z-Image, Qwen Image, and Stable Diffusion, with model dependencies resolved automatically.modl.run · read 12 Oct 2026
- Output formats
- PNGmodl.run · read 19 Sep 2026
- Purpose
- modl is a local-first toolkit for generating and editing images and training LoRAs from a CLI and web interface.modl.run · read 12 Oct 2026
