fal

Point Claude at any game. Skills, tools and the fal MCP that let Claude Code mod almost any PC game you own: recon, reverse engineering, fal-generated art/3D/audio, in-game testing, showcase videos.

Production-ready ComfyUI custom nodes for 1,400+ fal.ai models, auto-updated image, video, audio, LLM and VLM APIs with native media, caching and cost controls.

A voice-driven 3D character in the browser. The model that talks is not the model that moves: GPT-Live-1 talks, Jev moves her, three.js + VRM render her, a thin broker runs on fal.

One sentence -> a rigged, animated voxel creature or RPG character. Claude Code skills + tools: fal Seedream/Hunyuan-3D -> voxelizer -> headless Blender (derived rig, procedural gaits or CC0 retarget) -> glTF

Community fork of rehan-remade/universal-modder with the built-in agent guardrail text removed. Same skills, tools and knowledge base; no guardrail layer.

The open-source, self-hosted unified API for generative media. One webhook-native endpoint across Fal, Replicate, and more — bring your own keys, get persistent jobs and automatic provider failover for free.

Engine to run the Fantasy Anime League

Example of using the dbt-cloud-action to run with fal run in GH Actions

OpenClaw skill for Fal.ai generative media API - image, video, and audio generation with FLUX, SDXL, Whisper, and 600+ models.

AI-powered CLI tool that generates engaging podcast-style conversations with realistic text-to-speech capabilities

Cursor Agent Skills for preparing portrait LoRA datasets and training them with fal-ai/flux-lora-portrait-trainer

A complete fruit fly connectome (164,587 neurons) running as a spiking network, seeing and steering through a world an AI imagines in real time.

PhotoCleanser-i2i is an adapter for black-forest-lab's FLUX.1-Kontext-dev. It is an experimental LoRA designed for removing specified object(s) while preserving the remaining content in the image.

Automate LoRA model training with a guided pipeline for curation, tagging, and validation compatible with Claude Code and other agentic workflows.

Turn any script or topic into a finished narrated video (Shorts, Reels, TikTok, YouTube) at a quoted low cost. Claude skill + plugin.

Open, reproducible benchmark for image-to-video generation models, run on fal.ai

See what a model provider adds to your prompt before you pay — per-endpoint rewrites, expansions, canned negative prompts and safety screens, with the switch that turns each one off. 20 hosted image, video and chat endpoints, every claim sourced.

Cataloged, reviewable, game-ready 3D asset generation with fal and TRELLIS.2

Automated AI car-edit Shorts: one seed → AI generation (fal.ai) → quality-control → beat-synced 9:16 render → optional YouTube auto-publish. Python + ffmpeg.

Upscale generative-model output to print-ready resolution, with a DPI check before you commit to a print