What problem does it solve? Accessing dozens of AI models for image generation, video creation, TTS, and search normally requires managing separate provider APIs, credentials, and SDKs. This Skill consolidates access to 150+ cloud AI apps through a single CLI, eliminating per-provider integration work and the need for local GPUs. ## Core Features & Use Cases - App Discovery: Search the inference.sh catalog with infsh app list --search to find the correct app ID before running anything. - Media Generation: Run image models (FLUX, Seedream, Grok, Gemini), video models (Veo, Seedance, Wan), avatars (OmniHuman), and TTS with a single JSON input command. - Local File Uploads: Pass local file paths directly in the input JSON; the CLI uploads them automatically for tasks like upscaling, image-to-video, and lipsync. - Use Case: A user asks for a product mockup video. Search for video apps, run google/veo-3-1-fast with a prompt, and return the generated video URL for inline display. ## Quick Start Ask the assistant to generate an image of a sunset over mountains using inference.sh, and it will search for the right app and run it with JSON output.
