What problem does it solve? Creating AI-generated media requires knowing which model fits each task, what parameters each endpoint accepts, and how to control cost and reproducibility. This Skill consolidates image, video, and audio generation through the fal.ai MCP server into one guided workflow. ## Core Features & Use Cases - Image Generation: Text-to-image and image editing with Nano Banana 2 for fast drafts and Nano Banana Pro for high-fidelity output, with control over aspect ratio, seed, and guidance scale. - Video Generation: Text-to-video and image-to-video via Seedance 1.0 Pro, Kling Video v3 Pro, and Veo 3, including duration and aspect ratio parameters. - Audio Generation: Conversational text-to-speech with CSM-1B, video-to-audio with ThinkSound, plus ElevenLabs API and VideoDB options for voice, music, and sound effects. - Use Case: A content creator needs a thumbnail, a short promo clip, and a voiceover. They iterate on the thumbnail with Nano Banana 2, generate the clip from the final image with Seedance, and produce narration with CSM-1B, checking estimate_cost before each expensive run. ## Quick Start Configure the fal.ai MCP server with your FAL_KEY, then ask the assistant to generate an image of a specific scene using the fal-ai nano-banana-2 model.