luma-imagegen

原文涵盖的主题

• Luma Image Generation Skill
• When to use
• Workflow
• API key detection & setup
• Interactive questions to ask the user
• Running the CLI
• Output conventions
• Prompt augmentation

Generates images using the Luma AI Photon model (Dream Machine API). Handles API key detection, interactive prompt collection, parameter selection, async polling, and final image download — all via the bundled scripts/lumaimagegen.py CLI. Generate a new image from a text description using Luma AI (Photon / Photon Flash) Use a reference image to guide style, structure, or character consistency Modify or stylize an existing image using Luma's modifyimageref 1. Check API key — detect LUMAAPIKEY in environment. If missing, guide the user (see below). 2. Collect inputs — ask the user for: prompt, aspect ratio, model choice, and any optional reference images. 3. Build the structured prompt — augment the user's description into a labeled spec (see prompt template below). 4. Run the bundled CLI — execute scripts/lumaimagegen.py with the collected parameters. 5. Poll until complete — the script handles async polling automatically; wait for state: completed. 6. Display result — show the final image URL and download the image to output/luma/. 7. Iterate — if the result doesn't match expectations, adjust the prompt and re-run. Before any API call, check for the key: If LUMAAPIKEY is missing: 1

这里只展示节选，请以完整原文和当前要求为准。