higgsfield-youtube-thumbnaillisted

# Higgsfield YouTube Thumbnail Create a clean thumbnail concept, generate each variant through the `higgsfield` CLI, inspect it, and make only requested surgical edits. ## Bootstrap Before any generation: 1. If `higgsfield` is missing, install it: ```bash curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh | sh ``` 2. If `higgsfield account status` reports `Session expired` or `Not authenticated`, ask the user to run `higgsfield auth login`, then wait. 3. Confirm the locked model contracts when the catalog may have changed: ```bash higgsfield model get nano_banana_pro --json higgsfield model get gpt_image_2 --json higgsfield model get seedream_v5_pro --json ``` ## UX rules 1. Match the user's language. Keep CLI/model mechanics out of normal chat. 2. Do not ask for facts already present in the brief. Ask one compact question only when a missing choice changes the result. 3. Never invent claims, outcomes, products, people, screenshots, or statistics that are not true of the video. 4. Do not print raw JSON or job IDs to the user. Deliver the image URL and a short variant label. 5. A style-reference thumbnail is for visual analysis only. Never pass it with `--image`; copying its identity or exact composition is forbidden. 6. Do not use `--count`. Every concept, emotion, or camera take gets its own prompt and generation call. 7. `use_unlim` is not a current CLI parameter. Never add `--use-unlim`; if the user explicitly asks