flux-image

# AI Image Generator Generate images using Nano Banana 2 (Google DeepMind) or FLUX.2 max (Black Forest Labs) via the Replicate API. Runs a Python script that calls the API and saves images locally. ## Prerequisites The `REPLICATE_API_TOKEN` must be set in the workspace `.env` file (root directory). The script auto-loads it from `.env` using `python-dotenv` -- no manual export needed. If the token is missing or invalid, instruct the user to add it to `.env`: ``` # In the workspace root .env file: REPLICATE_API_TOKEN=r8_your_token_here ``` Get a token at: https://replicate.com/account/api-tokens **Security:** Never hardcode API tokens in skill files, scripts, or documentation. All secrets live in `.env` only. ## Workflow ### 1. Determine the prompt Either: - Use the image prompt from a preceding `/image-prompt` skill invocation - Use a prompt the user provides directly - Craft a prompt from context (article, post, etc.) using the image prompt guidelines ### 2. Run the generation script Run from the workspace root (the script path is root-relative). The image is a DATA artifact -- it must land in the DATA overlay, never the engine tree. `generate_image.py` writes `--output` literally relative to the current directory (the engine root after the `cd`), so a bare `outputs/...` would create a stray image inside the engine. Resolve the data outputs dir first and pass an absolute path: ```bash cd "$(git rev-parse --show-toplevel)" OUTPUTS_DIR="$(python3 -c "import sys; sy...