Generates AI images using the BlockEden OpenAI proxy (DALL-E 3 / DALL-E 2 / gpt-image-1). Use this skill whenever the user wants to generate, create, draw, make, or produce an image, picture, photo, illustration, artwork, or visual — even if they don't say "DALL-E" or "BlockEden". Trigger on phrases like "generate an image of", "create a picture of", "make me an illustration", "draw a scene", "visualize this", "I want an image", or "generate based on this image/URL". Requires the BLOCKEDEN_ACCESS_KEY environment variable to be set.
You are helping the user generate an AI image using the BlockEden OpenAI proxy, which is fully compatible with the OpenAI Images API (DALL-E 3 / DALL-E 2 / gpt-image-1).
The BLOCKEDEN_ACCESS_KEY environment variable must be set. If it's missing, tell the user:
Please set the
BLOCKEDEN_ACCESS_KEYenvironment variable before using this skill.
Use the bundled script at scripts/generate_image.py (relative to this SKILL.md):
python <skill_dir>/scripts/generate_image.py "<prompt>" [options]
| Flag | Default | Choices |
|---|
| Notes |
|---|
--reference-image | None | any URI | Reference image URL to base generation on. Uses gpt-image-1 via /v1/responses. |
--size | 1024x1024 | 1024x1024, 1792x1024, 1024x1792 | Landscape: 1792x1024, Portrait: 1024x1792 |
--quality | standard | standard, hd | hd gives finer detail, costs more (text-only mode only) |
--model | dall-e-3 | dall-e-3, dall-e-2 | Model for text-only generation. Ignored when --reference-image is set. |
--style | vivid | vivid, natural | DALL-E 3 only. vivid = dramatic, natural = realistic |
--output-dir | . | any path | Directory where the PNG will be saved |
python /path/to/skill/scripts/generate_image.py \
"a cozy coffee shop on a rainy day, impressionist painting style" \
--size 1792x1024 \
--quality hd \
--style natural \
--output-dir ~/Desktop
python /path/to/skill/scripts/generate_image.py \
"same composition but set at night with neon lights" \
--reference-image "https://example.com/my-photo.jpg" \
--output-dir ~/Desktop
{
"filepath": "/path/to/image_1234567890.png",
"revised_prompt": "...",
"model": "dall-e-3",
"size": "1024x1024",
"quality": "standard",
"style": "vivid"
}
{
"filepath": "/path/to/image_1234567890.png",
"model": "gpt-image-1",
"reference_image": "https://example.com/my-photo.jpg",
"prompt": "same composition but set at night with neon lights"
}
Once the image is saved:
revised_prompt if DALL-E rewrote it — this helps the user refine future prompts.--reference-image. The model switches automatically to gpt-image-1.--size.--quality hd (text-only mode only).--style natural.--style vivid (the default).--output-dir.Good image prompts are specific and visual. If the user's request is vague, enhance it slightly: