image-creation
Generate or refine images with Seedream (text-to-image + image-to-image).
Resources
3Install
npx skillscat add cklxx/elephant-ai/image-creation Install via the SkillsCat registry.
SKILL.md
image-creation
Generate images via Seedream.
Required Env
ARK_API_KEY(required)SEEDREAM_TEXT_ENDPOINT_ID(optional; fallback:SEEDREAM_TEXT_MODEL-> built-in default model)SEEDREAM_I2I_ENDPOINT_ID(required forrefine)
Constraints
- Backend minimum pixels:
1920*1920. Smaller inputs (for example1024x1024) are auto-upscaled. success=trueonly when the output file is actually written and non-empty.- Backend response must contain
b64_jsonorurl; otherwise the call fails. - Default output path is
/tmpunlessoutputis provided.
Usage
# Text to image
python3 skills/image-creation/run.py '{"action":"generate","prompt":"white cat in moonlight","style":"realistic"}'
# Image to image
python3 skills/image-creation/run.py '{"action":"refine","image_path":"/tmp/cat.png","prompt":"add starry sky background"}'Parameters
generate
| name | type | required | notes |
|---|---|---|---|
| prompt | string | yes | image description |
| style | string | no | style tag (default: realistic) |
| size | string | no | WIDTHxHEIGHT, default 1920x1920 |
| output | string | no | output file path (default /tmp/seedream_<ts>.png) |
refine
| name | type | required | notes |
|---|---|---|---|
| image_path | string | yes | input image path |
| prompt | string | yes | refinement instruction |
| output | string | no | output path (default /tmp/seedream_refined_<ts>.png) |
Install
npx skillscat add cklxx/elephant-ai/image-creation Install via the SkillsCat registry.