Wiseflow siliconflow-img-gen
Generate images via SiliconFlow Images API. Default model is Qwen/Qwen-Image-Edit-2509. Supports text-to-image.
install
source · Clone the upstream repo
git clone https://github.com/TeamWiseFlow/wiseflow
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/TeamWiseFlow/wiseflow "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/siliconflow-img-gen" ~/.claude/skills/teamwiseflow-wiseflow-siliconflow-img-gen && rm -rf "$T"
manifest:
skills/siliconflow-img-gen/SKILL.mdsource content
SiliconFlow Image Gen
Generate images using the SiliconFlow Images API.
Run
Note: Image generation can take 10–60 seconds. Set a higher timeout when invoking via exec (e.g.,
exec timeout=120).
python3 {baseDir}/scripts/gen.py --prompt "your prompt here"
Useful flags:
# Default model (Qwen/Qwen-Image-Edit-2509), square output python3 {baseDir}/scripts/gen.py --prompt "a futuristic city at dusk" # Portrait / landscape sizes python3 {baseDir}/scripts/gen.py --prompt "mountain lake" --image-size 720x1280 python3 {baseDir}/scripts/gen.py --prompt "mountain lake" --image-size 1280x720 # Use Kolors model (supports guidance/batch) python3 {baseDir}/scripts/gen.py --prompt "flower field" --model "Kwai-Kolors/Kolors" --batch-size 3 # Save to specific directory python3 {baseDir}/scripts/gen.py --prompt "sunset" --out-dir ./out/images
Parameters
| Flag | Default | Description |
|---|---|---|
| required | Text description for the image |
| | Model ID |
| | Resolution: , , , , |
| | Number of images (1–4, Kolors only) |
| | Inference steps (1–100) |
| — | Guidance scale (Kolors only) |
| — | What to avoid in the image |
| — | Random seed for reproducibility |
| | Output directory |
Output
images named by index*.png
mapping index → prompt + URLprompts.json
thumbnail galleryindex.html
Environment Variables
| Variable | Description |
|---|---|
| Your SiliconFlow API key (required) |