Rd Cn Txt2Img
rd_cn_txt2imgGenerate images from text prompts with ControlNet conditions (composition, depth, pose, sketch, tile) using reference images and optional palettes for structure-aware pixel art.
Instructions
ControlNet Text to Image.
controlnets: list of {model: Composition|Depth|Pose|Sketch|Tile, weight: 0-100, process: bool (preprocess input), enabled: bool}; control_images: parallel list of input PNG paths (None for disabled slots). Palette constraint via palette_files (PNG palettes) or palette_url. Uses explicit steps (no quality).
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"prompt": "<prompt>",
"controlnets": "<controlnets>",
"control_images": "<control_images>"
},
"name": "rd_cn_txt2img"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| seed | No | ||
| swap | No | ||
| loras | No | ||
| model | No | model.pxlm | |
| rembg | No | ||
| steps | No | ||
| width | No | ||
| height | No | ||
| prompt | Yes | ||
| light_x | No | ||
| light_y | No | ||
| light_z | No | ||
| comp_hue | No | ||
| negative | No | ||
| pixelvae | No | ||
| use_ella | No | ||
| adherence | No | ||
| cfg_scale | No | ||
| comp_tint | No | ||
| save_grid | No | ||
| pixel_size | No | ||
| controlnets | Yes | ||
| generations | No | ||
| light_apply | No | ||
| palette_url | No | ||
| size_preset | No | ||
| comp_outline | No | ||
| post_process | No | ||
| return_image | No | ||
| add_to_prompt | No | ||
| comp_contrast | No | ||
| palette_files | No | ||
| prompt_tuning | No | ||
| save_progress | No | ||
| control_images | Yes | ||
| comp_brightness | No | ||
| comp_saturation | No |