SDXL Image-to-Image
Generate SDXL image variations from a source image using prompt guidance and denoise strength
Workflow id: sdxl_img2img · Image → Image
Calling it
POST /api/image/generate
{
"workflow": "sdxl_img2img",
"prompt": "...",
"image": "...",
"checkpoint": "..."
}Params
Every input this workflow takes. Your install is the source of truth:GET /api/workflows/sdxl_img2img returns these as they are on your machine.
prompt· string · required
Comma-separated tags describing the image you want out, not the change you want made — this is a re-render of the source at `denoise` strength, not an instruction-following edit. 'restyled as an oil painting' works because it is a description of the result; 'make the sky darker' does not, because nothing here reads commands. For an edit you can phrase as an instruction, use flux2_klein_edit or qwen_pose_edit instead. Same tag syntax as sdxl_base: subject first, `(term:1.2)` to weight a term. Keep the prompt consistent with what is already in the frame — at the 0.25-0.45 denoise this workflow is built for, a prompt that contradicts the source fights it and smears.image· string · required
Source image filename or Studio output pathcheckpoint· string · required
SDXL checkpoint model filenamenegative_prompt· string · optional
What to steer away from, same tag syntax. Keep it to defects you actually see — 'blurry, low quality, watermark'.width· integer · default832height· integer · default1216seed· integer · optional
Optional. Leave it out and every run is a new random take. Send a seed only to remake an image exactly: the seed a job used is in its record.steps· integer · default28cfg· float · default7sampler· string · defaultdpmpp_2mscheduler· string · defaultkarrasdenoise· float · default0.35
Lower preserves the source image more; 0.25-0.45 is good for identity-preserving variations