ComfyUI Node
Z-Image img2img ⚡
Prompts, init latent and optional ControlNet for Z-Image. Leave image unconnected for txt2img. Feed the outputs straight into a stock KSampler.
Z-Image img2img ⚡
- model
- clip
- vae
- image
- control_patch
- control_image
- model
- positive
- negative
- latent
- denoise
◄prompt—►
◄negative_prompt►
◄strength0.60►
◄batch_size1►
◄width1024►
◄height1024►
◄control_strength0.70►
Category🤖 CCTech/Z-Image
Inputs (13)
| Name | Type | Default | Description |
|---|---|---|---|
| model | MODEL | — | |
| clip | CLIP | — | |
| vae | VAE | — | |
| prompt | STRING | — | |
| negative_prompt | STRING | — | |
| strength | FLOAT | 0.600–1 | img2img only. How much of the init image to discard. Ignored without an image. |
| batch_size | INT | 11–4096 | — |
| width | INT | 102416–16384 | Output size. With an init image this resizes it. |
| height | INT | 102416–16384 | — |
| imageopt | IMAGE | Init image for img2img. Leave unconnected for txt2img. | |
| control_patchopt | MODEL_PATCH | ModelPatchLoader with a Z-Image Fun ControlNet. | |
| control_imageopt | IMAGE | Control map, usually Canny. | |
| control_strengthopt | FLOAT | 0.70-10–10 | 1.0 over-conditions and softens detail; 0.7 keeps structure with detail. |
Outputs (5)
| Name | Type | Description |
|---|---|---|
| model | MODEL | — |
| positive | CONDITIONING | — |
| negative | CONDITIONING | — |
| latent | LATENT | — |
| denoise | FLOAT | — |