ComfyUI Node
Z-Image Turbo I2I (Replicate)
A ComfyUI node in Replicate Select/image with 10 inputs and 1 output.
Z-Image Turbo I2I (Replicate)
- image
- image
◄prompt►
◄strength0.60►
◄num_inference_steps8►
◄guidance_scale0.00►
◄seed0►
◄lora_weights►
◄lora_scales►
◄output_formatjpg►
◄output_quality80►
CategoryReplicate Select/image
Inputs (10)
| Name | Type | Default | Description |
|---|---|---|---|
| prompt | STRING | Text prompt for image generation | |
| image | IMAGE | Input image for img2img | |
| strengthopt | FLOAT | 0.600–1 | Strength of the img2img transformation. 0.0 is no change, 1.0 is full transformation |
| num_inference_stepsopt | INT | 81–50 | Number of inference steps. This actually results in (num_inference_steps - 1) DiT forwards |
| guidance_scaleopt | FLOAT | 0.000–20 | Guidance scale. Should be 0 for Turbo models |
| seedopt | INT | 0-2147483648–2147483647 | Random seed. Set for reproducible generation |
| lora_weightsopt | STRING | LoRA weights as an array of URLs. Supports .safetensors URLs, tar files, and zip files (e.g., ['https://example.com/lora1.safetensors', 'https://example.com/lora2.safetensors']) | |
| lora_scalesopt | STRING | Scales for each LoRA as an array of floats. Must match the number of lora_weights. Defaults to 1.0 for each if not provided. | |
| output_formatopt | COMBO | jpg | Format of the output images |
| output_qualityopt | INT | 800–100 | Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| image | IMAGE | — |