ComfyUI Node
Z-Image Integrated KSampler
Z-Image Integrated KSampler - All-in-one generation with LLM prompt enhancement, sampling, AuraFlow, CFGNorm, and auto-save.
Z-Image Integrated KSampler
- model
- clip
- vae
- config
- options
- image_1
- image_2
- image_3
- image_4
- latent
- images
- latent
- enhanced_prompt
- debug_log
◄positive_prompt►
◄negative_prompt►
◄generation_modetext_to_image►
◄width1024►
◄height1024►
◄seed0►
◄steps20►
◄cfg7.0►
◄sampler_nameeuler►
◄schedulernormal►
◄denoise1.00►
◄prompt_templatechinese►
◄enable_prompt_enhancetrue►
◄batch_size1►
◄auraflow_shift0.00►
◄cfg_norm_strength0.00►
◄enable_clean_gpufalse►
◄enable_clean_ramfalse►
◄auto_save_folder►
◄output_prefixz_image►
◄custom_system_prompt►
◄instructionDescribe the key features of the input image (color, shape, size, texture, objects, background), then explain how the user's text instruction should alter or modify the image. Generate a new image that meets the user's requirements while maintaining consistency with the original input where appropriate.►
CategoryZ-Image
Inputs (32)
| Name | Type | Default | Description |
|---|---|---|---|
| model | MODEL | Diffusion model for image generation | |
| clip | CLIP | CLIP model for text encoding | |
| vae | VAE | VAE model for latent encode/decode | |
| config | ZIMAGE_CONFIG | LLM configuration for prompt enhancement | |
| positive_prompt | STRING | Positive prompt - will be enhanced by LLM | |
| negative_prompt | STRING | Negative prompt for unwanted elements | |
| generation_mode | COMBO | text_to_image | T2I: Generate from text. I2I: Edit/transform input images |
| width | INT | 102464–8192 | Output image width |
| height | INT | 102464–8192 | Output image height |
| seed | INT | 00–18446744073709550000 | Random seed |
| steps | INT | 201–1000 | Sampling steps |
| cfg | FLOAT | 7.00–100 | CFG scale |
| sampler_name | COMBO | euler | Sampler algorithm |
| scheduler | COMBO | normal | Scheduler type |
| denoise | FLOAT | 1.000–1 | Denoise strength (1.0 = full, <1.0 for I2I) |
| optionsopt | ZIMAGE_OPTIONS | Advanced LLM options | |
| image_1opt | IMAGE | First image for I2I/vision enhancement | |
| image_2opt | IMAGE | Second image (optional) | |
| image_3opt | IMAGE | Third image (optional) | |
| image_4opt | IMAGE | Fourth image (optional) | |
| latentopt | LATENT | Optional latent input (for custom latent) | |
| prompt_templateopt | COMBO | chinese | LLM prompt template language |
| enable_prompt_enhanceopt | BOOLEAN | true | Enable LLM prompt enhancement (disable to use prompt as-is) |
| batch_sizeopt | INT | 11–16 | Number of images to generate |
| auraflow_shiftopt | FLOAT | 0.000–100 | AuraFlow shift (0 = disabled) |
| cfg_norm_strengthopt | FLOAT | 0.000–10 | CFGNorm strength (0 = disabled) |
| enable_clean_gpuopt | BOOLEAN | false | Clean GPU memory before/after sampling |
| enable_clean_ramopt | BOOLEAN | false | Clean RAM after completion |
| auto_save_folderopt | STRING | Auto-save folder (empty = disabled) | |
| output_prefixopt | STRING | z_image | Filename prefix for auto-save |
| custom_system_promptopt | STRING | — | |
| instructionopt | STRING | Describe the key features of the input image (color, shape, size, texture, objects, background), then explain how the user's text instruction should alter or modify the image. Generate a new image that meets the user's requirements while maintaining consistency with the original input where appropriate. | System instruction for the Vision-Language Model in I2I mode |
Outputs (4)
| Name | Type | Description |
|---|---|---|
| images | IMAGE | — |
| latent | LATENT | — |
| enhanced_prompt | STRING | — |
| debug_log | STRING | — |