ComfyUI Node
Fat Mex Image Edit Sampler
All-in-one Qwen Image Edit sampler. Feed reference images + a prompt describing the edit. Handles vision-language encoding, layered latent creation, sampling, and decoding in one node.
Fat Mex Image Edit Sampler
- model
- clip
- vae
- image1
- image2
- image3
- images
- latent
◄prompt►
◄negative_promptugly, blurry, deformed, bad anatomy, low quality►
◄seed0►
◄preset_hintauto►
◄steps0►
◄cfg0.0►
◄sampler_nameauto►
◄schedulerauto►
◄width1024►
◄height1024►
◄layers3►
CategoryFat Mex
Inputs (17)
| Name | Type | Default | Description |
|---|---|---|---|
| model | MODEL | Model from Fat Mex Model Loader (Qwen Edit preset). | |
| clip | CLIP | CLIP from Fat Mex Model Loader. | |
| vae | VAE | VAE from Fat Mex Model Loader. | |
| prompt | STRING | Describe the edit. Reference images as 'image 1', 'image 2', etc. | |
| negative_prompt | STRING | ugly, blurry, deformed, bad anatomy, low quality | What to avoid. |
| seed | INT | 00–18446744073709550000 | — |
| image1opt | IMAGE | Reference image 1 (e.g. the face to use). | |
| image2opt | IMAGE | Reference image 2 (optional). | |
| image3opt | IMAGE | Reference image 3 (optional). | |
| preset_hintopt | COMBO | auto | 8 options: auto, Klein 9B, Klein 9B True, Qwen Image Edit 2509, Qwen Image Edit 2511, Qwen Image 2512, +2 |
| stepsopt | INT | 00–100 | Override steps (0 = preset). |
| cfgopt | FLOAT | 0.00–100 | — |
| sampler_nameopt | COMBO | auto | 45 options: auto, euler, euler_cfg_pp, euler_ancestral, euler_ancestral_cfg_pp, heun, +39 |
| scheduleropt | COMBO | auto | 10 options: auto, simple, sgm_uniform, karras, exponential, ddim_uniform, +4 |
| widthopt | INT | 102464–16384 | Output width. |
| heightopt | INT | 102464–16384 | Output height. |
| layersopt | INT | 30–16 | Qwen layered latent layers (usually = number of images). |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| images | IMAGE | — |
| latent | LATENT | — |