ComfyUI Node
Fat Mex Model Loader
All-in-one model loader. Pick a preset to load the correct UNET, CLIP, and VAE. Optionally stack up to 2 LoRAs. Supports all Fat Mex model families: Klein 9B, Qwen Image Edit, Z-Image Turbo, Chroma HD, etc.
Fat Mex Model Loader
- model
- clip
- vae
◄presetKlein 9B►
◄sage_attentiontrue►
◄lora_1none►
◄lora_1_strength1.00►
◄lora_2none►
◄lora_2_strength1.00►
◄weight_dtype_overridedefault►
CategoryFat Mex
Inputs (7)
| Name | Type | Default | Description |
|---|---|---|---|
| preset | COMBO | Klein 9B | Model preset to load. Each preset defines the UNET, CLIP, VAE, and default sampling settings. |
| sage_attentionopt | BOOLEAN | true | Enable sage attention for faster inference (requires sageattention package). |
| lora_1opt | COMBO | none | First LoRA to apply to the model. |
| lora_1_strengthopt | FLOAT | 1.00-10–10 | Strength of the first LoRA. |
| lora_2opt | COMBO | none | Second LoRA to apply to the model. |
| lora_2_strengthopt | FLOAT | 1.00-10–10 | Strength of the second LoRA. |
| weight_dtype_overrideopt | COMBO | default | Override weight data type. 'default' uses the preset's setting. |
Outputs (3)
| Name | Type | Description |
|---|---|---|
| model | MODEL | The loaded diffusion model. |
| clip | CLIP | The CLIP text encoder. |
| vae | VAE | The VAE for encoding/decoding images. |