Workflow for LongCat Image

RECOMMENDED SETTINGS

20-50 steps

• Standard Max: 1024 x 1024

• Widescreen (16:9): 1344 x 768

• Portrait (9:16): 768 x 1344

• Landscape (4:3): 1152 x 896

Ive included realESERGAN2x to help boost resolution because the model natively generates at 1024x1024 (1mp). This brings the output to 2048x2048 (2mp). If you dont want it, just bypass or remove it.

Files:

Dev model (12gb)

https://huggingface.co/stduhpf/LongCat-Image-Dev-gguf/blob/main/longcat_dev_bfl_format.safetensors

non-dev Model (12gb)

https://huggingface.co/Comfy-Org/LongCat-Image/tree/main/split_files/diffusion_models

GGUF (2-12gb) requires unet loader node instead of load diffusion model node

https://huggingface.co/vantagewithai/LongCat-Image-GGUF/tree/main/comfy

Text Encoder

https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/blob/main/split_files/text_encoders/qwen_2.5_vl_7b_fp8_scaled.safetensors

Vae

https://huggingface.co/Comfy-Org/z_image_turbo/blob/main/split_files/vae/ae.safetensors

realesergan2x (upscale models folder)

https://huggingface.co/ai-forever/Real-ESRGAN/blob/main/RealESRGAN_x2.pth