Workflow for LongCat ImageRECOMMENDED SETTINGS20-50 steps<ul><li>Standard Max: 1024 x 1024</li><li>Widescreen (16:9): 1344 x 768</li><li>Portrait (9:16): 768 x 1344</li><li>Landscape (4:3): 1152 x 896</li></ul>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)<a target="_blank" rel="ugc" href="https://huggingface.co/stduhpf/LongCat-Image-Dev-gguf/blob/main/longcat_dev_bfl_format.safetensors">https://huggingface.co/stduhpf/LongCat-Image-Dev-gguf/blob/main/longcat_dev_bfl_format.safetensors</a> non-dev Model (12gb)<a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/LongCat-Image/tree/main/split_files/diffusion_models">https://huggingface.co/Comfy-Org/LongCat-Image/tree/main/split_files/diffusion_models</a>GGUF (2-12gb) requires unet loader node instead of load diffusion model node<a target="_blank" rel="ugc" href="https://huggingface.co/vantagewithai/LongCat-Image-GGUF/tree/main/comfy">https://huggingface.co/vantagewithai/LongCat-Image-GGUF/tree/main/comfy</a>Text Encoder<a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/blob/main/split_files/text_encoders/qwen_2.5_vl_7b_fp8_scaled.safetensors">https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/blob/main/split_files/text_encoders/qwen_2.5_vl_7b_fp8_scaled.safetensors</a>Vae<a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/z_image_turbo/blob/main/split_files/vae/ae.safetensors">https://huggingface.co/Comfy-Org/z_image_turbo/blob/main/split_files/vae/ae.safetensors</a>realesergan2x (upscale models folder)<a target="_blank" rel="ugc" href="https://huggingface.co/ai-forever/Real-ESRGAN/blob/main/RealESRGAN_x2.pth">https://huggingface.co/ai-forever/Real-ESRGAN/blob/main/RealESRGAN_x2.pth</a>

Files with SHA256: bdff0c1168d0610a2bc973d925a01b88d3d1b73f9eb0103c679af85de3f4c35e