ComfyUI OmniGen2 Native Workflow Examples - Unified text-to-image, image editing, and multi-image composition model.
Load Diffusion Model
node loads omnigen2_fp16.safetensors
Load CLIP
node loads qwen_2.5_vl_fp16.safetensors
Load VAE
node loads ae.safetensors
EmptySD3LatentImage
node (recommended 1024x1024)CLipTextEncode
node (content you want to appear in the image)CLipTextEncode
node (content you don’t want to appear in the image)Queue Prompt
button, or use the shortcut Ctrl(cmd) + Enter
to execute text-to-image generationComfyUI/output/
directory, and you can also preview them in the SaveImage
nodeLoad Diffusion Model
node loads omnigen2_fp16.safetensors
Load CLIP
node loads qwen_2.5_vl_fp16.safetensors
Load VAE
node loads ae.safetensors
Load Image
nodeCLipTextEncode
node (content you want to appear in the image)CLipTextEncode
node (content you don’t want to appear in the image)Queue Prompt
button, or use the shortcut Ctrl(cmd) + Enter
to execute text-to-image generationComfyUI/output/
directory, and you can also preview them in the SaveImage
nodeGet image size
node linked to the EmptySD3LatentImage
node and input custom dimensions