​
About OmniGen2

OmniGen2 is a powerful and efficient unified multimodal generation model with approximately 7B total parameters (3B text model + 4B image generation model). Unlike OmniGen v1, OmniGen2 adopts an innovative dual-path Transformer architecture with completely independent text autoregressive model and image diffusion model, achieving parameter decoupling and specialized optimization.

​
Model Highlights

  • Visual Understanding: Inherits the powerful image content interpretation and analysis capabilities of the Qwen-VL-2.5 foundation model
  • Text-to-Image Generation: Creates high-fidelity and aesthetically pleasing images from text prompts
  • Instruction-guided Image Editing: Performs complex, instruction-based image modifications, achieving state-of-the-art performance among open-source models
  • Contextual Generation: Versatile capabilities to process and flexibly combine diverse inputs (including people, reference objects, and scenes), producing novel and coherent visual outputs

​
Technical Features

  • Dual-path Architecture: Based on Qwen 2.5 VL (3B) text encoder + independent diffusion Transformer (4B)
  • Omni-RoPE Position Encoding: Supports multi-image spatial positioning and identity distinction
  • Parameter Decoupling Design: Avoids negative impact of text generation on image quality
  • Support for complex text understanding and image understanding
  • Controllable image generation and editing
  • Excellent detail preservation capabilities
  • Unified architecture supporting multiple image generation tasks
  • Text generation capability: Can generate clear text content within images

If you find missing nodes when loading the workflow file below, it may be due to the following situations:

  1. You are not using the latest Development (Nightly) version of ComfyUI.
  2. You are using the Stable (Release) version or Desktop version of ComfyUI (which does not include the latest feature updates).
  3. You are using the latest Commit version of ComfyUI, but some nodes failed to import during startup.

Please make sure you have successfully updated ComfyUI to the latest Development (Nightly) version. See: How to Update ComfyUI section to learn how to update ComfyUI.

​
OmniGen2 Model Download

Since this article involves different workflows, the corresponding model files and installation locations are as follows. The download information for model files is also included in the corresponding workflows:

Diffusion Models

VAE

Text Encoders

File save location:

📂 ComfyUI/
├── 📂 models/
│   ├── 📂 diffusion_models/
│   │   └── omnigen2_fp16.safetensors
│   ├── 📂 vae/
│   │   └── ae.safetensors
│   └── 📂 text_encoders/
│       └── qwen_2.5_vl_fp16.safetensors

​
ComfyUI OmniGen2 Text-to-Image Workflow

​
1. Download Workflow File

​
2. Complete Workflow Step by Step

Please follow the numbered steps in the image for step-by-step confirmation to ensure smooth operation of the corresponding workflow:

  1. Load Main Model: Ensure the Load Diffusion Model node loads omnigen2_fp16.safetensors
  2. Load Text Encoder: Ensure the Load CLIP node loads qwen_2.5_vl_fp16.safetensors
  3. Load VAE: Ensure the Load VAE node loads ae.safetensors
  4. Set Image Dimensions: Set the generated image dimensions in the EmptySD3LatentImage node (recommended 1024x1024)
  5. Input Prompts:
    • Input positive prompts in the first CLipTextEncode node (content you want to appear in the image)
    • Input negative prompts in the second CLipTextEncode node (content you don’t want to appear in the image)
  6. Start Generation: Click the Queue Prompt button, or use the shortcut Ctrl(cmd) + Enter to execute text-to-image generation
  7. View Results: After generation is complete, the corresponding images will be automatically saved to the ComfyUI/output/ directory, and you can also preview them in the SaveImage node

​
ComfyUI OmniGen2 Image Editing Workflow

OmniGen2 has rich image editing capabilities and supports adding text to images

​
1. Download Workflow File

Download the image below, which we will use as the input image.

​
2. Complete Workflow Step by Step

  1. Load Main Model: Ensure the Load Diffusion Model node loads omnigen2_fp16.safetensors
  2. Load Text Encoder: Ensure the Load CLIP node loads qwen_2.5_vl_fp16.safetensors
  3. Load VAE: Ensure the Load VAE node loads ae.safetensors
  4. Set Image Dimensions: Set the generated image dimensions in the EmptySD3LatentImage node (recommended 1024x1024)
  5. Input Prompts:
    • Input positive prompts in the first CLipTextEncode node (content you want to appear in the image)
    • Input negative prompts in the second CLipTextEncode node (content you don’t want to appear in the image)
  6. Start Generation: Click the Queue Prompt button, or use the shortcut Ctrl(cmd) + Enter to execute text-to-image generation
  7. View Results: After generation is complete, the corresponding images will be automatically saved to the ComfyUI/output/ directory, and you can also preview them in the SaveImage node

​
3. Additional Workflow Instructions

  • If you want to enable the second image input, you can use the shortcut Ctrl + B to enable the corresponding node inputs for nodes that are in pink/purple state in the workflow
  • If you want to customize dimensions, you can delete the Get image size node linked to the EmptySD3LatentImage node and input custom dimensions