OmniGen AI
Transform your images with OmniGen AI
Your generated image will appear here
OmniGen AI Examples
Enter your prompt, use <img><|image_i|></img> to represent i-th input image | <img><|image_1|></img> | <img><|image_2|></img> | Result |
---|---|---|---|
A man and a short-haired woman with a wrinkled face are standing in front of a bookshelf in a library. The man is the man in the middle of <img><|image_1|></img>, and the woman is oldest woman in <img><|image_2|></img> | ![]() | ![]() | ![]() |
Detect the skeleton of human in this image: <img><|image_1|></img>. | ![]() | ![]() | ![]() |
Two woman are raising fried chicken legs in a bar. A woman is <img><|image_1|></img>. Another woman is <img><|image_2|></img>. | ![]() | ![]() | ![]() |
Enter your prompt, use <img><|image_i|></img> to represent i-th input image: A man and a short-haired woman with a wrinkled face are standing in front of a bookshelf in a library. The man is the man in the middle of <img><|image_1|></img>, and the woman is oldest woman in <img><|image_2|></img>
Result

Enter your prompt, use <img><|image_i|></img> to represent i-th input image: Detect the skeleton of human in this image: <img><|image_1|></img>.
Result

Enter your prompt, use <img><|image_i|></img> to represent i-th input image: Two woman are raising fried chicken legs in a bar. A woman is <img><|image_1|></img>. Another woman is <img><|image_2|></img>.
Result

Frequently Asked Questions
Get answers to common questions about OmniGen AI, contact us at [email protected] for more help.
How do I use OmniGen?
To use OmniGen, simply upload your reference image(s) and write a descriptive prompt. For example: 'A woman holds a bouquet of flowers and faces the camera. The woman is <img><|image_1|></img>.' The system will process your inputs and generate a new image based on your specifications.
How to write effective prompts?
For best results, use detailed descriptions in your prompts. For image editing tasks, place the image before the editing instruction (e.g., '<img><|image_1|></img> remove suit'). If generated images appear in anime style, try adding 'photo' to your prompt. Provide clear information about subject, scene, and style.
What image formats are supported?
OmniGen supports common image formats including JPG, JPEG, PNG and WebP. Please ensure your uploaded images are in the correct format for proper processing.
How long does image generation take?
Image generation typically takes 30-60 seconds, depending on image complexity, server load, number and size of input images, and whether the offload_model option is enabled.
What is the maximum image size supported?
Images uploaded to OmniGen must be smaller than 5MB in file size. If your image exceeds this limit, please compress or resize it before uploading.
What's the difference between OmniGen Pro and free version?
OmniGen Pro offers faster image generation, higher quality results, enhanced editing capabilities, better multimodal understanding, and optimized resource utilization compared to the standard version.