AllImageAI

OmniGen2 AI Image Generator and Editor

Open multimodal generation for text-to-image, instruction editing and combining up to three references.

Developed by VectorSpaceLabActiveVerified August 25, 2026

Model Version

Mode

Reference Images0/3

Preview mode: placeholder output, no credits charged

Output

OmniGen2

Open multimodal generation for text-to-image, instruction editing and combining up to three references.

SlowUp to 1KRefs ×31:116:99:164:3

Try one of these prompts

Developer
VectorSpaceLab
Model
OmniGen2
Status
Active
Max Output
1K
Input
Text + Images
Released
June 16, 2025
Last Verified
August 25, 2026

What Is OmniGen2?

OmniGen2 is VectorSpaceLab’s open unified generator. It can create from text, follow an edit instruction or combine people, objects and scenes from as many as three ordered images through one exact endpoint.

What Is OmniGen2 Best For?

  • In-context generation
  • Combining people and objects
  • Instruction-guided editing
  • Open-model workflows

How to Use OmniGen2

  1. Upload up to three references.
  2. Number every image in the prompt.
  3. Balance text and reference guidance.
  4. Generate one output before increasing the batch.

OmniGen2 Settings Explained

Reference Guidance

Use 1.3–2.0 for editing and 2.0–3.0 for stronger in-context reference following.

Text Guidance

Higher values prioritise the written instruction over variation.

The panel above shows only the parameters OmniGen2 actually supports. Switch versions and unsupported controls disappear rather than sitting there doing nothing.

OmniGen2 Prompt Examples

Multi-reference

Put the bird from image 1 on the desk in image 2, use the room lighting from image 3, preserve the bird markings

Edit

Keep the person and pose unchanged; make the dress cobalt blue with a matte silk texture

OmniGen2 Test Results

Testing in progress

Every model runs the same eight-category prompt set — portrait, product, poster text, anime character, interior, multi-reference, image editing and character consistency — recording generation time, success rate, text accuracy and identity retention. That run has not finished for OmniGen2, so this page shows no scores. We do not publish numbers we have not measured.

OmniGen2 Limitations

  • 1K output
  • Slower 50-step default
  • Reference-heavy prompts must identify every image by number

OmniGen2 Pricing and Credits

Credits scale with resolution and image count. The Generate button always shows what this run costs.

1K

7 credits / image

Failed generations cost 0 credits.

Commercial Use and Image Rights

Commercial use is subject to the OmniGen2 model licence and the selected service terms.

  • Model used: OmniGen2
  • Model developer: VectorSpaceLab
  • The inference route is managed internally and may change without changing the selected model
  • Uploads are sent only to the configured inference service needed to complete the generation
  • You can delete any generation from your history at any time

Frequently Asked Questions

Does it need a separate edit endpoint?+

No. The same OmniGen2 operation accepts zero to three input images.

Why does it cost more than draft models?+

The verified route bills per output megapixel at a materially higher rate.

Model Updates and Changelog

  • 2026-08-25 —— Added exact text, edit and three-reference request mappings.