How to run OmniGen v1 locally

BAAI · Unified image gen + edit · 3.88B params · MIT (commercial OK)

A single 3.88B unified image-generation transformer that handles text-to-image, editing, subject-driven and identity-preserving generation from multimodal prompts with no extra plugins or ControlNets.

What it costs to run — $0 markup

On your own machine — $0. Runs free if you have about 12 GB of VRAM (~12-16GB to run the 3.88B unified transformer at 1024px; lower-VRAM cards work with offload and smaller resolutions.), via Diffusers.
Rent a GPU — from $0.26/hr. Fits RTX 3090 24GB at the direct vendor price ($0 markup) — pay only for the minutes you generate.
Download the weights — free. Open weights at Shitao/OmniGen-v1.

Note: generative-media models are billed per image / per second / per minute on hosted services — not per token. Running locally or on your own rented GPU is usually far cheaper and keeps your data on your machine.

Key facts

Does	Text → image, Image editing, Subject driven generation, Identity preserving generation, Image conditioned generation
VRAM to run	~12 GB (~12-16GB to run the 3.88B unified transformer at 1024px; lower-VRAM cards work with offload and smaller resolutions.)
Download	~16 GB
Parameters	3.88B
License	MIT (commercial use OK)
Run with	Diffusers

Get OmniGen v1 on Hugging Face →

More multimodal / omni models

Qwen2.5-Omni-7B — Omni understanding + speech generation, ~24 GB VRAM
Janus-Pro-7B — Unified understanding + image gen, ~16 GB VRAM
OmniGen2 — Any to image (gen + edit + in context), ~17 GB VRAM
MiniCPM-o 2.6 — Omni understanding + speech generation, ~9.0 GB VRAM
BAGEL-7B-MoT — Unified understanding + image gen + edit, ~24 GB VRAM
Emu3.5 — Any to any world model (gen + edit), ~48 GB VRAM

Browse: all media models · chat / LLM models