How to run Show-o2-7B locally

Show Lab (NUS) · Unified understanding + image/video gen · 7B params · Apache-2.0 (commercial OK)

A native unified model combining autoregressive text prediction with flow-matching over a 3D causal VAE space, so one transformer understands and generates across text, image and video. A 1.5B variant is also released.

What it costs to run — $0 markup

On your own machine — $0. Runs free if you have about 18 GB of VRAM (~14-18GB in BF16 for the 7B model; the 1.5B variant runs comfortably under 8GB for lighter setups.), via Diffusers / Transformers.
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 showlab/show-o2-7B.

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, Text → video, Visual understanding, Video understanding, Mixed modal generation
VRAM to run	~18 GB (~14-18GB in BF16 for the 7B model; the 1.5B variant runs comfortably under 8GB for lighter setups.)
Download	~16 GB
Parameters	7B
License	Apache-2.0 (commercial use OK)
Run with	Diffusers / Transformers

Get Show-o2-7B 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