Qwen-Image 2.1 local test: transparency, text and infographics at 30.8GB
DevDminGod · x · 2026-09-20
Hands-on with Qwen-Image 2.1 running locally: pretty images, transparency support, coherent text rendering, dense infographics (though below NBP and GPT), up to 10 input images, precise selective editing, and chaining images into simple "animated" videos.
- 30.84 GiB on disk: 16.33 GiB text encoder + 13.25 GiB image transformer + 1.26 GiB VAE
- Runs on a 48GB M5 Mac using 31GB while generating, despite no Mac-specific optimization yet
The author calls it a very strong open-weights release.
More from Multimodal
- The 'turn your pet into a paper box' image-gen prompt is sweeping X — AIandDesign · 2026-09-21
- GPT Images 2.5 demo: one prompt yields a 9-grid of 70s sci-fi portraits — aziz4ai · 2026-09-21
- Qwen-Image 2.1 repo reveals the official prompt format for best text-to-image results — mantafloppy · 2026-09-21
- Full AI Music Video Built with Suno, Wan 3 and Kling 3 — CactusMonkey12 · 2026-09-21
- Dev Ships Zero-Shot Neural Style Transfer App in 6 Days Using AdaIN — whosupfirst · 2026-09-21
- Alibaba's open-weight Qwen-Image-2.1 claims to beat closed models with 7B params — The Decoder · 2026-09-21