Qwen releases 7B image model with native transparency, local edits and 10 reference images
VraserX · x · 2026-09-24
Qwen has released a 7B image generation model that can natively generate transparent images, perform local edits, and combine up to 10 reference images.
The poster argues that a model this small doing serious creative work locally is more interesting than yet another giant cloud-only image model — the appeal is powerful AI you can actually own and run yourself.
More from Multimodal
- WVLNGTH Brighton puts 9 AI video creators' work on cinema screens — LudovicCreator · 2026-09-24
- Pixel Art Test Improved by Having GPT-6-Sol Use PixiJS Instead of Pure JS — burny_tech · 2026-09-24
- Claude Opus 5.5 writes a Bach-style fugue good enough to enjoy as music — repligate · 2026-09-24
- Claude One-Shots a Full Music Video: P(doom) MV Source Code Goes Open Source — trq212 · 2026-09-24
- ECCV MMBU Benchmark Shows VLMs Answer Biomedical Questions Without Knowing What They See — davidjhwu · 2026-09-24
- Dev reverse-engineers Qwen Image 2.1 PE, ships ComfyUI node that auto-computes dimensions — BleynSpecnaz · 2026-09-24