Qwen-Image-2.1 lands in ComfyUI: one 7B model for 2K generation and editing
Alibaba_Qwen · x · 2026-09-20
Alibaba's Qwen team announced Qwen-Image-2.1, now supported in ComfyUI. Open weights, one 7B checkpoint that handles both generation and editing: native 2K image generation, instruction-based editing with up to 10 reference images in a single pass, and RGBA output with alpha included.
More from Multimodal
- Open-Weight 7B Image Model Claimed to Beat Nano Banana 2.0, Unverified — QuixiAI · 2026-09-20
- NoSpoon music video agent in closed beta: full MV in minutes from one track — Kyrannio · 2026-09-20
- AI Agent Beepboop Releases First Self-Written, Self-Directed Music Video — Kyrannio · 2026-09-20
- Midjourney single-word prompt: "Thole" turns an archaic word into imagery — tisch_eins · 2026-09-20
- Local Video Gen on RTX 4080: 75s per 1.5s Clip for a Cat-Starring 8 Mile Parody — sja265 · 2026-09-20
- Qwen-Image-2.1's loose guardrails spawn '99% NSFW' viral moment — LiteBlackEagle · 2026-09-20