{"model":"alibaba-qwen-image-2-1-pro","air":"alibaba:qwen-image@2.1-pro","name":"Qwen-Image-2.1-Pro","creator":"alibaba","status":"live","releasedAt":"2026-09-20T00:00:00Z","weight":5,"headline":"Unified image generation and multi-reference editing with LLM prompt rewriting","description":"Qwen-Image-2.1-Pro is the Pro tier of Alibaba's Qwen-Image-2.1 family, a unified model for text-to-image generation and prompt-guided image editing. It composes and edits from up to 10 reference images and can rewrite prompts with an LLM before generation, in a direct or agent mode with optional thinking. It outputs from 0.26 to 4.19 megapixels at aspect ratios from 1:8 to 8:1, suited to product imagery, marketing visuals, and multi-image compositions.","capabilities":["io:text-to-image","io:image-to-image","op:edit","form:checkpoint","feat:transparency"],"coverImage":"https://assets.runware.ai/covers/alibaba-qwen-image-2-1-pro.jpg","ogImage":"https://assets.runware.ai/og/alibaba-qwen-image-2-1-pro.png","pricingRates":[{"amount":0.075,"unit":"output"}],"pricingExamples":[{"configuration":"text-to-image · 1536×1024","price":"$0.075","latencyMs":63384,"exampleId":"airport-falconer-editorial-portrait"},{"configuration":"text-to-image · 1536×1024","price":"$0.075","latencyMs":69651,"exampleId":"abyssal-cable-repair-game-key-art"},{"configuration":"reference-to-image · 1024×1536","price":"$0.075","latencyMs":59450,"exampleId":"sheep-shearing-docuseries-poster"},{"configuration":"reference-to-image · 1024×1536","price":"$0.075","latencyMs":27622,"exampleId":"antique-automaton-auction-cleanup"}],"guides":[{"slug":"editing-images","title":"Editing images","description":"How to edit a single image with Qwen-Image-2.1-Pro: naming what changes and what holds, swapping label copy, circling the region to edit, and chaining edits.","date":"2026-09-30","url":"https://runware.ai/docs/models/alibaba-qwen-image-2-1-pro/guides/editing-images"},{"slug":"multi-reference-composition","title":"Composing from multiple reference images","description":"How to combine up to ten reference images with Qwen-Image-2.1-Pro: assigning each a role, dressing a model from packshots, staging a room, and building a team photo.","date":"2026-09-30","url":"https://runware.ai/docs/models/alibaba-qwen-image-2-1-pro/guides/multi-reference-composition"},{"slug":"prompt-extension","title":"Prompt extension","description":"How promptExtend works on Qwen-Image-2.1-Pro: what the LLM rewrite adds, how direct and agent differ, where thinking fits, and why an extended prompt breaks seeds.","date":"2026-09-30","url":"https://runware.ai/docs/models/alibaba-qwen-image-2-1-pro/guides/prompt-extension"},{"slug":"prompting","title":"Prompting","description":"How to prompt Qwen-Image-2.1-Pro, from sizing inside its pixel budget and banner ratios to layering a scene, quoting on-image copy, and locking a result with a seed.","date":"2026-09-30","url":"https://runware.ai/docs/models/alibaba-qwen-image-2-1-pro/guides/prompting"},{"slug":"transparent-backgrounds","title":"Transparent backgrounds","description":"How to generate cut-outs with a real alpha channel on Qwen-Image-2.1-Pro: the prompt wording that turns it on, the output formats that keep it, and subject extraction from a photo.","date":"2026-10-05","url":"https://runware.ai/docs/models/alibaba-qwen-image-2-1-pro/guides/transparent-backgrounds"}]}