Message from September 21, AliQuestionsIt was announced yesterday thatOpen SourceThe thousands of questions about the current open source of the image series that combines the effects of generation, the efficiency of reasoning and the cost of useimagery model Qwen-Image-2.1。
Qwen-Image-2.1 integrates the texture map with image editing in the same model, with only 7B parameters in the visual generation component, and the original supports the generation and editing of transparent images。
Officially, the main features of this update include four aspects:
- It's a very good model: Light-weight model structure optimizes with reasoning, striking a balance between quality generation and costing。
- Original transparency, transformation: Generate normal or transparent images based on the hints and support transparent layer editing and graphing。
- Full-time editor, multi-set security: Most supported 10 reference maps, enhances local editing, image and commodity authenticity and covers multiple editorial tasks。
- That's very substantive. Nice words: To enhance text layouts, person-sight and detail, to make the results more beautiful。
1AI WITH RELEVANT LINKS:
- GitHub: https://github.com/QwenLM/Qwen-Image-2.1
- HuggingFace: https://huggingface.co/Qwen/Qwen-Image-2.1
- ModelScope: https://www.modelscope.cn/models/Qwen/Qwen-Image-2.1
statement:The content of the source of public various media platforms, if the inclusion of the content violates your rights and interests, please contact the mailbox, this site will be the first time to deal with.