ModelScope Civision adds Qwen-Image-2.1 inference and LoRA training
ModelScope says it now supports both inference and LoRA training for Qwen-Image-2.1 in Civision.
The announcement links to modelscope.ai/civision.
Related AI news
inclusionAI open-sources two 6B Ming-Image-0.1-Design models
inclusionAI has open-sourced the Ming-Image-0.1-Design family under the MIT License: two complementary 6B models, Design and Layer, for visual-design workflows. ModelScope says Design ranks first among open-weight models on the Artificial Analysis UI/UX Design leaderboard, and that Layer leads all 12 evaluated Crello settings while running 4.3× faster than the evaluated 20B open-weight baseline.
Qwen introduces RecreationBench for hybrid computer-use agents
ModelScope said Qwen has introduced RecreationBench, a 250-task benchmark for Hybrid Computer-Use Agents across Ubuntu, macOS, Windows, Android, and Web. Agents must explore a running app, recreate it in code, and pass programmatic tests plus VLM-based visual evaluation.
Shanghai AI Lab and SJTU's LUMIA Lab release 8.9B open-weight model NCP-ArchPreview
NCP-ArchPreview is released under Apache 2.0. The labs report that, after training on 5.73 trillion Dolma 3 tokens, it matches OLMo-3-7B’s final Stage 1 loss with 51.3% of the tokens, a 1.95× convergence gain.
Sayak Paul: KV caching in QwenImage 2.1 measured at 2.55x speedup
Sayak Paul described how KV caching is incorporated in QwenImage 2.1 by caching fixed context separately from image positions that change at each denoising step. He said later steps become cheaper and a 2.55x speedup was measured.
Alibaba Cloud says Qwen-Image-2.1 improves text and portrait aesthetics
Alibaba Cloud said Qwen-Image-2.1 improves visual quality over its predecessor, particularly in the aesthetics of text and portraits, and shared text-rendering examples.