@HuggingPapers: Alibaba released Qwen-Image-Flash Few-step distillation goes beyond objectives. Data composition, teacher guidance, and…
Summary
Alibaba released Qwen-Image-Flash, a few-step distilled model for fast, high-quality text-to-image generation and instruction-guided editing, leveraging data composition, teacher guidance, and task mixture.
Similar Articles
Qwen-Image-Flash (26 minute read)
This paper from Alibaba revisits few-step distillation for visual generative models, focusing on training recipe factors such as data composition, teacher guidance, and task mixture, using Qwen-Image-2.0 as a case study to develop Qwen-Image-Flash.
Qwen-Image-Flash: Beyond Objective Design
This paper investigates training recipes for few-step distillation of visual generative models, using Qwen-Image-2.0 as a case study. It reveals non-obvious behaviors and proposes Qwen-Image-Flash.
Qwen-Image-2.0 Technical Report (57 minute read)
This technical report presents Qwen-Image-2.0, a new image generation model from Alibaba's Qwen team, detailing its architecture and capabilities.
@AdinaYakup: Qwen @Alibaba_Qwen just dropped a new Text to Image benchmark + a judge model https://huggingface.co/collections/Qwen/q…
Qwen released a new Text-to-Image benchmark with 56 fine-grained evaluation facets, measuring creativity beyond prompt alignment, and includes a human-aligned judge model.
Qwen-Image-2.0 Technical Report
Qwen-Image-2.0 is a new image generation foundation model that unifies high-fidelity synthesis and precise editing using Qwen3-VL and a Multimodal Diffusion Transformer. It excels in text-rich content, multilingual typography, and photorealistic generation.