Qwen image 2.1 图像处理工作流

工作流介绍

阿里巴巴通义千问团队于 2026 年 9 月 20 日发布 Qwen-Image-2.1，推出一款把文生图和图像编辑放进同一条流水线的轻量图像模型。可以更好的在本地进行图像编辑。

视频讲解

模型需求

• qwen_image_2.1_int8_convrot.safetensors 位置models\\diffusion_models
• qwen3vl_8b_int8_convrot.safetensors 位置models\\text_encoders
• qwen_image_2.1_vae_bf16.safetensors 位置 models\\vae\

下载地址：（根据说明按需下载）：https://www.digitfold.com/5075.html

参数说明

像素量

提示词指令

Qwen-Image-2.1/prompt_rewrite/prompts at main · QwenLM/Qwen-Image-2.1

提示词参考

1. l3n0v0. A woman with long brown hair sits in profile on a stone ledge, ove – Pastebin.com

A woman with long brown hair sits in profile on a stone ledge, overlooking a wide river during a vivid sunset. They are dressed in a dark long-sleeved top with fingerless gloves, sheer black stockings, and chunky platform shoes, carrying a black backpack adorned with a silver metallic charm. In the distance, a large suspension bridge spans the calm water, silhouetted against a cityscape under a sky filled with glowing orange and gold cumulus clouds. The scene is bathed in warm, soft-focus sunset backlighting that casts deep shadows and reflects brilliant amber tones across the water’s surface. The image exhibits a slight grain typical of high-ISO digital photography, creating an atmospheric, melancholic, and serene mood.

candid raw amateur phone snapshot, standing full-body eye-level portrait taken outdoors on a subway platform. A young woman with messy shoulder-length dark brown hair and a pensive, neutral expression, looking slightly off-camera. She is wearing an oversized black knitted cardigan sweater, used as a dress, black platform combat boots, and patterned cream-white lace knee-high socks. She holds a very large, dense bouquet of fresh white daisies (marguerites) with prominent green stems and leaves, clutched casually against her chest with both hands. She is standing centered in the frame. The background is a moving blue and white subway train with large windows and a distinct white horizontal stripe, captured with motion blur that creates streaks of light and dark, emphasizing speed and transit. The station lights are soft and low, casting realistic, slightly uneven light on her. Visible phone camera digital grain, high ISO noise, muted moody colors, natural shallow depth of field, realistic unposed texture, vertical 3:4 aspect ratio.

Skill

iamvts/Qwen-Image-2.1-Skills · Hugging Face