Overview
Who this competition fits
适合已有 AIGC 图像生成基础、能在魔搭平台训练和发布 LoRA 的创作者。参赛者还需要能围绕地标建筑收集或制作训练图像,并产出多组可辨认的风格化建筑作品。
Read the original official blurb
当冬日的寒风拂过,我们用AI+艺术温暖每一个角落,共同绘制每个人心中的理想城市。 Official category: LoRA训练赛. Participants: 0. Organizers: 魔搭社区.
Preparation
From registration to a first submission
- 01
LoRA 模型训练
- 02
图像数据集整理与打标
- 03
提示词编写
- 04
SDXL 图像生成
- 05
ControlNet 线稿与深度控制
- 06
图生图工作流
Before you commit: 最费工夫的是把 LoRA 训练成既有鲜明风格、又能迁移到不同地标和场景的模型;评审明确考察泛化性,且生成效果需要能够明显复现。还需按规范公开模型、提交多组原图与风格化图,并附地标名称和 LoRA 链接。
Source
How this page was assembled
Competition information is structured from the official page. Scores are platform estimates for decision support; official rules take precedence.
- Official competition page
- ModelScope
- Last checked
- Jul 15, 2025