Tavondo
CompetitionsEventsGuidesPlatforms
中文Start matching
CompetitionsEventsGuidesPlatforms
中文Sign in
Tavondo

Find AI competitions and events worth your time.

CompetitionsEventsGuidesPlatforms
Sign inRegisterStart matching

© 2026 Tavondo

中文
  1. Home
  2. Competitions
  3. 可图Kolors-LoRA风格故事挑战赛
ModelScopeLLMIntermediateRegistration closed

可图Kolors-LoRA风格故事挑战赛

A intermediate llm competition requiring roughly 10–30 hours for an end-to-end practice run.

Difficulty
Intermediate
Estimated effort
10–30 hours
Registration deadline
Aug 31, 2024
Compute
Free GPU OK
OverviewPreparationSource

Overview

Who this competition fits

适合已有扩散模型图像生成与 LoRA 微调经验的人,尤其是能在 Kolors 基础上训练风格模型、用提示词维持角色和画风一致性的创作者。决赛选手还需要能将图文故事作品在线上答辩中展示并说明创作过程。

Read the original official blurb
1. 参赛者需在可图Kolors 模型的基础上训练LoRA 模型,生成无限风格,如水墨画风格、水彩风格、赛博朋克风格、日漫风格...... 2. 基于LoRA模型生成 8 张图片组成连贯故事,故事内容可自定义;基于8图故事,评估LoRA风格的美感度及连贯性。 Official category: LoRA训练赛. Participants: 0. Organizers: 魔搭社区.

Preparation

From registration to a first submission

  1. 01

    Kolors LoRA 训练

  2. 02

    DiffSynth-Studio

  3. 03

    图像数据集处理

  4. 04

    Data-Juicer

  5. 05

    ComfyUI 工作流

  6. 06

    提示词编写

Before you commit: 难点不只是训练出好看的单张图,而是提交可复现的 LoRA 模型、模型介绍、至少 8 张图片及对应 prompt,并让同一风格下的人物、场景和剧情跨图保持连贯。最终评分以主观评审为准,技术运用、连贯性和视觉效果都要兼顾。

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

Entry assessment

est.
55

Prepare before joining

Overall fit estimate

Beginner fit55/100
Learning value58/100

Confirm eligibility and time commitment before moving into formal preparation.

Entry eligibility needs official confirmation

Open official pageSign in to saveOpen guide

Timeline

Registration deadline
Aug 31, 2024

Data and review state

Separate what is confirmed from what still needs review. Official rules and deadlines win.

View data stateClose
Source page verifiedMetric confirmedReviewed
Source published
Jul 15, 2025
Published on this site
Aug 11, 2026

Official metric is not published on the ModelScope competition listing; verify scoring on the competition page.

reward_value_usd is a rough CNY→USD estimate (×0.14) for ranking only; use reward_summary for the official prize text.