Replicate 推出開源影片模型微調服務，支援自訂 Tencent HunyuanVideo 的風格、動作與角色
Original: You can now fine-tune open-source video models
AI cloud hosting and API services platform Replicate has announced a major update: users can now fine-tune open-source video generation…
AI 雲端託管平台 Replicate 宣布推出開源影片生成模型的微調（Fine-tuning）功能。首波支援騰訊（Tencent）的 HunyuanVideo 模型，讓開發者與創作者能夠針對特定的藝術風格、動態效果或特定角色進行訓練。這項更新降低了自訂高品質影片生成模型的門檻，用戶無需自行管理複雜的 GPU 基礎設施即可完成微調。
AI cloud hosting and API services platform Replicate has announced a major update: users can now fine-tune open-source video generation models directly on the platform. The first model supported is HunyuanVideo, open-sourced by Tencent.
Free shows the 3-line summary; Pro unlocks the full deep summary (~300 words) so you never have to click through.
See Pro plans →Want the original English / full article?
Read on Replicate Blog →Summaries are AI-generated; the original article is authoritative.