KlingTeam
/

VidEmo-7B

Video-Text-to-Text

Model card Files Files and versions

VidEmo: Affective-Tree Reasoning for Emotion-Centric Video Foundation Models

Zhicheng Zhang^1,†, Weicheng Wang¹, Yongjie Zhu^3,‡, Wenyu Qin³, Pengfei Wan³, Di Zhang³, Jufeng Yang^1,2,✉

¹Nankai University ²Pengcheng Laboratory ³Kuaishou Technology

^†Work done at KlingAI ^‡Project Leader ^✉Corresponding Author

🎉 Accepted by NeurIPS 2025 🎉

HF Model: VidEmo Family

HF Model: VidEmo Family

HF Dataset: Emo-CFG 2.1M

Downloads last month: 21

Safetensors

Model size

8B params

Tensor type

BF16

·

Inference Providers NEW

Video-Text-to-Text

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for KlingTeam/VidEmo-7B

Base model

Qwen/Qwen2.5-VL-7B-Instruct

Finetuned

(1024)

this model

Quantizations

Dataset used to train KlingTeam/VidEmo-7B

Paper for KlingTeam/VidEmo-7B

VidEmo: Affective-Tree Reasoning for Emotion-Centric Video Foundation Models

Paper • 2511.02712 • Published Nov 4, 2025 • 6