SkyCaptioner-V1

Skywork/SkyCaptioner-V1

Video Text To Text8.3B parameterstransformersLicense: apache-2.0
Tracked by OpenModelStats since September 30, 2026View on Hugging Face ↗
Downloads 30D
372
Total downloads
17.4K
Gained 7D
+131(increase)
0.8%(up) vs baseline
Gained 30D
—
Likes
51
+0 in 7D
Rank · tracked models
#46,704
644(down 644 places)this week
Parameters
8.3B
Last source update
Apr 25, 2025
Momentum
35.2
  • SkyCaptioner-V1 gained 131 downloads during the last seven tracked days.

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Overview

SkyCaptioner-V1 is a video text to text model published by Skywork. OpenModelStats has tracked the model since Sep 30, 2026, most recently observing it 33h ago.

Published
Apr 18, 2025
Last updated
Apr 25, 2025
Library
transformers
License
apache-2.0
Task
Video Text To Text
Parameters
8,292,166,656
Spaces
—
Derivative models
—
Velocity 7D/day
19
transformerssafetensorsqwen2_5_vlimage-text-to-textvideo-text-to-textarxiv:2504.13074license:apache-2.0text-generation-inferenceendpoints_compatibleregion:us

Similar models

Models similar to SkyCaptioner-V1
ModelDL 30D
TimeLens-7BTencentARC924
qwen2.5-vl-7b-cam-motionchancharikm242
VideoChat-R1_7B_captionOpenGVLab44
VideoScore-v1.1TIGER-Lab1,050
VITA-1.5VITA-MLLM378
InternVideo2_5_Chat_8BOpenGVLab4,030
Skywork/SkyCaptioner-V1 — Downloads, Growth & Stats | OpenModelStats