video / image + reference image / motion / audio = video tencent/HunyuanCustom Image-to-Video • Updated Jun 6, 2025 • 190
text to text Qwen/Qwen3-235B-A22B Text Generation • 235B • Updated Jul 26, 2025 • 250k • • 1.07k
image + motion = video ZheWang123/UniAnimate-DiT Image-to-Video • Updated May 19, 2025 • • 24 shiyi0408/FlexiAct Image-to-Video • Updated May 11, 2025 • 28
Web research WebThinker: Empowering Large Reasoning Models with Deep Research Capability Paper • 2504.21776 • Published Apr 30, 2025 • 59
WebThinker: Empowering Large Reasoning Models with Deep Research Capability Paper • 2504.21776 • Published Apr 30, 2025 • 59
line art to colored image consistantly JunhaoZhuang/Cobra Image-to-Image • Updated Dec 10, 2025 • 30
video / image + reference image / motion / audio = video tencent/HunyuanCustom Image-to-Video • Updated Jun 6, 2025 • 190
Web research WebThinker: Empowering Large Reasoning Models with Deep Research Capability Paper • 2504.21776 • Published Apr 30, 2025 • 59
WebThinker: Empowering Large Reasoning Models with Deep Research Capability Paper • 2504.21776 • Published Apr 30, 2025 • 59
text to text Qwen/Qwen3-235B-A22B Text Generation • 235B • Updated Jul 26, 2025 • 250k • • 1.07k
image + motion = video ZheWang123/UniAnimate-DiT Image-to-Video • Updated May 19, 2025 • • 24 shiyi0408/FlexiAct Image-to-Video • Updated May 11, 2025 • 28
line art to colored image consistantly JunhaoZhuang/Cobra Image-to-Image • Updated Dec 10, 2025 • 30