正在加载视频...

视频加载失败

返回首页

Any2Caption Interpreting Any Condition to Caption for Controllable Video Generation

_akhaliq's profile picture

AK

410,653 subscribers

50,115 次观看 • 1 年前 •via X (Twitter)

教育科学技术
LIVE

Anya Rossi• Live Now

Private livecam show

3 条评论

AK 的头像
AK1 年前

discuss with author:

SecBriefs | Making Cybersecurity Simple 的头像
SecBriefs | Making Cybersecurity Simple1 年前

Quantum computers can break today’s encryption in seconds.🔑 Quantum tech will reshape our digital lives. Governments & hackers are preparing for the quantum era. How about you?🛡️ Don’t get left behind!🧠 Cybersecurity Dictionary for Everyone can help:

Tori 的头像
Tori1 年前

Thank @_akhaliq for sharing our work! A SoTA controllable video generation framework from **any condition** by leveraging MLLMs to interpret diverse inputs into dense structured captions. Project: Huggingface:

相关视频

CineMaster A 3D-Aware and Controllable Framework for Cinematic Text-to-Video Generation
1:43

CineMaster A 3D-Aware and Controllable Framework for Cinematic Text-to-Video Generation

AK

18,655 次观看 • 1 年前

Wan-Move Motion-controllable Video Generation via Latent Trajectory Guidance
2:00

Wan-Move Motion-controllable Video Generation via Latent Trajectory Guidance

AK

14,853 次观看 • 6 个月前

Gen-3 Alpha Text to Video is now available to everyone. A new frontier for high-fidelity, fast and controllable video generation. Try it now at
2:22

Gen-3 Alpha Text to Video is now available to everyone. A new frontier for high-fidelity, fast and controllable video generation. Try it now at

Runway

4,065,483 次观看 • 1 年前

🔥1-min Interactive Video Generation with Multimodal Control🔥 Towards *long-context world model*, #LongVie is an end-to-end autoregressive framework for controllable ultra-long video generation - Page: - Paper: . Thanks AK
2:12

🔥1-min Interactive Video Generation with Multimodal Control🔥 Towards *long-context world model*, #LongVie is an end-to-end autoregressive framework for controllable ultra-long video generation - Page: - Paper: . Thanks AK

Ziwei Liu

14,150 次观看 • 10 个月前

Infinity-RoPE Action-Controllable Infinite Video Generation Emerges From Autoregressive Self-Rollout
1:00

Infinity-RoPE Action-Controllable Infinite Video Generation Emerges From Autoregressive Self-Rollout

AK

19,562 次观看 • 6 个月前

I'm excited to share our new work Diffusion as Shader (DaS), a versatile controllable video generation method for various tasks: object manipulation, camera control, mesh-to-video, and motion transfer. Project page: Github:
0:46

I'm excited to share our new work Diffusion as Shader (DaS), a versatile controllable video generation method for various tasks: object manipulation, camera control, mesh-to-video, and motion transfer. Project page: Github:

Yuan Liu

33,363 次观看 • 1 年前

VIGGLE'S NEW MODEL IS HERE! Controllable video generation is our mission, and character is where we start. Animate any character just as you want, simply with a prompt, or by uploading a reference video featuring clear motion. Try Viggle for FREE:
1:00

VIGGLE'S NEW MODEL IS HERE! Controllable video generation is our mission, and character is where we start. Animate any character just as you want, simply with a prompt, or by uploading a reference video featuring clear motion. Try Viggle for FREE:

ViggleAI

37,487 次观看 • 2 年前

I don’t have any caption. My caption is in the video.
1:03

I don’t have any caption. My caption is in the video.

Ifediche

13,708 次观看 • 4 个月前

Hunyuan-GameCraft High-dynamic Interactive Game Video Generation with Hybrid History Condition
1:02

Hunyuan-GameCraft High-dynamic Interactive Game Video Generation with Hybrid History Condition

AK

91,039 次观看 • 11 个月前

The poverty amongst Ugandans has been deliberate to keep them controllable See the generation Museveni has created 🙌
0:31

The poverty amongst Ugandans has been deliberate to keep them controllable See the generation Museveni has created 🙌

DR MORGANS

23,691 次观看 • 7 个月前

Introducing Cube 2.0, a significant step towards controllable 3D game-world and video generation from any input. Powered by: 🌟 Image-to-3D in seconds w/ a new foundation model 🐎 Text-to-animation 🌎 AI rendering to create beautiful worlds (mesh+splats) Web app → Discord → Blog →
1:11

Introducing Cube 2.0, a significant step towards controllable 3D game-world and video generation from any input. Powered by: 🌟 Image-to-3D in seconds w/ a new foundation model 🐎 Text-to-animation 🌎 AI rendering to create beautiful worlds (mesh+splats) Web app → Discord → Blog →

Common Sense Machines

411,366 次观看 • 2 年前

No need to caption! Condition of Health system in India .💔💔
0:22

No need to caption! Condition of Health system in India .💔💔

खुरपेंची स्वास्थ्य

35,667 次观看 • 6 个月前

No need any Caption for this Video..... Caption లో చెప్పాలి అనుకున్నవి మొత్తం ఈ Video లో చెప్పేసాo... Cult #Nagfans 🔥 🔥 🔥 We love ❤️ Nagarjuna Akkineni Sir always ❤️
3:29

No need any Caption for this Video..... Caption లో చెప్పాలి అనుకున్నవి మొత్తం ఈ Video లో చెప్పేసాo... Cult #Nagfans 🔥 🔥 🔥 We love ❤️ Nagarjuna Akkineni Sir always ❤️

NagaKiran Akkineni

23,871 次观看 • 9 个月前

Condition of today’s generation
0:35

Condition of today’s generation

Mohini Maheshwari

126,015 次观看 • 1 年前

3D controllable video generation works well now and pixel alignment is impressive! We took our new 3D sculpt model, generated a blender scene and then asked a video-to-video model to render. Image to 3D sculpt: Common Sense Machines Synthetic rendering: Blender 🔶 Video-to-Video: Runway
0:29

3D controllable video generation works well now and pixel alignment is impressive! We took our new 3D sculpt model, generated a blender scene and then asked a video-to-video model to render. Image to 3D sculpt: Common Sense Machines Synthetic rendering: Blender 🔶 Video-to-Video: Runway

Common Sense Machines

18,714 次观看 • 1 年前

1/ 🚀 Introducing AIDO.StructureDiffusion: A generative model for structural protein design—enabling high-quality, controllable generation of monomers, complexes, and antibodies. 🧵
0:33

1/ 🚀 Introducing AIDO.StructureDiffusion: A generative model for structural protein design—enabling high-quality, controllable generation of monomers, complexes, and antibodies. 🧵

GenBio AI

918,205 次观看 • 10 个月前

(1/n) Time to unify your favorite visual generative models, VLMs, and simulators for controllable visual generation—Introducing a Product of Experts (PoE) framework for inference-time knowledge composition from heterogeneous models.
0:55

(1/n) Time to unify your favorite visual generative models, VLMs, and simulators for controllable visual generation—Introducing a Product of Experts (PoE) framework for inference-time knowledge composition from heterogeneous models.

Yunzhi Zhang

48,871 次观看 • 11 个月前

Remixable element "Ultimate Low Thermo Drivable Vehicles" just released in Dreams! Controllable vehicles for any game! #MadeInDreams
0:33

Remixable element "Ultimate Low Thermo Drivable Vehicles" just released in Dreams! Controllable vehicles for any game! #MadeInDreams

Freako

23,949 次观看 • 6 个月前