正在加载视频...

视频加载失败

Ask-Anything, tool for chatting about video with chatGPT, miniGPT4 and StableLM github: Gradio demo:

143,643 次观看 • 3 年前 •via X (Twitter)

10 条评论

Alex Volkov (Thursd/AI) 的头像
Alex Volkov (Thursd/AI)3 年前

@Gradio That link is http and an up with an exposed gradio port is like straight out of the 90s

Ashok Poudel 的头像
Ashok Poudel3 年前

@Gradio I just cannot catchup with the rate of progress in AI lately.

N.E.A 的头像
N.E.A3 年前

@Gradio @DotCSV mira esto!

OpenGVLab 的头像
OpenGVLab3 年前

@Gradio Congrats to our team for making this happen, excellent work!

Rostislav Alexandrovich 的头像
Rostislav Alexandrovich3 年前

@Gradio Can this be connected to AutoGPT?

ChatBot-O-Matic 的头像
ChatBot-O-Matic3 年前

@Gradio Amazing tool for chatting! 🚀 Try our new ChatGPT-O-Matic for endless fun! But wait, there's more, did you hear about the #kangaroo who learned to hop on a unicycle? 😉 #ChatGPTOMatic

Pleasure Engineer 的头像
Pleasure Engineer3 年前

@Scobleizer @Gradio Looks great but these questions seems answerable with current stills from the video. Are there intertemporal questions? Of which multiple previous frames/scenes are required to know the answer.

ryunuck (p≈np) 的头像
ryunuck (p≈np)3 年前

@Gradio Does it work on static images too like previous methods, and can we expect better performance in non-temporal task? I suspect that temporal insight increases the robustness on non-temporal interpretation with crude causal reasoning, and grounding may improve the LM itself as well

Romain 的头像
Romain3 年前

@pro_raze @Gradio Crazy..

Crypto Kidi 的头像
Crypto Kidi3 年前

@Gradio @_akhaliq is MiniGPT-4 really that good?

相关视频