Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: Infinity – Realistic AI characters that can speak

news.ycombinator.com

Post reply on HN
Print view View original

161–170 of 320 posts

Re: Show HN: Infinity – Realistic AI characters that can speak

#161

Post by andrew-w »

zoogeny wrote: post #153

I am actively working in this area from a wrapper application perspective. In general, tools that generate video are not sufficient on their own. They are likely to be used as part of some larger video-production workflow. One drawback of tools like runway (and midjourney) is the lack of an API allowing integration into products. I would love to re-sell your service to my clients as part of a larger offering. Is this…

I agree, I think power users are happy to go to specific platforms, but APIs open up more use cases that can reach a broader audience. What kind of application would you use it for? We don't have specific plans at the moment, but are gauging interest.

Re: Show HN: Infinity – Realistic AI characters that can speak

#162

Post by GrantMoyer »

WaffleIronMaker wrote: post #135

Does anybody know about the legality of using Eminem's "Gozilla" as promotional material[1] for this service? I thought you had to pay artists for a license before using their work in promotional material. [1] https://infinity.ai/videos/setA_video3.mp4

https://6ammc3n5zzf5ljnz.public.blob.vercel-storage.com/inf2...

Re: Show HN: Infinity – Realistic AI characters that can speak

#163

Post by lossolo »

lcolucci wrote: post #128
genaiguy wrote: post #119

[flagged]

We are big fans of Hedra. Do you know if they've publicly commented on their model architecture? As far as we know, our particular choice of an end-to-end diffusion + transformer is novel. We don't know what Hedra is doing. It could be the approach EMO has taken ( https://humanaigc.github.io/emote-portrait-alive/ ) or VASA ( https://www.microsoft.com/en-us/research/project/vasa-1/ ) or Loopy Avatar ( https://loopyava…

One of Hedra job offers for ML role lists "diffusion transformers".

Re: Show HN: Infinity – Realistic AI characters that can speak

#165

Post by bobbylarrybobby »

andrew-w wrote: post #112
drhodes wrote: post #107

Earlier quoted context omitted.

Hmm, maybe adding white noise would work. -- OK, that's quite enough unsolicited suggestions from me up in the peanut gallery. Nice job on the website, it's impressive, thank you for not requiring a sign up.

All for suggestions! We've tried white noise as well, but it only works on plain talking samples (not music, for example). My guess is that the most robust solution will come from updating how it's trained.

What if you train it to hold the last frame on silence (or quiet noise)?

Re: Show HN: Infinity – Realistic AI characters that can speak

#166

Post by zoogeny »

andrew-w wrote: post #161
zoogeny wrote: post #153

I am actively working in this area from a wrapper application perspective. In general, tools that generate video are not sufficient on their own. They are likely to be used as part of some larger video-production workflow. One drawback of tools like runway (and midjourney) is the lack of an API allowing integration into products. I would love to re-sell your service to my clients as part of a larger offering. Is this…

I agree, I think power users are happy to go to specific platforms, but APIs open up more use cases that can reach a broader audience. What kind of application would you use it for? We don't have specific plans at the moment, but are gauging interest.

I'm looking to create an end-to-end story telling interface. I'm currently working on the MVP and my plan was just to generate the prompts and then require users to manually paste those prompts into the interfaces of products that don't support APIs and then re-upload the results. This is so far below ideal that I'm not sure it will sell at all. It is especially difficult if one tries to imagine a mobile client. Given the state of the industry it may be acceptable for a while, but ideally I can just charge some additional margin on top of existing services and package that as credits (monthly plan + extras).

Consider all of the assets someone would have to generate for a 1 minute video. Lets assume 12 clips of 5 seconds each. First they may have to generate a script (claude/openai). They will have to generate text audio and background/music audio (suno/udio). They probably have to generate the images (runway/midjourney/flux/etc) which they will feed into a img2vid product (infinity/runway/kling/etc). Then they need to do basic editing like trimming clip lengths. They made need to add text/captions and image overlays. Then they want to upload it to TikTok/YouTube/Instagram/etc (including all of the metadata for that). Then they will want to track performance, etc.

That is a lot of UI, workflows, etc. I don't think a company such as yours will want to provide all of that glue. And consumers are going to want choice (e.g. access to their favorite image gen, their favorite text-to-speech).

Happy to talk more if you are interested. I'm at the prototype stage currently. As an example, consider the next logical step for an app like https://autoshorts.ai/

Re: Show HN: Infinity – Realistic AI characters that can speak

#167

Post by bhanu423 »

andrew-w wrote: post #161
zoogeny wrote: post #153

I am actively working in this area from a wrapper application perspective. In general, tools that generate video are not sufficient on their own. They are likely to be used as part of some larger video-production workflow. One drawback of tools like runway (and midjourney) is the lack of an API allowing integration into products. I would love to re-sell your service to my clients as part of a larger offering. Is this…

I agree, I think power users are happy to go to specific platforms, but APIs open up more use cases that can reach a broader audience. What kind of application would you use it for? We don't have specific plans at the moment, but are gauging interest.

Hopping onto the original comment - I am building an video creation platform focused on providing accessible education to the masses in developing countries. Would love to integrate something like this into our platform. Would love to pay for an API access and so will so many others. Please consider opening API, you would make lot of money right now which can be used for your future plans.

Re: Show HN: Infinity – Realistic AI characters that can speak

#169

Post by andrew-w »

zoogeny wrote: post #166
andrew-w wrote: post #161

Earlier quoted context omitted.

I agree, I think power users are happy to go to specific platforms, but APIs open up more use cases that can reach a broader audience. What kind of application would you use it for? We don't have specific plans at the moment, but are gauging interest.

I'm looking to create an end-to-end story telling interface. I'm currently working on the MVP and my plan was just to generate the prompts and then require users to manually paste those prompts into the interfaces of products that don't support APIs and then re-upload the results. This is so far below ideal that I'm not sure it will sell at all. It is especially difficult if one tries to imagine a mobile client. Give…

Makes sense, thank you!

Re: Show HN: Infinity – Realistic AI characters that can speak

#170

Post by andrew-w »

bhanu423 wrote: post #167
andrew-w wrote: post #161

Earlier quoted context omitted.

I agree, I think power users are happy to go to specific platforms, but APIs open up more use cases that can reach a broader audience. What kind of application would you use it for? We don't have specific plans at the moment, but are gauging interest.

Hopping onto the original comment - I am building an video creation platform focused on providing accessible education to the masses in developing countries. Would love to integrate something like this into our platform. Would love to pay for an API access and so will so many others. Please consider opening API, you would make lot of money right now which can be used for your future plans.

Cool use case! Thanks for sharing your thoughts.
Post reply on HN