[dead]
Veo 3 and Imagen 4, and a new tool for filmmaking called Flow
261–270 of 570 posts
Re: Veo 3 and Imagen 4, and a new tool for filmmaking called Flow
#262Earlier quoted context omitted.
Yeah, there will be so many AI generated videos that many will go unwatched. Not sure where this is heading but it's certainly an interesting future.
Nobody will watch anyone's "creations". The TV or whatever device watch on will observe what you and everyone else engage with and how you interact with it and create content for you on the fly, just like Instagram and TikTok's feeds do now. AI creatives can enjoy the brief blip in time where they might get someone else to watch what they've created before their skills become obsolete in an exponentially faster rate…
Then everyone can just get their own personal movies and infinite content stream. Honestly people would probably like that given how atomized society has become.
Re: Veo 3 and Imagen 4, and a new tool for filmmaking called Flow
#263All my Veo 3 videos has sound missing. No idea why. Seems like a common problem.
Re: Veo 3 and Imagen 4, and a new tool for filmmaking called Flow
#264[dead]
Re: Veo 3 and Imagen 4, and a new tool for filmmaking called Flow
#265This is technically impressive and I commend the team that brought it to life. It makes me sad, though. I wish we were pushing AI more to automate non-creative work and not burying the creatives among us in a pile of AI generated content.
Data for the non creative work isn’t as easy to, uh, “obtain” from others without their consent.
Re: Veo 3 and Imagen 4, and a new tool for filmmaking called Flow
#266It finally feels like the professional tools have greatly outpaced the open source versions. While wan and hunyuan are solid free options, the latest from Google and Runway have started to feel like a league above. Interestingly it feels like the biggest differentiator is editing tools - ability to prompt motion, direction, cuts, or weaving in audio, rather than just pure ability to one shot. These larger companies a…
We will know GAI exists when there is no difference, because anything can be coded at any level of quality :)
Re: Veo 3 and Imagen 4, and a new tool for filmmaking called Flow
#267Earlier quoted context omitted.
The first two paragraphs of your argument could be used to discuss whether Photography (Camera is doing most of the work) or Digital Drawing (Photoshop is doing most of the work) are art. Both things which were dismissed as not art at first but are widely accepted as an art medium nowadays.
I see this comparison to a camera a lot but I don't think it works (not that you're saying this, I'm just contributing). I'm not an expert but to me the camera is doing very little of the work involved in taking an artistic picture. The photographer chooses which camera to use to get a certain effect, which lenses, the framing, etc. All the camera is doing recording the output of what the person is specifying.
Billions of R&D and millions of man hours made the camera exist. It’s doing most of the embodied work.
Re: Veo 3 and Imagen 4, and a new tool for filmmaking called Flow
#268After doing some testing, Imagen 4 doesn't score any higher than Imagen 3 on my comparison chart, approximately ~60% prompt adherence accuracy. https://genai-showdown.specr.net
More difficult examples: - wine glass that is full to the edge with wine (ie. not half full) - wrist watch not showing V (hands at 10 and 2 o'clock) - 9 step IKEA shelf assembly instruction diagram - any kind of gymnastics / sport acro
What's the reason to test the "not showing ..."? I've never seen anyone make that kind of request in real life. They ask for what they actually want instead. You'd ask for a clock showing 3:25 rather than "not 10:10".
I mean, it's a fun edge case, but I'm practice - does it matter?
Re: Veo 3 and Imagen 4, and a new tool for filmmaking called Flow
#269After doing some testing, Imagen 4 doesn't score any higher than Imagen 3 on my comparison chart, approximately ~60% prompt adherence accuracy. https://genai-showdown.specr.net
The winning image entry for "The Yarrctic Circle" by OpenAI 4o doesn't actually wields a cutlass. It's very aesthetically pleasing, even though it's so wrong in all fundamental aspects (perspective is nonsensical and anatomy is messed up, with one leg 150% longer than the other, ...). It's a very interesting resource to map some of the limits of existing models.
Good catch - that's on me I accidentally uploaded the wrong image for gpt-image-1. Fixed!
Re: Veo 3 and Imagen 4, and a new tool for filmmaking called Flow
#270It finally feels like the professional tools have greatly outpaced the open source versions. While wan and hunyuan are solid free options, the latest from Google and Runway have started to feel like a league above. Interestingly it feels like the biggest differentiator is editing tools - ability to prompt motion, direction, cuts, or weaving in audio, rather than just pure ability to one shot. These larger companies a…
We will know GAI exists when there is no difference, because anything can be coded at any level of quality :)
Well no, humans have 'natural' general intelligence and there's an obvious gap between an expert and a novice at any task.