Yeah like a neural genie representation of your video with a slider so you can go from faithful to plausible
CREATIVE AI
-
Virtual Production Sessions: Async and Live Collaboration Modes
By
–
like a virtual production session – with the equivalents for async over zoom or live IRL. need both modes.
-
OpenAI Releases Wildly Capable ChatGPT Images 2.0
By
–
quoted tweet takes you to the reply he blocked me after 🙂 clearly talking about opensource efforts and what's good and bad for the community is off-topic / offensive now (???)
-

AI Model Excels at Text Rendering and Creative Generation
By
–
– I said that this was genuinely sad and I was trying to engage him around his oss efforts in a transparent way, undeserved reaction – As I said, it is not easy to be getting messages like from people I vouched for P.S. In the age of agents, the # of commits are irrelevant
-

OpenAI Unveils ChatGPT Images 2.0, Heralded as Smartest Ever
By
–

(see pinned tweet to my profile and to my x/LocalLLaMA community below) https://
x.com/i/status/20375
40360310731036
… -
World Labs Models Progress: Photorealism and Capture Requirements Evolution
By
–
Coexist – I feel like world labs and models like it are at the Midjourney v2/3 stage rn. They’ll get more photorealistic, support larger generations. Meanwhile density of capture requirements on the reality capture / radiance field end will go down.
-
Anthropic Launches Claude Design for AI-Generated Visuals
By
–
Same answer I told the guy below except it'll be the 35B
-
Meta Announces Muse Spark, a New Multimodal AI Model
By
–
I agree Part of working in opensource is actually transparency and being open to critique (otherwise you end up with code thieves like Ollama) I hope everyone reassess themselves and work for the good of the community
-
Radiance Fields Revive Shuttered Videogrammetry Capture Studios
By
–
i feel u – think of all the videogrammetry capture studios that shuttered (eg that massive intel stage). radiance fields would breathe new life into them instantly AND we can play all this back on a regular phone now
-
Image Models Generate Dreamlike Art Through Inpainting Techniques
By
–
Sounds like a fun rabbit hole 🙂 Using the world knowledge of image models to fill in the holes would make it particularly dream like