The model is fast, producing a 2.25-megapixel depth map in 0.3 seconds on a standard GPU.
https://github.com/apple/ml-depth-pro
https://arxiv.org/pdf/2410.02073
a blog of links related to computer animation and production technology Sponsored by ReelMatters.com
Category: A.I.
-
Sam Altman – The Intelligence Age
In the next couple of decades, we will be able to do things that would have seemed like magic to our grandparents.
This phenomenon is not new, but it will be newly accelerated. People have become dramatically more capable over time; we can already accomplish things now that our predecessors would have believed to be impossible.
We are more capable not because of genetic change, but because we benefit from the infrastructure of society being way smarter and more capable than any one of us; in an important sense, society itself is a form of advanced intelligence. Our grandparents – and the generations that came before them – built and achieved great things. They contributed to the scaffolding of human progress that we all benefit from. AI will give people tools to solve hard problems and help us add new struts to that scaffolding that we couldn’t have figured out on our own. The story of progress will continue, and our children will be able to do things we can’t.
-
The riddles humans can solve but AI computers cannot
https://www.bbc.com/future/article/20240912-what-riddles-teach-us-about-the-human-mind
“As human beings, it’s very easy for us to have common sense, and apply it at the right time and adapt it to new problems,” says Ilievski, who describes his branch of computer science as “common sense AI”. But right now, AI has a “general lack of grounding in the world”, which makes that kind of basic, flexible reasoning a struggle.
AI excels at pattern recognition, “but it tends to be worse than humans at questions that require more abstract thinking”, says Xaq Pitkow, an associate professor at Carnegie Mellon University in the US, who studies the intersection of AI and neuroscience. In many cases, though, it depends on the problem.
A bizarre truth about AI is we have no idea how it works. The same is true about the brain.
That’s why the best systems may come from a combination of AI and human work; we can play to the machine’s strengths, Ilievski says.
-
Lionsgate signs deal with AI company Runway, hoping that AI can eliminate storyboard artists and VFX crews
The goal is to reduce costs by replacing traditional storyboard artists and VFX crews with AI-generated “cinematic video.” Lionsgate hopes to use this technology for both pre- and post-production processes. While the company promotes the cost-saving potential, the creative community has raised concerns, as Runway is currently facing a lawsuit over copyright infringement.
-
DepthCrafter – Generating Consistent Normals Long Depth Sequences for Open-world Videos
https://depthcrafter.github.io/
We innovate DepthCrafter, a novel video depth estimation approach, by leveraging video diffusion models. It can generate temporally consistent long depth sequences with fine-grained details for open-world videos, without requiring additional information such as camera poses or optical flow.
-
ByteDance Loopy: Taming Audio-Driven Portrait Avatar with Long-Term Motion Dependency
https://loopyavatar.github.io/
Loopy supports various visual and audio styles. It can generate vivid motion details from audio alone, such as non-speech movements like sighing, emotion-driven eyebrow and eye movements, and natural head movements.
-
Freepik Mystic – AI image-generator based on Flux
Built on top of a series of fine-tunes of Stable Diffusion, Flux, and Magnific-built models.
https://www.freepik.com/ai/image-generator
-
Artifacts now available for all Claude.ai users across our Free, Pro, and Team plans
https://www.anthropic.com/news/artifacts
Artifacts turn conversations with Claude into a more creative and collaborative experience.
-
Francisco Contreras – vinavfx / nuke_comfyui
It connects Nuke with the ComfyUI server, any plugin that comes out in ComfyUI can be used in nuke, rotos with sam, rescaling, image generation, inpaintins, normal generator, the nodes are IPAdapter, ControlNet, AnimateDiff, Flux etc.
https://github.com/vinavfx/nuke_comfyui
-
Convert 2D Images to 3D Models
- HyperHuman Rodin – free and pay per use
- LumaLabs Genie – free, web based
- Vectary – free and monthly fees, web based
- Selva3D – pay per use
- 3D-Tool – one off payment
- Insight3d – free and open-source
- ItsLitho – free, web based
- Blender – free
- SculptGL – free, web based
- Embossify – pay per use, web based
- Smoothie-3D – free, web based
- ZW3D – one off payment
- ImageToSTL – free, web based
- Alpha3D – First 50 AI-generated 3D assets free
- Reliefmod – free, web based
- 3D Builder – free
- Cube by CSM.ai – web based
- Kaedim3D – monthly and pay per use fees
- 3DForPrint – free, web based
- ZoeDepth – free, web based
- ZoeDepth Colab notebook – easy to use interface for the depth estimation model “ZoeDepth”
- TilingZoeDepth – higher resolution free web based
- DreamGaussian – free, web based
- Photoshop Neural Filters – monthly fees
- DepthR – pay per use
- Materialize – open source
- VistaSculpt – monthly fees
- STL2PNG Converter – free
- Hi3D – free
- Meshy.ai – Text to 3D – free and pay per use
https://www.rankred.com/convert-2d-images-to-3d/
Categories
- 3Dprinting (166)
- A.I. (557)
- animation (337)
- blender (183)
- colour (224)
- commercials (45)
- composition (147)
- cool (357)
- design (617)
- Featured (56)
- hardware (291)
- IOS (107)
- jokes (134)
- lighting (272)
- modeling (104)
- music (183)
- photogrammetry (161)
- photography (740)
- production (1,225)
- python (81)
- quotes (480)
- reference (302)
- software (1,285)
- trailers (287)
- ves (510)
- VR (218)
Recent Posts
- Arvid Schneider – Environments Using Biomes in Houdini
- Odyssey.systems Explorer – pioneering generative world models and gaussian splatting
- AnimateAI.pro – All-in-One temporally stable and consistent AI Animation Story Video Generator
- Meta Releases Video Seal – A state-of-the-art, open-source model for video watermarking
- TencentARC BrushEdit – All-In-One Image Inpainting and Editing