Batch API — 50% off for async requests to our models:
GENERATIVE AI
-
Tencent InstantMesh Converts Single Photos to 3D Models
By
–
Making 3D objects from a single photograph was a big challenge, but Tecent's image mesh can create one in 10 seconds
— Ethan Mollick (@emollick) 15 avril 2024
There is a free demo to play with. I made a penguin mech in Midjourney (the upper lefthand image) and it made it a 3D model. Impressive. https://t.co/Sm5Z1nbJ9w pic.twitter.com/ZDPN0ymcaZMaking 3D objects from a single photograph was a big challenge, but Tecent's image mesh can create one in 10 seconds There is a free demo to play with. I made a penguin mech in Midjourney (the upper lefthand image) and it made it a 3D model. Impressive. https://
huggingface.co/spaces/Tencent
ARC/InstantMesh
… -
Clear Communication Key to Effective AI Model Prompting
By
–
I wonder if part of that is that being "good st prompting" is mainly about being good at clear and explicit communication People with prompts of a less high quality may find they see bigger differences between models
-
NVIDIA Named Google Cloud Partner of Year for Generative AI
By
–
We're thrilled to be named a #GoogleCloudPartnersTechnology Partner of the Year. NVIDIA on #GoogleCloud supports more platforms, services, and hardware to accelerate customer journeys with #GenerativeAI. https://
nvda.ws/4aYJZCt #GoogleCloudNext -
Hacking AI Pin to Run Gemma 2B Locally Without Internet
By
–
Who is going to be the first to find a way to hack the ai pin and run like Gemma 2B locally on it and see how it works instead of needing an internet connection (or only periodically phoning a cv/tts model)?
-
Refactoring Diffusion Models: Updates on Generative AI Research
By
–
Spent some time refactoring the 2021 post on diffusion model with new content: https://
lilianweng.github.io/posts/2021-07-
11-diffusion-models/
… Then another short piece on diffusion video models: https://
lilianweng.github.io/posts/2024-04-
12-diffusion-video/
… (Yes, I had an intensive weekend) -
Reka Core AI Model Now Available on Poe Platform
By
–
Reka Core is available at https://
poe.com/RekaCore and across all Poe apps. (2/2) -
Reka Core Multimodal Model Now Available on Poe Platform
By
–
Reka Core is now available on Poe! This state-of-the-art multimodal model matches leading LLMs in key evaluation metrics around reasoning, advanced coding, and multilingual capabilities, and is state of the art at understanding short videos. (1/2) https://t.co/OWl2ac2ZLD
— Poe (@poe_platform) 15 avril 2024Reka Core is now available on Poe! This state-of-the-art multimodal model matches leading LLMs in key evaluation metrics around reasoning, advanced coding, and multilingual capabilities, and is state of the art at understanding short videos. (1/2)
-
Prompt Portability Across Claude GPT-4 Gemini Models
By
–
It is a surprise that you can move very complex prompts (like pages of text) from Claude 3 to GPT-4 to Gemini 1.5 and have it generally work quite well without modification. Tweaking is usually only a couple of minutes to match the models "mood." I wouldn't have expected that.
-
Quantization Dramatically Compresses LLMs for Consumer Hardware
By
–
LLMs can take gigabytes of memory to store, which limits what can be run on consumer hardware. But quantization can dramatically compress models, making a wider selection of models available to developers. You can often reduce model size by 4x or more while maintaining reasonable… pic.twitter.com/ASQ28fzgkB
— Andrew Ng (@AndrewYNg) 15 avril 2024LLMs can take gigabytes of memory to store, which limits what can be run on consumer hardware. But quantization can dramatically compress models, making a wider selection of models available to developers. You can often reduce model size by 4x or more while maintaining reasonable