BREAKING NEWS
LATEST POSTS
-
ByteDance OmniHuman-1
https://omnihuman-lab.github.io
They propose an end-to-end multimodality-conditioned human video generation framework named OmniHuman, which can generate human videos based on a single human image and motion signals (e.g., audio only, video only, or a combination of audio and video). In OmniHuman, we introduce a multimodality motion conditioning mixed training strategy, allowing the model to benefit from data scaling up of mixed conditioning. This overcomes the issue that previous end-to-end approaches faced due to the scarcity of high-quality data. OmniHuman significantly outperforms existing methods, generating extremely realistic human videos based on weak signal inputs, especially audio. It supports image inputs of any aspect ratio, whether they are portraits, half-body, or full-body images, delivering more lifelike and high-quality results across various scenarios.
-
Conda – an open source management system for installing multiple versions of software packages and their dependencies into a virtual environment
https://anaconda.org/anaconda/conda
https://docs.conda.io/projects/conda/en/latest/user-guide/getting-started.html
NOTE The company recently changed their TOS and this service now incurs into costs for teams above a threshold.
Use MicroMamba instead.
-
Vashi Nedomansky – Shooting ratios of feature films
In the Golden Age of Hollywood (1930-1959), a 10:1 shooting ratio was the norm—a 90-minute film meant about 15 hours of footage. Directors like Alfred Hitchcock famously kept it tight with a 3:1 ratio, giving studios little wiggle room in the edit.
Fast forward to today: the digital era has sent shooting ratios skyrocketing. Affordable cameras roll endlessly, capturing multiple takes, resets, and everything in between. Gone are the disciplined “Action to Cut” days of film.https://en.wikipedia.org/wiki/Shooting_ratio
-
General OCR Theory – Towards OCR-2.0 via a Unified End-to-end Model – HF Transformers implementation
https://huggingface.co/stepfun-ai/GOT-OCR-2.0-hf
GOT-OCR2 works on a wide range of tasks, including plain document OCR, scene text OCR, formatted document OCR, and even OCR for tables, charts, mathematical formulas, geometric shapes, molecular formulas and sheet music.
-
QNTM – Developer Philosophy
- Avoid, at all costs, arriving at a scenario where the ground-up rewrite starts to look attractive
- Aim to be 90% done in 50% of the available time
- Automate good practice
- Think about pathological data
- There is usually a simpler way to write it
- Write code to be testable
- It is insufficient for code to be provably correct; it should be obviously, visibly, trivially correct
-
Arminas Valunas – “Coca-Cola: Wherever you are.”
Arminas created this using Juggernaut Xl model and QR Code Monster SDXL ControlNet.
His pipeline:
Static Images – Forge UI.
Upscaled with Leonardo AI universal upscaler.
Animated with Runway ML and Minimax.
Video upscale – Topaz Video AI.
Composited in Adobe Premiere.
Juggernaut Xl download here:
https://civitai.com/models/133005/juggernaut-xl
QR Code Monster SDXL:
https://civitai.com/models/197247?modelVersionId=221829
FEATURED POSTS
-
Black Body color aka the Planckian Locus curve for white point eye perception
http://en.wikipedia.org/wiki/Black-body_radiation
Black-body radiation is the type of electromagnetic radiation within or surrounding a body in thermodynamic equilibrium with its environment, or emitted by a black body (an opaque and non-reflective body) held at constant, uniform temperature. The radiation has a specific spectrum and intensity that depends only on the temperature of the body.
A black-body at room temperature appears black, as most of the energy it radiates is infra-red and cannot be perceived by the human eye. At higher temperatures, black bodies glow with increasing intensity and colors that range from dull red to blindingly brilliant blue-white as the temperature increases.
(more…)
-
Types of AI Explained in a few Minutes – AI Glossary
1️⃣ 𝗔𝗿𝘁𝗶𝗳𝗶𝗰𝗶𝗮𝗹 𝗜𝗻𝘁𝗲𝗹𝗹𝗶𝗴𝗲𝗻𝗰𝗲 (𝗔𝗜) – The broadest category, covering automation, reasoning, and decision-making. Early AI was rule-based, but today, it’s mainly data-driven.
2️⃣ 𝗠𝗮𝗰𝗵𝗶𝗻𝗲 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 (𝗠𝗟) – AI that learns patterns from data without explicit programming. Includes decision trees, clustering, and regression models.
3️⃣ 𝗡𝗲𝘂𝗿𝗮𝗹 𝗡𝗲𝘁𝘄𝗼𝗿𝗸𝘀 (𝗡𝗡) – A subset of ML, inspired by the human brain, designed for pattern recognition and feature extraction.
4️⃣ 𝗗𝗲𝗲𝗽 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 (𝗗𝗟) – Multi-layered neural networks that drives a lot of modern AI advancements, for example enabling image recognition, speech processing, and more.
5️⃣ 𝗧𝗿𝗮𝗻𝘀𝗳𝗼𝗿𝗺𝗲𝗿𝘀 – A revolutionary deep learning architecture introduced by Google in 2017 that allows models to understand and generate language efficiently.
6️⃣ 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝘃𝗲 𝗔𝗜 (𝗚𝗲𝗻𝗔𝗜) – AI that doesn’t just analyze data—it creates. From text and images to music and code, this layer powers today’s most advanced AI models.
7️⃣ 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝘃𝗲 𝗣𝗿𝗲-𝗧𝗿𝗮𝗶𝗻𝗲𝗱 𝗧𝗿𝗮𝗻𝘀𝗳𝗼𝗿𝗺𝗲𝗿𝘀 (𝗚𝗣𝗧) – A specific subset of Generative AI that uses transformers for text generation.
8️⃣ 𝗟𝗮𝗿𝗴𝗲 𝗟𝗮𝗻𝗴𝘂𝗮𝗴𝗲 𝗠𝗼𝗱𝗲𝗹𝘀 (𝗟𝗟𝗠) – Massive AI models trained on extensive datasets to understand and generate human-like language.
9️⃣ 𝗚𝗣𝗧-4 – One of the most advanced LLMs, built on transformer architecture, trained on vast datasets to generate human-like responses.
🔟 𝗖𝗵𝗮𝘁𝗚𝗣𝗧 – A specific application of GPT-4, optimized for conversational AI and interactive use.
-
Disney’s Moana Island Scene – Free data set
https://www.disneyanimation.com/resources/moana-island-scene/
This data set contains everything necessary to render a version of the Motunui island featured in the 2016 film Moana.
