BeyondTodAI @BeyondTodAI

Testing OpenAI’s GPT-4o Image gen. A vivid series of character-driven portraits capturing intense, exaggerated emotions—horror, joy, grief, rage, confusion, and arrogance—each infused with surreal or symbolic elements. Pretty good expressions imo 👌

keyboard_arrow_left Previous keyboard_arrow_right Next

Chinese ByteDance just announced OmniHuman. This AI can make a single image talk, sing, and rap expressively with gestures from audio or video input. 10 wild examples: 1.

#veo2 excels at generating videos that feel remarkably "real". Dynamic living backgrounds + fluid motion + finely rendered details in faces, hands, and bodies, that creates truly natural looking videos. Here is some videos with "mundane life" as prompt. no cherry picking. #veo

20+ labs just worked together to open source Genesis - a physics engine with a VLM agent that turns text prompts into interactive 4D worlds Think instant physics-accurate environments, camera paths, and character animations - all from natural language 🤯

Very cool and creative (as a lot of what @tldraw has done over time), I love it. You lay out interactive and visual programs in 2D that incorporate LLM elements. "imagine a computer that runs on AI. No code, just natural language, infinite knowledge, and vibes"

tldraw @tldraw

2 years ago

We just launched tldraw computer

131 388 4K 1.2M 3K

It's over. Google Veo 2 just wiped out the competition and became the new king of the AI media world. No one can tell this is AI now. 10 wild examples:

Now we need longer videos. Consistency is getting there! Google’s Phenaki research was incredible for longer times. Add that & we’re golden! Kudos to the Google team 👏🏽

Google DeepMind @GoogleDeepMind

2 years ago

Today, we’re announcing Veo 2: our state-of-the-art video generation model which produces realistic, high-quality clips from text or image prompts. 🎥 We’re also releasing an improved version of our text-to-image model, Imagen 3 - available to use in ImageFX through

keyboard_arrow_left Previous keyboard_arrow_right Next

263 1K 7K 2.3M 2K

We’ve also enhanced Imagen 3’s ability to: ▪️ Produce diverse art styles: realism, fantasy, portraiture and more ▪️ More faithfully turn prompts into accurate images ▪️ Generate brighter, more compositionally balanced visuals → goo.gle/imagen-3-update

keyboard_arrow_left Previous keyboard_arrow_right Next

Today, we’re announcing Veo 2: our state-of-the-art video generation model which produces realistic, high-quality clips from text or image prompts. 🎥 We’re also releasing an improved version of our text-to-image model, Imagen 3 - available to use in ImageFX through @LabsDotGoogle. → goo.gle/veo-2-imagen-3

keyboard_arrow_left Previous keyboard_arrow_right Next

“I read a theory once that the human intellect was like peacock feathers. Just an extravagant display intended to attract a mate. All of art, literature, a bit of Mozart, William Shakespeare, Michelangelo, and the Empire State Building just an elaborate mating ritual. Maybe it doesn’t matter that we have accomplished so much for the basest of reasons. But, of course, the peacock can barely fly. It lives in the dirt, peeking insects out of the muck, consoling itself with its great beauty. I have come to think of so much of consciousness as a burden, a weight, and we have spared them that. Anxiety, self-loathing, guilt. The hosts are the ones who are free. Free here under my control.” -- Dr. Ford A new vibe of humanoid.

I’m going to say it This is a game changer!

Mochi 1 preview A new SOTA in open-source video generation. Apache 2.0

Runway Gen-3 Last Frame → Quality Addition It's nice to have this option. MJ Prompt Structure: Vivid, [shot type], Gourmet [food + ingredients], [colors + tones], [environment description], [texture details], [emotion], Bright, cheerful daylight --ar 16:9 --personalize [code] --stylize 175 --v 6.1 --q 2 MJ Prompt Example: Vivid, double overhand sandwich hold, Gourmet Fried Chicken Sandwich with pickles and special sauce, Vivid blue and warm sandwich tones, Urban eatery studio vibes, Crispy fried chicken, runny special sauce, Sunday fun-day indulgence, Bright, cheerful daylight --ar 16:9 --personalize [code] --stylize 175 --v 6.1 -q 2 RW Prompt Example: hand placing a piece of uncooked salmon on the left side of the image, 35mm style #runwaygen3 #runwayml #midjourney

🚀 Exciting News! 📷 We’re thrilled to announce our new AI Mentorship Program! 🔹Personalized Mentorship 🔹Extensive Curriculum 🔹 Real-World Projects & more Learn More 👉 beyondtodai.com/ai-mentorship-… #AI #AICareers #AICourse #GenAI #AInews

StoryDiffusion: Revolutionizing Image and Video Generation It is a project that uses a consistent self-attention mechanism to generate high-quality comics and videos. Its technology has far-reaching implications across industries, including entertainment, education, and more. Key FeaturesGenerates cohesive comics and videos. Maintains character consistency Ideal for cartoon character creation and educational content. Availability The project is available for exploration, but commercial use is not explicitly stated. However, its potential for commercial applications is evident, and licensing options may be available in the future. Features like duration, resolution, aspect ratio,... aren't clear. But seen this opens the door to new partners to play with. link: storydiffusion.github.io BTW Using Condition images from SORA 👇

When will every pixel be generated? Every 2 years AI systems can generate 10x more pixels. At this rate of progress we will have AI generated TV episodes by 2029 and movies by 2031.

Breaking news — gpt2-chatbots result is now out! gpt2-chatbots have just surged to the top, surpassing all the models by a significant gap (~50 Elo). It has become the strongest model ever in the Arena! With improvement across all boards, especially reasoning & coding capabilities, we're excited to see what app can build on top. Huge congrats to @OpenAI for this incredible milestone! Note: this is an internal screenshot. Its public version "gpt-4o" is now in Arena and will soon appear on the public leaderboard!