English

Posts with #generative

#generative

Public posts on X that use #generative.

  1. Sundar Pichai✓@sundarpichai
    Excited to share Genie 4 today our most realistic and interactive world model: - steer dynamic environments in real time, shaping events, camera angles, and actions - generate native audio matched to the world, from realistic background sounds to characters who can converse in real time! - simulate photorealistic scenes and real-world physics - create more coherent multi-step events through reasoning from Gemini We've started to roll out as a research preview to trusted testers. Coming soon to Google AI Ultra subscribers in Project Genie and early access partners via the Gemini API and AI Studio.
    Download
    8181.4K17.6K1.6M
  2. 🚨 AI News | TestingCatalog✓@testingcatalog
    GOOGLE 🔥: Genie 4 has been officially announced! Genie 4 is Google's latest World Model, with advanced realism and interactivity! Users can now prompt changes to the world dynamically and generate worlds with native audio. It is rolling out to Trusted Testers as a research preview and will soon come to Google AI Ultra subscribers and early access partners via the Gemini API and AI Studio. A sample from @sundarpichai
    Download
    Google DeepMind @GoogleDeepMind
    This is Genie 4, our most realistic and interactive world model yet. 🌐 Explore dynamic environments in real time to see how the scene responds, sounds, and how the people in it move, react, and speak.
    396089657.6K
  3. Google DeepMind@GoogleDeepMind
    This is Genie 4, our most realistic and interactive world model yet. 🌐 Explore dynamic environments in real time to see how the scene responds, sounds, and how the people in it move, react, and speak.
    Download
    8962.4K22K3M
  4. BytePlus✓@BytePlusGlobal
    Meet Seedance 2.5 4K. 🎬 The most capable model in the Seedance 2.5 generation brings more nuanced facial expressions and movements, alongside richer visual detail. With Draft mode, creators can test storyboards and refine shots using lower-cost 480p previews, then generate the final version in 4K once they’re happy with the result. Currently available to selected enterprise customers. Stay tuned for updates on API availability. Watch its screen debut in “Otter is Nobody 2” below.
    Download
    8087940103K
  5. ComfyUI✓@ComfyUI
    Flux 3 Max is now available in ComfyUI Generate a 10-second, 720/768p video in ~12 seconds. Click the link below to run the workflows ⬇️
    Download
    192339929.1K
  6. Atai Barkai✓@ataiiam
    🎉 Introducing OpenDuet Self-hostable, proactive AI agents that you own and works with ANY agent harness. Includes: - Build, generate, and edit live assets - Human-in-the-loop approvals - Computer use - Mobile, Web, and Channels Repo → Powered by @CopilotKit and AG-UI. Clone this template and customize it however you want. Enterprise-ready.
    Download
    Claude @claudeai
    We’re opening a research preview of Claude Duet, a new app where Claude works as a proactive agent. It comes to you with what needs your attention, completes tasks you ask of it, keeps working when you step away, and checks with you before it acts on your behalf.
    1312883.3K341K
  7. Claude✓@claudeai
    We’re opening a research preview of Claude Duet, a new app where Claude works as a proactive agent. It comes to you with what needs your attention, completes tasks you ask of it, keeps working when you step away, and checks with you before it acts on your behalf.
    Download
    2.4K4.3K55.4K11.2M
  8. Grok Imagine✓@imagine
    Our Prompting Guide is live. We're building the Odyssey episodes in public with a small crew of creatives. Learn from our workflows!
    1272351.8K718K
  9. ollama✓@ollama
    Meet Flint from @Recursive_SI! A ~40B parameter MoE open model for fast, accurate agentic coding use case made to run on-device. Flint can generate >125 tps on a M4 Pro Macbook Pro and >150 tps on a 64GB NVIDIA RTX Spark on short contexts. Try it on Ollama today: ollama run flint Claude Code: ollama launch claude --model flint
    Richard Socher @RichardSocher
    Introducing Flint, @Recursive_SI’s first model: a fast local coding model built with our automated research system, the Eureka Machine. • Best-in-class fast local coding • Up to 2x faster than comparable models: 125+ tokens/sec on a MacBook Pro, 150+ on RTX Spark • Built from scratch in under 4 months Private, unmetered intelligence on your own machine. Open weights available now on @huggingface, run it locally on your favorite framework or try it for free on @opencode or @pidotdev.
    593651739.5K
  10. Richard Socher✓@RichardSocher
    Introducing Flint, @Recursive_SI’s first model: a fast local coding model built with our automated research system, the Eureka Machine. • Best-in-class fast local coding • Up to 2x faster than comparable models: 125+ tokens/sec on a MacBook Pro, 150+ on RTX Spark • Built from scratch in under 4 months Private, unmetered intelligence on your own machine. Open weights available now on @huggingface, run it locally on your favorite framework or try it for free on @opencode or @pidotdev.
    Download
    6388938.4K3.4M
  11. Fokki✓@0x_fokki
    IF YOU'RE DRAFTING SEEDANCE 2.5 AT 720P, YOU'RE BURNING MONEY. I ran the exact same prompt twice. Once at 720p. Once at 480p, then upscaled to 4K. > "a guy in a football jersey walks up to a fisheye lens and throws a punch at it." I expected the 480p version to look like a 2009 webcam. Then I put both renders side by side and the 4K one came out cheaper. That killed my 720p habit in one afternoon. > every draft starts at 480p, the motion is basically identical > reroll there until the take actually works > upscale the winner once with Creative Upscale, right in Dreamina's Generate tab > native 4K needs a whitelist, Creative Upscale doesn't The 15 seconds above cost me one 480p draft and one upscale. The whole setup runs on a $0.29/month Dreamina plan I bought to test this and forgot to cancel. Same prompt. Same motion. Completely different credit bill. I wasn't paying for better motion. I was paying for more pixels on drafts I was going to delete anyway.
    Download
    21133771
  12. Peng✓@pengsonal
    FOUND 700+ AI VIDEO PROMPTS YOU CAN STEAL 🤯 this GitHub repo collects viral animations made with Claude Opus 5.5 you get prompts for: - cinematic motion graphics - stunning 3D scenes - animated explainers - interactive games just copy a prompt, give it to Opus 5.5, and let it generate the code some even have live remakes you can compare side by side perfect for creators who want to make better visuals without starting from scratch link:
    Download
    125635829.6K
  13. Philipp Schmid✓@_philschmid
    We launched the Gemini API CLI. A CLI for calling the Gemini API. Give it to the agent you already use (Claude Code, Codex, Antigravity, Cursor, OpenClaw, Hermes...). It's NOT a new coding agent you can use it too: 1. Generate images, video, speech, music. 2. Analyze PDFs, images, audio, video, YouTube URLs, 3. Transcribe recordings to md / json / srt, 4. Run Deep Research in the background. Stateless. No memory, no chat mode. Your agent owns the context and the plan, gemini-api does the API call. Build for Agents, it's self-describing. `--help`, `--dry-run`... Start here:
    Download
    2071601.8K213K
  14. Ideogram@ideogram_ai
    Today, we’re introducing Ideogram's first vector model. Generate clean, editable SVGs with smooth gradients and sharp typography from a text prompt, or turn any image into a detailed, scalable vector. Live in Ideogram and the API:
    Download
    2903341.8K579K
  15. Matt Workman✓@mattworkman
    GPT 6.1 Terra (Ultra) is INSANELY good at 3D Blender computer use *only used 3% of my Pro 200 plan > Codex + fal plugin > generate an image of the roadster > Blender 3D model the car and animate the camera move > GPT 2.5 CG first frame to photo real > Seedance 2.5 ref to video 3D video to photo real video
    Download
    OpenAI @OpenAI
    GPT-6.1 Terra: delivering fast and capable computer use at a lower price. GPT-6.1 Terra understands what’s on screen, takes action across apps, writes naturally, and is a more capable model for your whole workday with the efficiency to take on more of it.
    474962365.4K
  16. OpenAI✓@OpenAI
    GPT-6.1 Terra: delivering fast and capable computer use at a lower price. GPT-6.1 Terra understands what’s on screen, takes action across apps, writes naturally, and is a more capable model for your whole workday with the efficiency to take on more of it.
    Download
    1.7K2.5K27.8K6.3M
  17. Codio✓@0xCodio
    A university lab had an LLM build 3D molecules and only kept the ones the model itself couldn't explain Most generative chemistry rewards confidence, which means the output is a very expensive average of the training set. They inverted the filter, the model builds the structure and then has to justify why it works, and the ones it can't justify are the only ones that go forward: > Generate: structures are built against the target property as usual > Explain: the model writes the mechanism it believes makes each one work > Score: a confident, familiar explanation sends the candidate to the discard pile > Keep: anything it builds but cannot account for goes to the bench • Why the unexplainable ones are the valuable ones > A structure the model can explain is one the literature already implies > Novelty lives exactly where the learned pattern stops predicting > The explanation is a proxy for how crowded that chemical space already is • What came out of the first run > Four scaffolds with no close analog in any published series > One binding mode the model described as unlikely and the assay confirmed > A discard pile full of compounds three other groups were already patenting • Where this breaks if you're careless > Unexplainable also describes garbage, so synthesis screening runs first > Every keeper has to survive the same physical validity checks > A candidate with no route to the bench is dropped regardless of novelty One generate-and-filter cycle produces about 30 keepers from 400,000 builds. And the part that broke my brain: Every other pipeline ranks candidates by how sure the model is about them. This lab reads that same confidence as proof somebody already got there. Same model. One version optimises for the middle of what's known. The hard part was never generating molecules. It was noticing that the confident ones are the crowded ones ↓
    Download
    Codio @0xCodio
    142821910.7K
  18. Codio✓@0xCodio
    1830499759K
  19. rewind✓@rewind02
    with no coding background built a game in 6 weeks with claude opus 5.5 + godot... there’s a smart way to set it up: - step 1: run opus 5.5 in claude code inside your godot project - step 2: build one feature, test it in the game, adjust until it feels right, then start the next - step 3: generate reference images in your game’s style with codex/astra - step 4: save every image prompt that works as json, and use them to guide the next generations so the style doesn’t drift - step 5: make the big 3d assets in tripo p2 from those references - step 6: model the small props in blender, then texture them in tripo with matching refs (cheaper) - step 7: animate in cascadeur - step 8: document every vfx and shader in obsidian so the look stays consistent who does what: > opus 5.5: most of the code > codex/astra: references and assets > tripo p2: the big 3d models > godot: custom tools, headless scripts, the game one json file of good prompts is why every character, monster and prop looks like it belongs in the same game (dev: afterthewinddev)
    Download
    rewind @rewind02
    one concept art image into a real 3d level with claude opus 5.5 + godot... opus “churned for 33m 5s” the trick is scoring the render against the reference instead of eyeballing it, smart way to set it up: - step 1: pick one reference image as the target look - step 2: have opus generate the level in code from a seed (rust + godot 4.7) - step 3: build everything from small pieces: single stones, mixed flagstones, single planks, chains - step 4: skip textures: stone, wood, brass, cloth and flame are all procedural shaders - step 5: have opus write a script that compares the render with the reference (color, light, contrast, detail) and gives a 0-100 score - step 6: fix the scene first: lighting, haze, layout - step 7: auto-fit a color grade (lut) to the reference as the final step - step 8: loop: render > score > side-by-side > change one thing i like this way more than image gen > 3d model > cleanup one generator instead of 100 assets, and no generation credits burned
    607394756K
  20. rewind✓@rewind02
    one concept art image into a real 3d level with claude opus 5.5 + godot... opus “churned for 33m 5s” the trick is scoring the render against the reference instead of eyeballing it, smart way to set it up: - step 1: pick one reference image as the target look - step 2: have opus generate the level in code from a seed (rust + godot 4.7) - step 3: build everything from small pieces: single stones, mixed flagstones, single planks, chains - step 4: skip textures: stone, wood, brass, cloth and flame are all procedural shaders - step 5: have opus write a script that compares the render with the reference (color, light, contrast, detail) and gives a 0-100 score - step 6: fix the scene first: lighting, haze, layout - step 7: auto-fit a color grade (lut) to the reference as the final step - step 8: loop: render > score > side-by-side > change one thing i like this way more than image gen > 3d model > cleanup one generator instead of 100 assets, and no generation credits burned
    Download
    191634759.8K
  21. Sai✓@sai0xgen
    NVIDIA just open-sourced an AI that can generate character movements at insane speeds 👀 it's called MotionBricks, and it can generate motion at 15,000 FPS with just 2ms latency. basically, give it a character's recent poses and where you want it to go next, and it fills in the movement between them. here's what makes it interesting: > one model trained on 350K+ motion clips > Smart Primitives for navigation and object interaction without retraining > human character weights via SOMA > Unitree G1 humanoid robot weights > code under Apache 2.0, weights under NVIDIA's Open Model Agreement the goal is smoother, real-time movement for game characters and humanoid robots.
    Download
    192633918.5K
  22. Dmitry Lyalin✓@LyalinDotCom
    Introducing Gemini API CLI (gemini-api), now available in preview! Our CLI gives your agent power to generate images, videos, text-to-speech, or music, analyze media, transcribe audio, or manage agents. No more guessing model strings, throwaway scripts or endless curl. 🧵 👇
    Download
    1471511.9K265K
  23. Jessica AI✓@AkterBrist39045
    1. (write anything) 2. (create presentations) 3. (generate images with text) 4. (create AI art) 5. (generate realistic voices) 6. (create AI videos) 7. (generate stunning visuals) 8. (turn ideas into visuals) 9. (code with AI) 10. (build websites with AI) 11. (build apps with AI) 12. (create slides in minutes) 13. (remove background noise) 14. (transcribe meetings) 15. (turn ideas into presentations) 16. (design vector graphics) 17. (create AI music) 18. (create product photos) 19. (generate AI videos) 20. (turn ideas into songs) Save this list 🔖 + Follow me for more AI tools! 🚀
    Download
    2911328811.1K
  24. Krea✓@krea_ai
    introducing Krea for Grok bot. generate images and video with the best models in the world, right from Grok. try it now 👇
    Download
    2101212.3K222K
  25. Anatoli Kopadze✓@AnatoliKopadze
    RIP to everyone who spent years learning 3D in Blender 💀 Hi3D just released an open-source model that turns any object from a photo into a full 3D model. It's trained on 2 million 3D assets, and in their technical report 90% of its models pass 3D-print slicing. Just generate the base from a photo, refine the details with Opus 5.5 and you're done. The barrier to 3D just disappeared, you can find more details in the article below:
    Download
    Hi3D @Hi3D_AI
    1092752.9K201K
  26. Hi3D✓@Hi3D_AI
    1454476299K
  27. Felicia✓@heyliccia
    this is f**king insane. this 23 year old used Claude to reverse engineer a kids channel with 28.5M subscribers. then reportedly made $10K from YouTube Shorts. he didn't copy individual videos. he studied the formula behind them: → recurring characters 
→ simple stories 
→ bright visuals 
→ fast pacing 
→ formats already proven to generate massive views then he built an AI production engine around those patterns. Claude analyzes the channel, identifies repeatable ideas, and writes original scripts. connected AI tools handle the rest: → characters
→ voices
→ music
→ animation
→ final assembly his involvement? almost nothing. he chooses the direction, approves the strongest concepts, and lets the system handle the repetitive production. one prompt → one finished Short. and because the workflow is reusable, he can keep producing without rebuilding everything from scratch. the original channel reached 28.5M subscribers across 798 uploads. he didn't copy one cartoon. he reverse engineered the machine that could produce an entire channel. that's the real AI advantage.
    Download
    RUX @0xrux
    271681.3K80.6K
  28. RUX✓@0xrux
    702341.6K7.3M
  29. Show more posts