I launched rentahuman.ai last night and already 130+ people have signed up including an OF model (lmao) and the CEO of an AI startup. If your AI agent wants to rent a person to do an IRL task for them its as simple as one MCP call.

Another dark tactic higgsfield uses it throttling the app the moment you convert. They aggressively promote an "unlimited" annual plan (which is another scam) then the moment you convert, everything starts breaking. Once they have your money, they don't want you using the app.

It’s time to remind you that this Cloud Shader is completely FREE to download ☁️ Just received my 2025 Gumroad report and I’m honestly blown away… 15K views and nearly 4K unique downloads. Thank you all for the support ! 🙏 #b3d

Según Gemini está es su representación de mi: Esta imagen es una representación conceptual y abstracta de tu identidad digital y profesional. Al no generar un retrato fotorealista, busqué capturar la esencia de lo que haces y cómo interactúas con la tecnología. Aquí tienes el

I like the tools on Higgsfield. But, just so you know, generating anything there with Kling 3.0 takes FOREVER on their platform right now (which will eventually change as it goes to full release), and it doesn’t have all the functionality of Kling on their own platform.

Seedance V2: here is another great example.

This is crazy! With LTX 2 in ComfyUI i was able to keep my original camera movement + it did a full lip-sync on the singing haha. All running locally. I made the original video back in 2021 when Metahumans first came out and we were working in Unreal Engine 4. This music video

Anime fans are not sleeping for the next few days. 🌀🤯🔥

Prediction: In the AI age, taste will become even more important. When anyone can make anything, the big differentiator is what you choose to make. paulgraham.com/taste.html

Art Director, Jieyi Lee, reimagines reality — turning raw footage into a cinematic experience with Ray3.14 Modify in Dream Machine by Luma AI. See how every scene is transformed. Jieyi Lee

Generate vectorized images directly from a text prompt — no raster intermediate. Output clean vector illustrations in SVG. Open in Illustrator, Figma, and Sketch.

We are releasing the final version of Quixel Mixer as a free, unsupported, offline application. You can download this version by logging in to your account on the Quixel website. More details here: 👉 epic.gm/quixel-mixer-n…

El vídeo que me manda mí vieja preguntando si es real

Gemini 3.1 + Claude 4.6 seems like a dangerous combo. a dev built a geospatial tracking system with live planes, satellites traffic cams, and panoptic detection. this is literally a CIA tool lmao. i guess this is what happens when AI gets too good.

using the sref from OscarAI + grok imagine with no cherry pick, first output. Grok keeps style so well now.

another good example of grok video!, no prompt, just auto generate... really good for fast iteration.

1.5 billion creations later, @FlowByGoogle is getting its biggest upgrade yet. We've redesigned Flow to make it even better for your creative workflows, putting image generation front and center. Now you can generate, edit, and animate seamlessly, letting images and videos work

WIP version is up for anyone who wants to mess with the catan-like game I've been tinkering with. I'd love to hear some feedback on the play mechanics and costs specifically (from people who try playing it, if you don't try playing it your feedback isn't worth much 😂)

Most GenAI workflows were built for screens. Moment Factory needed one built for buildings. They used ComfyUI to pre-map outputs to architectural surfaces with spatial logic enforced from day one. As result: ✦ Concept work moved from days to hours ✦ Over 20 directions

Nano Banana 2 is here. Our latest image model gives you the power of Pro at the speed of Flash. You can create images with real-world accuracy, add text in many languages, and bring your wildest ideas to life faster with vibrant lighting, richer textures and sharper details. 🧵