Hyper3D Rodin is built for generating, editing, and refining... 3D assets. Most segmentation tools leave rough edges, broken parts, and extra cleanup before the model is usable. Bang to Parts understands the object first, then turns one complete model into clean, editable components.show more

💥🍌3D Nano Banana just dropped! ✨We just launched #Rodin... Gen-2 "Edit", upload ANY model and edit like magic: 1️⃣ Smart Low-poly → artist-style topology 2️⃣ Local edits via prompt (Beta) 3️⃣ BANG to Parts 4️⃣+ more #Hyper3D is now the FIRST true #3D GenAI editing platform! 🚀show more

The 3D drops keep coming 💥 Rodin Hyper3D Bang!... is live on Scenario. It takes a finished 3D mesh, breaks it into separate, semantically meaningful parts, and re-derives fresh materials for each one in a single pass.show more

A single image. An entire 3D world. And every... important object is editable. Hyper3D WorldGen turns a single scene image into a structured 3D environment with: - Independent assets - Spatial relationships - Physical properties - The freedom to move, replace, refine, and interact with them This is scene-level 3D generation. 🧵👇show more

Today we're releasing the Segment Anything Model (SAM) —... a step toward the first foundation model for image segmentation. SAM is capable of one-click segmentation of any object from any photo or video + zero-shot transfer to other segmentation tasks ➡️show more

Motel metal casting turns scrap into clean parts with... simple tools.show more

Most 3DGS segmentation tools either pre‑train per scene or... lock errors into a feature field you can’t undo. ArtisanGS instead turns a few 2D masks into editable 3D object selections via Cutie tracking + black‑box splat aggregation, then lets you iteratively correct mistakes with consistent 2D/3D selection modes. 📗 #NVIDIAResearch paper:show more

Another big drop from Hunyuan3D by Tencent. Hunyuan3D-Buffalo 1.0... is not just another text-to-3D model. The more interesting part is its approach to 3D understanding and editing. It can understand separate parts of a complete asset, extract them, remove or replace them with prompts, and edit only the selected region while keeping the rest of the geometry unchanged. That feels like a much more useful direction for 3D AI in general: not just generating a mesh once, but actually understanding its structure and letting you continue working with it. The model combines Qwen-VL, TRELLIS and Hunyuan3D, and was trained on an impressive dataset of 87 million 3D samples. Source:show more

🚨 Dreamina Seedance 2.5 is coming soon to the... Dreamina platform. ByteDance’s latest AI video model is designed to take AI filmmaking beyond short clips and into more complete, controllable production workflows. Here’s what to expect: 🎬 Up to 50 multimodal reference assets in one generation — including images, videos, and audio ⏱️ Up to 30 seconds of continuous video generation for longer, more coherent storytelling 🎥 Support for 3D white models and green-screen references for greater control over movement and composition 🌍 Multilingual creation with support for multiple languages ✂️ Precise local editing for refining specific parts of a video without regenerating everything Dreamina Seedance 2.5 is coming soon. Until then, start creating with Dreamina Seedance 2.0 and get ready for the next upgrade. 👉 #dreamina #dreaminapartner #seedance #dreaminaseedance25show more

BANG is a #3D model part-splitting tool designed for... artists 🎨✨. That’s why “Controllable” is our first core principle: artists can divide parts with BBox, Surface Points, or even text prompts. Unleash your creative control with #BANG! 🚀show more

Every AI video creator has that one clip they... gave up on because the model just refused to place the character right. Topview 3D Shot Composer is the fix. You stage the shot in 3D before generating, so the composition is locked before the model touches it. TopviewAI shipped something real.show more

Here is the second outfit of our customizable 3D... vtuber model! <3 The model will launch in 5 days! -^u^- Now that most of the coding is done, we can focus on making more assets for the model like ears, tails, wings, and accessories! 🩷show more

🚨 This changes how 3D worlds get made. Upload... a single image, and Hyper3D WorldGen transforms the scene into an immersive, editable 3D world. The important objects don’t just become part of the environment — they become independent 3D assets you can edit and manipulate. ✨show more

Is ultra detailed geometry the biggest upgrade in #Hyper3D... Rodin Gen-2.5? No — not even close. 🔥 There’s something way more impactful for text/image-to-3D. Waitlist opens today 🚀 Reply and I’ll catch you up 👇 #Rodin #3D #CG #gamingshow more

3D to Video is now live on H3 Max,... the fastest video model on the market and ranked #1 for video editing. Upload a Blender previs up to 15 seconds, and H3 Max turns it into photoreal video while preserving camera movement and shot timing. Add reference images to carry specific characters and environments into the final shot.show more

What if a SINGLE IMAGE could become a fully... editable 3D WORLD? 🤯 I tried Hyper3D WorldGen, and honestly… I wasn’t expecting this. It didn’t just look at the image and turn it into a 3D object. It actually figured out what was happening in the scene — where the objects were, how they were positioned, and how everything fit together — then rebuilt the whole thing as a 3D world. And this is where it gets REALLY interesting. The objects you actually want to work with become individual 3D assets, while the surrounding environment keeps its detail through 3D Gaussian Splatting. So instead of getting one giant 3D model that you can barely do anything with… You get a whole scene that you can actually mess around with. 👇show more

The new model Extract Object by Bria is now... live on fal! - Isolates any object from an image with a single API call - Turns a natural-language prompt into a clean RGBA-PNG cutout - Outputs composite-ready results with no masks or manual editing requiredshow more

3D #VTuber Model footwear details 🐊💚 The way the... gold reacts to the camera angle might be one of my favorite parts honestly ✨show more

The gap between generating video and actually shipping it... has been the whole problem with AI video. Seedance 2.0 is the first model built around closing that gap.show more

2025 is year of 3D AI Rodin AI 1.5... now can not only generate 3D model with clean meshes but also create high quality textures You can export all the models to 3D software to create a new worldshow more

it starts with a simple clay model, then things... get interesting turns out GPT-6 Astra + Dreamina Seedance 2.5 is an actual pipeline Astra codes the geometry → Blender → Clay Renderer Plugin → final render on Dreamina the Dreamina Clay Renderer Plugin takes the Blender clay model directly into Dreamina in one click. The camera and layout stay locked, so there’s no need to rebuild the shot before rendering with Seedance 2.5 and you get the same Seedance model and quality without paying extra just for the pipeline ready to try it? 👇 #Dreamina #DreaminaPartnershow more