Hohastudios

@OP__Nico Looks like it’s using google’s mediapipe behind the scenes, codex just built the UI around it

As promised: Animateur is now public! It's a work in progress vibe-animating editor that hopefully will rock the gamedev world. This is a flight anim taken from the Superman Movie intro! You can animate manually, ask codex to make changes or rip animation off of YT videos (in that case I recomment using full body videos and put the playback speed to at least a half). Other than that is already featuring some animations I did manually or with the help of Codex. Codex is AUTOMATICALLY trained on this, animations are by default in JSON, so it understands them really well. Alternatively, you can expor in .glb format. It also features a playground to play with your animations. There are sooo many features like saving poses, exporting them, saving animations, exporting them, keyframes time editor, inverse Kinematics and SO, SO many new ones coming. I am making this public for all those like me that want to do simple animations but find every single software out there just TOO complex for no reason. This is the simplest I could do. Open the Index File (it's literally an HTML file lol. It doesn't require ANY type of installation. So u can download the repo and start playing with it :) Please contribute adding code, animations or whatever you prefer :) With the help of everyone, we can solve vibe-animating all togheter! P.S: I am not a programmer, nor know how to code, so please excuse if it lacks structure or any sort of professionalism :) P.P.S: The editor is also SUPER young and rough around the edges, it was made in 4h so far, so be patient and understanding please, I am just making it available super early so that we can start evolving it toghether :) @levelsio @threejs this could really help people doing the vibejam with animations! If you guys could repost it it would mean the world to me (and hopefully to people eventually using or contributing to it :) Here's the repo: github.com/ilatroce/Anima…

So now you can even rip anims off of YT videos or any other video lol! Rip poses, animations and export them to re-use or to mix an' edit! All done in a browser, no installs! @alightinastorm this is going to speed up anims even more!

@OP__Nico @alightinastorm Awesome stuff!

🪄 Introducing daVinci-MagiHuman: The Performance-Level Audio-Video Generative Foundation Model Proudly open-sourced and jointly developed by SII GAIR Lab & Sand.ai, it sets a new standard for multimodal AI. ⏳ 1/6

@deepbeepmeep Will it off load vram from the agent when video generation happens?

Meet Deepy your friendly WanGP v11 Agent. It works offline with as little of 8 GB of VRAM and won't divulge your secrets. It is 100% free (no need for a ChatGPT/Claude subscription). You can ask Deepy to perform for you tedious tasks such as: Generate a black frame, crop a video, extract a specific frame from a video, trim an audio, ... Deepy can also perform full workflows including multiple models (LTX-2.3, Wan, Qwen3 TTS, ...). For instance: 1) Generate an image of a robot disco dancing on top of a horse in a nightclub. 2) Now edit the image so the setting stays the same, but the robot has gotten off the horse and the horse is standing next to the robot. 3) Verify that the edited image matches the description; if it does not, generate another one. 4) Generate a transition between the two images. or Create a high quality image portrait that you think represents you best in your favorite setting. Then create an audio sample in which you will introduce the users to your capabilities. When done generate a video based on these two files. github.com/deepbeepmeep/W…

Announcing NVIDIA DLSS 5, an AI-powered breakthrough in visual fidelity for games, coming this fall. DLSS 5 infuses pixels with photorealistic lighting and materials, bridging the gap between rendering and reality. Learn More → nvidia.com/en-us/geforce/…

🌍Tencent HY 3D Studio is now live globally. An AI-powered workspace for professional 3D production pipelines. 🧱Image → 3D → topology → UVs → texturing → rigging → animation All in one workflow. Built for creators, game developers, and 3D artists. 🕹️ Try it: 3d.hunyuanglobal.com/studio New users get 20 free generations daily (limited-time). ⚙️ API access: tencentcloud.com/products/ai3d New developers receive 200 free credits to get started.

😂

Ucupaint 2.4.5 is now available! Normal preview mode now has a space option to help you paint custom normals, along with many bugfixes! 🎨 #b3d #ucupaint github.com/ucupumar/ucupa…

3 years of AI progress

LTX-2.3 is a major upgrade. It’s a production-ready multimodal engine - designed to be built on. Here’s what’s new 🧵 1/7

Step inside Project Genie: our experimental research prototype that lets you create, edit, and explore virtual worlds. 🌎

I'm definitely trying this.. google just made your pet a playable character

@bobs_ter @deepbeepmeep

@bobs_ter @deepbeepmeep It works well for me

LTX 2 just landed in WanGP 10 Low VRAM as usual: with 10GB of VRAM you can generate 10s. If you have a RTX 4090, get ready for 20s at 720p in 2 minutes using the distilled model. github.com/deepbeepmeep/W…

Find out about everything arriving in the free Procreate Dreams 2 update, available now. Head to our YouTube channel for the full video. #ProcreateDreams #Procreate

bro packaged math and programming into a game and 1000s of people are playing it on steam. this looks so cool 🤯

context-aware css card glow/shine effect 👨‍🍳 the trick: duplicate and scale the icon. translate it on pointermove. apply feGaussianBlur 🤙 check it 👇