Stefan 3D AI's banner
Stefan 3D AI's profile picture

Stefan 3D AI

@Stefan_3D_AI • 15,321 subscribers

Stefan Vaskevich: 3D AI Explorer. Sharing my insights.

Shorts

Video In, Retargeted Mocap Out, All Running Locally Free Windows app by toyxyz: pick one of five AI mocap models, clean up the contacts on a timeline and put the motion on your humanoid character. Highlights: • Several people per video • Two or more synced cameras via MAMMA • Foot locking to stop sliding • Mixamo, VRM and PMX characters supported • MIT app code, research-only models GitHub:

Video In, Retargeted Mocap Out, All Running Locally Free Windows app by toyxyz: pick one of five AI mocap models, clean up the contacts on a timeline and put the motion on your humanoid character. Highlights: • Several people per video • Two or more synced cameras via MAMMA • Foot locking to stop sliding • Mixamo, VRM and PMX characters supported • MIT app code, research-only models GitHub:

22,911 просмотров

Video-to-3D Animation Just Leveled Up With This New AI Workflow The classic problem with animating animals from video: the AI mixes up the near and far legs. Give every leg its own color, and a believable walk comes out on the first try. Highlights: • 3D model from a single image with Tripo AI • Opus 5.5 rigs each leg and colors it • H3 generates the reference video • Opus keyframes the rig against the video • No mocap suit, no hand keyframing

Video-to-3D Animation Just Leveled Up With This New AI Workflow The classic problem with animating animals from video: the AI mixes up the near and far legs. Give every leg its own color, and a believable walk comes out on the first try. Highlights: • 3D model from a single image with Tripo AI • Opus 5.5 rigs each leg and colors it • H3 generates the reference video • Opus keyframes the rig against the video • No mocap suit, no hand keyframing

27,983 просмотров

Found old test I did with Opus 4.7 and tested with Opus 5.5. I left speechless. Difference between these two tests is only 5 months

Found old test I did with Opus 4.7 and tested with Opus 5.5. I left speechless. Difference between these two tests is only 5 months

23,035 просмотров

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:

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:

36,487 просмотров

I'm building my game with GPT-6, and color correction has become one of my favorite uses for it. When I generate assets separately, I can like each one on its own and still end up with a scene where the colors don't belong together. A castle looks fine in isolation, then turns greenish against the terrain. Its swords and shields disappear into the background. Getting those things to match used to mean a lot of repainting and trying different textures. Now I've built a workflow where GPT-6 takes screenshots in Unity, inspects the object's color textures, and helps bring them closer to the look I want. I can give it the terrain or tree textures as color references. It can prepare masks, send the relevant textures through Image Edit, then put the result back into the game for another look. Editors such as GPT Image 2 Edit or Nano Banana Edit can be part of that workflow. This is also why I keep pushing for properly prepared 3D models. If the parts are separated logically, you get much more control later. We could work on the swords and shields without changing the whole castle. The stone could stay dark while the equipment became easier to read. The latest pass on my game covered the overall post effects and the skeleton castles. We matched the castles to the surrounding terrain, adjusted the equipment colors, and added a subtle moving highlight. The first stronger color pass went too far. I asked for the accents to move about 30% closer to gray, and that got them where I wanted: visible, without pulling all the attention. I'm so happy with the difference. The video shows the before and after across the map and on the castles. Being able to give feedback on the actual scene and keep refining it this way feels great.

I'm building my game with GPT-6, and color correction has become one of my favorite uses for it. When I generate assets separately, I can like each one on its own and still end up with a scene where the colors don't belong together. A castle looks fine in isolation, then turns greenish against the terrain. Its swords and shields disappear into the background. Getting those things to match used to mean a lot of repainting and trying different textures. Now I've built a workflow where GPT-6 takes screenshots in Unity, inspects the object's color textures, and helps bring them closer to the look I want. I can give it the terrain or tree textures as color references. It can prepare masks, send the relevant textures through Image Edit, then put the result back into the game for another look. Editors such as GPT Image 2 Edit or Nano Banana Edit can be part of that workflow. This is also why I keep pushing for properly prepared 3D models. If the parts are separated logically, you get much more control later. We could work on the swords and shields without changing the whole castle. The stone could stay dark while the equipment became easier to read. The latest pass on my game covered the overall post effects and the skeleton castles. We matched the castles to the surrounding terrain, adjusted the equipment colors, and added a subtle moving highlight. The first stronger color pass went too far. I asked for the accents to move about 30% closer to gray, and that got them where I wanted: visible, without pulling all the attention. I'm so happy with the difference. The video shows the before and after across the map and on the castles. Being able to give feedback on the actual scene and keep refining it this way feels great.

17,351 просмотров

Who has best ride lol...

Who has best ride lol...

14,881 просмотров

Okay this is kinda wild 👀 NVIDIA is basically handing out FREE API keys to 100+ top AI models - GLM 5.2, DeepSeek V4, Kimi K2.6, MiniMax M3, their own Nemotron and a ton more. it's called NVIDIA NIM and I had no idea it existed. it's rate-limited, so not something you'd run in production - but for personal use it's honestly great. you can poke a dozen frontier models, and some you can even grab and self-host. dropped a key into OpenCode and it just worked. the hyped ones like GLM 5.2 are jammed with queue right now, but the lighter models fly. all of it free.

Okay this is kinda wild 👀 NVIDIA is basically handing out FREE API keys to 100+ top AI models - GLM 5.2, DeepSeek V4, Kimi K2.6, MiniMax M3, their own Nemotron and a ton more. it's called NVIDIA NIM and I had no idea it existed. it's rate-limited, so not something you'd run in production - but for personal use it's honestly great. you can poke a dozen frontier models, and some you can even grab and self-host. dropped a key into OpenCode and it just worked. the hyped ones like GLM 5.2 are jammed with queue right now, but the lighter models fly. all of it free.

26,272 просмотров

How far can a skilled 3D artist get with the right AI tools? I'm about to show you. Working on a video where I built Souls-like boss fight in a few days — the whole level, the boss, the player character, all in Unreal Engine 5. AI made the assets, I did the rest by hand. No one-shot magic. Dropping video soon guys, stay tuned. ⚡

How far can a skilled 3D artist get with the right AI tools? I'm about to show you. Working on a video where I built Souls-like boss fight in a few days — the whole level, the boss, the player character, all in Unreal Engine 5. AI made the assets, I did the rest by hand. No one-shot magic. Dropping video soon guys, stay tuned. ⚡

12,007 просмотров

Videos

Stefan_3D_AI's profile picture

Day 11. Building the game I've dreamed of for 15 years with AI. I thought humanoid animations would be the easy part. Then I spent half the night trying to get a skeleton to swing its arm. I wanted that awkward, broken skeleton movement. GPT-6 Astra couldn't get the attack right in Blender on its own, even though other parts were working. Time to bring in some of my own animation knowledge. Three things I tried: 1. Recorded myself doing the arm swing, turned the video into mocap, and gave that animation to Codex. I asked it to fix just the arm, keeping the parts that already worked. 2. Put my generated Seedance video references through mocap too. They converted surprisingly well. The free option I tried was Unreal Engine 5.8; Quick Magic was the paid one. Both gave me motion I could use. 3. Let the agent try Cascadeur through its MCP server. It set up AutoPosing and experimented with AutoPhysics. This part is still inconclusive for me. The MCP integration felt too limited to call it a reliable part of the workflow yet. GPT-6 took those mocap clips and assembled the final animations. About six or seven rounds, roughly half an hour each. Today I got the skeletons into the game, and I'm so happy with how they turned out. I'm already working on the archers. For difficult movements, I'll be using mocap references much more often now. GPT can take just an arm movement from a clip and adjust the rest itself. Being able to combine those two approaches is what finally got this working for me.

Stefan 3D AI

150,815 просмотров • 1 месяц назад