Stefan 3D AI's banner

Stefan 3D AI

@Stefan_3D_AI • 15,293 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:

22,493 views

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 views

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 views

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 views

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 views

Who has best ride lol...

Who has best ride lol...

14,881 views

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 views

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 views

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

Finally! Rigged hair cards from a single image. HairDeck (Tsinghua + CMU + CUHK) takes one character image and builds a stylized haircut as separate 3D hair cards, with bone chains already attached. The hair sways when the head turns. Exports to GLB, or straight onto a VRM avatar. Code and weights are open under Apache 2.0. You get geometry and UVs, no textures yet. Local run wants Linux and CUDA.

368,556 views • 2 days ago

This is what $2,175 of Opus 5.5 tokens can do! Let him cook on my gaming laptop and do whatever it takes, also gave Unity, Blender and APIs. 36 hours, 7.85 B tokens, $230 for 2d/3d/music generation and I got playable old school MMO RPG. That is just insane...

This is what $2,175 of Opus 5.5 tokens can do! Let him cook on my gaming laptop and do whatever it takes, also gave Unity, Blender and APIs. 36 hours, 7.85 B tokens, $230 for 2d/3d/music generation and I got playable old school MMO RPG. That is just insane...

1,569,815 views • 1 month ago

First Opus 5.5 vs GPT-6 Astra test is 3D. One prompt, Blender only, all procedural. Render the 10-second shot, and record your own build timelapse. Opus 5.5: 35 min, 199.6k output tokens, about $13.3 in API terms. GPT-6 Astra: 28 min, 56.6k output tokens, about $14.5 in API terms. Feels like a worthy rival, and honestly I am glad about that. From what I watched, Opus juggles way more at once and is faster overall. Astra is still good imo.

First Opus 5.5 vs GPT-6 Astra test is 3D. One prompt, Blender only, all procedural. Render the 10-second shot, and record your own build timelapse. Opus 5.5: 35 min, 199.6k output tokens, about $13.3 in API terms. GPT-6 Astra: 28 min, 56.6k output tokens, about $14.5 in API terms. Feels like a worthy rival, and honestly I am glad about that. From what I watched, Opus juggles way more at once and is faster overall. Astra is still good imo.

471,023 views • 1 month ago

One person made this FPS with Claude Code in just 3 weeks, demo is already on Steam. Iron Curtain Call by Whale Dev Studios looks like a 1930s rubber-hose cartoon drafted into World War III, with ink lines and comic sound effects on every hit.

One person made this FPS with Claude Code in just 3 weeks, demo is already on Steam. Iron Curtain Call by Whale Dev Studios looks like a 1930s rubber-hose cartoon drafted into World War III, with ink lines and comic sound effects on every hit.

47,003 views • 6 days ago

The cleanest game MVP made with AI I've seen. After the Wind by After The Wind: Ragnarok Online meets Monster Hunter, 5 weeks in Godot. Every asset matches the style. Rare with AI. 38.5B tokens processed in Claude Code, 2.9B in Codex, 112k tool calls, up to 8 agents at once.

The cleanest game MVP made with AI I've seen. After the Wind by After The Wind: Ragnarok Online meets Monster Hunter, 5 weeks in Godot. Every asset matches the style. Rare with AI. 38.5B tokens processed in Claude Code, 2.9B in Codex, 112k tool calls, up to 8 agents at once.

100,719 views • 14 days ago

New Open-Source AI Animator: Text-to-Animation for Humans, Animals, Creatures, Robots & More UniMate generates motion from text prompts for rigged 3D characters. Describe an action and turn it into animation. Highlights: • One model, different skeletons—no separate retraining for each rig. • Generate transitions between existing keyframes. • Edit motion with text while keeping selected joints unchanged. • Extend animations with a sequence of prompts. • Export animated meshes as FBX and GLB. • MIT-licensed code + downloadable preview weights.

New Open-Source AI Animator: Text-to-Animation for Humans, Animals, Creatures, Robots & More UniMate generates motion from text prompts for rigged 3D characters. Describe an action and turn it into animation. Highlights: • One model, different skeletons—no separate retraining for each rig. • Generate transitions between existing keyframes. • Edit motion with text while keeping selected joints unchanged. • Extend animations with a sequence of prompts. • Export animated meshes as FBX and GLB. • MIT-licensed code + downloadable preview weights.

245,967 views • 1 month ago

Day 10. Building the game I've dreamed of for 15 years with AI. I still can't get over the feeling that I can finally animate all the creatures I've been imagining for this game. Animation was the part I was most worried about when I started. I thought I'd need an animator, especially for creatures like centaurs, scorpions and spiders. So today I went off-plan and made a Scorpid. It won't even be in the first version of the game. I just wanted to see whether I could get its animations working. I started with a good model made in Tripo P2.0, already optimized and split into logical parts. I think that preparation matters a lot. GPT-6 works with the mesh through code and calculations. A sensible number of vertices and well-organized parts make it easier to work out bone placement and skin weights. Then I made video references for the animations with SD 2.5 and repeated the same workflow. About an hour and a half with GPT-6 Astra on xhigh: five animations ready for the game, including several rounds of feedback. Another hour later, I had it running in Unity. I used to run a 3D studio. Work like this used to take weeks. Now I'm watching this thing move around in my game, and I still can't quite believe my eyes.

Day 10. Building the game I've dreamed of for 15 years with AI. I still can't get over the feeling that I can finally animate all the creatures I've been imagining for this game. Animation was the part I was most worried about when I started. I thought I'd need an animator, especially for creatures like centaurs, scorpions and spiders. So today I went off-plan and made a Scorpid. It won't even be in the first version of the game. I just wanted to see whether I could get its animations working. I started with a good model made in Tripo P2.0, already optimized and split into logical parts. I think that preparation matters a lot. GPT-6 works with the mesh through code and calculations. A sensible number of vertices and well-organized parts make it easier to work out bone placement and skin weights. Then I made video references for the animations with SD 2.5 and repeated the same workflow. About an hour and a half with GPT-6 Astra on xhigh: five animations ready for the game, including several rounds of feedback. Another hour later, I had it running in Unity. I used to run a 3D studio. Work like this used to take weeks. Now I'm watching this thing move around in my game, and I still can't quite believe my eyes.

315,021 views • 1 month ago

Day 9. Building the game I've dreamed of for 15 years with AI. I'm still in shock from GPT-6. Today I handed it my game's UI. I'd started working on it last week with Fable 5.1 and design skills. I built it in HTML first, preparing the images and icons along the way. Figuring out what I wanted and how it should work took time. I needed that time. I also made animated character portraits. I tried Seedance 2.5 for those, and MiniMax H3 gave me much better results for this job. By the end, I had an interactive prototype with the UI logic worked out and all the assets ready. I could click through it and test how everything behaved before taking it into the game. Once I'd tested it and worked through the remaining questions, I opened GPT-6 in the same project. Gave it the interface and all the materials, and asked it to implement everything in Unity. About two hours later, I had a working UI and nothing to complain about. GPT-6 even went through different resolutions on its own. I'd expected this part to be difficult. It ended up being one of the easiest parts so far. I'd recommend building your UI in HTML first. Iterations are faster, you can click through it just like a real interface, and it's easier to catch the things you missed. Once you've worked those out, connect it to the game. You still have to wait for the engine to compile, whether you write the code yourself or use AI.

Day 9. Building the game I've dreamed of for 15 years with AI. I'm still in shock from GPT-6. Today I handed it my game's UI. I'd started working on it last week with Fable 5.1 and design skills. I built it in HTML first, preparing the images and icons along the way. Figuring out what I wanted and how it should work took time. I needed that time. I also made animated character portraits. I tried Seedance 2.5 for those, and MiniMax H3 gave me much better results for this job. By the end, I had an interactive prototype with the UI logic worked out and all the assets ready. I could click through it and test how everything behaved before taking it into the game. Once I'd tested it and worked through the remaining questions, I opened GPT-6 in the same project. Gave it the interface and all the materials, and asked it to implement everything in Unity. About two hours later, I had a working UI and nothing to complain about. GPT-6 even went through different resolutions on its own. I'd expected this part to be difficult. It ended up being one of the easiest parts so far. I'd recommend building your UI in HTML first. Iterations are faster, you can click through it just like a real interface, and it's easier to catch the things you missed. Once you've worked those out, connect it to the game. You still have to wait for the engine to compile, whether you write the code yourself or use AI.

276,787 views • 1 month ago

$63M in 2004. One weekly Claude limit in 2026. In 36 hours Opus 5.5 built a WoW-style game: 6 races, character creation, combat, a zone and a stone city. At pay-per-use prices that's about $2,400 (breakdown below). The original WoW took $63M to develop. A game millions of people love still takes talent. But the build itself is becoming the cheap part. What's left is an idea people fall in love with, and knowing how to show it. And almost anyone who ever dreamed of making their own game is about to get a shot at it.

$63M in 2004. One weekly Claude limit in 2026. In 36 hours Opus 5.5 built a WoW-style game: 6 races, character creation, combat, a zone and a stone city. At pay-per-use prices that's about $2,400 (breakdown below). The original WoW took $63M to develop. A game millions of people love still takes talent. But the build itself is becoming the cheap part. What's left is an idea people fall in love with, and knowing how to show it. And almost anyone who ever dreamed of making their own game is about to get a shot at it.

182,574 views • 1 month ago

Day 16. Building the game I've dreamed of for 15 years with AI. I built this Dryad from start to finish in about a day and a half, including her animations and VFX. Opus 5.5 and Gpt-6 Astra is dream combo😍 She crawls across the ground on her roots. More roots reach out to drain enemies, and when too many attackers crowd her, a wall of leaves protects her. Even the leaves on her body move, and she sheds more as she travels. Those little details make her feel alive. The key to my workflow is going in small steps and checking the result at every stage. First I sketched out the effects and worked out how they should behave. Then I made the animations. Once those worked, I built the VFX around them, reviewing and adjusting each part as I went. Watching her crawl into a fight with all of this working together feels like magic. I'll definitely make a video breaking down how I built these VFX, step by step. I think a lot of you will find this workflow useful.

Day 16. Building the game I've dreamed of for 15 years with AI. I built this Dryad from start to finish in about a day and a half, including her animations and VFX. Opus 5.5 and Gpt-6 Astra is dream combo😍 She crawls across the ground on her roots. More roots reach out to drain enemies, and when too many attackers crowd her, a wall of leaves protects her. Even the leaves on her body move, and she sheds more as she travels. Those little details make her feel alive. The key to my workflow is going in small steps and checking the result at every stage. First I sketched out the effects and worked out how they should behave. Then I made the animations. Once those worked, I built the VFX around them, reviewing and adjusting each part as I went. Watching her crawl into a fight with all of this working together feels like magic. I'll definitely make a video breaking down how I built these VFX, step by step. I think a lot of you will find this workflow useful.

180,130 views • 1 month ago

GPT-6 makes me scared as a 3D artist, cuz it's freaking insane. I mean, I'm testing this first hand everyday, but this time it is massive leap. look, 4 month ago I was testing GPT & Claude in Blender and they were not able to position simple objects in simple scene.. And look now... Whole car assembled from primitives in ONE prompt and animate it (hate to say that, but it was indeed one prompt). Yes, yes, it is not perfect and maybe not really usable still at this stage. BUT WHAT A JUMP.

GPT-6 makes me scared as a 3D artist, cuz it's freaking insane. I mean, I'm testing this first hand everyday, but this time it is massive leap. look, 4 month ago I was testing GPT & Claude in Blender and they were not able to position simple objects in simple scene.. And look now... Whole car assembled from primitives in ONE prompt and animate it (hate to say that, but it was indeed one prompt). Yes, yes, it is not perfect and maybe not really usable still at this stage. BUT WHAT A JUMP.

189,471 views • 1 month ago

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.

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.

150,815 views • 1 month ago

Free Open-Source Video-to-Animation for Mixamo Rigs, Now Inside Blender Motion2MixamoRig copies the motion of a person in a video onto a Mixamo-rigged character and hands you a skinned GLB for Blender or Unity. Highlights: • Video or a single photo as input • New Blender 4.2+ extension panel • Runs locally on CPU, CUDA or Apple Silicon • Reuse one take on other characters in tens of seconds • Apache-2.0 code GitHub:

Free Open-Source Video-to-Animation for Mixamo Rigs, Now Inside Blender Motion2MixamoRig copies the motion of a person in a video onto a Mixamo-rigged character and hands you a skinned GLB for Blender or Unity. Highlights: • Video or a single photo as input • New Blender 4.2+ extension panel • Runs locally on CPU, CUDA or Apple Silicon • Reuse one take on other characters in tens of seconds • Apache-2.0 code GitHub:

57,018 views • 20 days ago

I spent 2.5 billion tokens, every limit I had and five days to make this. A GTA-style city, built with GPT-6 using only prompts. No code or 3D by hand. The whole point was to push it as far as it goes and wire in every API I had. The setup: Codex driving Unreal Engine 5, with Higgsfield, Tripo, Meshy, Seedance, Seed Audio and fal handling the buildings, characters, animations, materials and sound. 8 buildings taken from concept to game, 247 generated voice lines for residents and police, 10 radio tracks across 5 stations. Here's the honest part. Most of those tokens didn't go into building. They went into fixing. The model writes a mechanic, runs it, watches it break, and tries again for hours. Getting a character to open a car door and actually sit in the seat took an absurd number of passes. A carjacking needed two separate bodies to stay locked to the same grab. Half the work was animation that looked fine on its own and fell apart the moment it ran in the game. And almost all of that 2.5B is the same project history being re-read from cache on every request, not unique code. Procedural generation from prompts is genuinely fun to watch and wildly inefficient at the same time. The city started as glowing blocks with working driving, money and jobs underneath, and ended up somewhere I'd actually screenshot. Full breakdown:

I spent 2.5 billion tokens, every limit I had and five days to make this. A GTA-style city, built with GPT-6 using only prompts. No code or 3D by hand. The whole point was to push it as far as it goes and wire in every API I had. The setup: Codex driving Unreal Engine 5, with Higgsfield, Tripo, Meshy, Seedance, Seed Audio and fal handling the buildings, characters, animations, materials and sound. 8 buildings taken from concept to game, 247 generated voice lines for residents and police, 10 radio tracks across 5 stations. Here's the honest part. Most of those tokens didn't go into building. They went into fixing. The model writes a mechanic, runs it, watches it break, and tries again for hours. Getting a character to open a car door and actually sit in the seat took an absurd number of passes. A carjacking needed two separate bodies to stay locked to the same grab. Half the work was animation that looked fine on its own and fell apart the moment it ran in the game. And almost all of that 2.5B is the same project history being re-read from cache on every request, not unique code. Procedural generation from prompts is genuinely fun to watch and wildly inefficient at the same time. The city started as glowing blocks with working driving, money and jobs underneath, and ended up somewhere I'd actually screenshot. Full breakdown:

129,647 views • 1 month ago

GPT-6 changes 3D modeling forever. It works inside Blender completely autonomously, like an artist: gathers reference photos on its own, builds the scene, renders test frames, checks them against the references, then fixes what's off. When the scene holds up, it ships it to Unreal Engine 5 as a walkable level. Clips from the OpenAI launch. More demos in the thread. Full announcement:

GPT-6 changes 3D modeling forever. It works inside Blender completely autonomously, like an artist: gathers reference photos on its own, builds the scene, renders test frames, checks them against the references, then fixes what's off. When the scene holds up, it ships it to Unreal Engine 5 as a walkable level. Clips from the OpenAI launch. More demos in the thread. Full announcement:

161,522 views • 1 month ago

Two days. That's how long it took me to rebuild F-Zero X, my favourite N64 game as a kid. I played, Claude Code built, my workflows made the art, animations and vfx. Then I lost hours just racing it. Anyone can make something like this now. Play:

Two days. That's how long it took me to rebuild F-Zero X, my favourite N64 game as a kid. I played, Claude Code built, my workflows made the art, animations and vfx. Then I lost hours just racing it. Anyone can make something like this now. Play:

73,752 views • 27 days ago

I made a UE 5 game using only free AI in just 4 days. I generated 26 props, created two characters, and got ragdoll physics, checkpoints, and NPCs working. I still had to rig the characters, build the level, and fix bugs myself. Total spent on AI - $0. Full breakdown: #UnrealEngine #UE5 #GameDev #FreeAI #3DAI

I made a UE 5 game using only free AI in just 4 days. I generated 26 props, created two characters, and got ragdoll physics, checkpoints, and NPCs working. I still had to rig the characters, build the level, and fix bugs myself. Total spent on AI - $0. Full breakdown: #UnrealEngine #UE5 #GameDev #FreeAI #3DAI

14,207 views • 5 days ago

Day 8 of building the game I've wanted to play for 15 years with AI. I absolutely love GPT-6. I'm switching from Claude completely. Today it finally happened: a full animation set for a non-humanoid character. My wolf is rigged and animated. All of last week I was trying approaches in parallel: Mesh2Motion, Cascadeur, Animate Anything, a pile of smaller tools. Everything kept almost working and then falling apart. Then GPT-6, and it's done. To be fair, I came in with a worked-out workflow: 1. Generate the model optimized from the start. Tripo P2.0 with multiview input, around 10k polygons, and the model came out great. 2. My agent turned the same side reference I used for the 3D gen into motion references with Seedance 2.5. Takes vary, so I picked the best ones. I only need 4 animations. 3. I decided the timing of each animation upfront, so they drop into the game as is. 4. Handed all of it to GPT-6 with Blender MCP. A couple of hours and a couple of feedback rounds later I have working animations I'm taking into the game. I fought this with Fable and the automation always came out crooked. This time it just worked. If you've been stuck on animations for a creature like this, try that route. And if anyone wants my workflow MD for GPT-6, I'll share it.

Day 8 of building the game I've wanted to play for 15 years with AI. I absolutely love GPT-6. I'm switching from Claude completely. Today it finally happened: a full animation set for a non-humanoid character. My wolf is rigged and animated. All of last week I was trying approaches in parallel: Mesh2Motion, Cascadeur, Animate Anything, a pile of smaller tools. Everything kept almost working and then falling apart. Then GPT-6, and it's done. To be fair, I came in with a worked-out workflow: 1. Generate the model optimized from the start. Tripo P2.0 with multiview input, around 10k polygons, and the model came out great. 2. My agent turned the same side reference I used for the 3D gen into motion references with Seedance 2.5. Takes vary, so I picked the best ones. I only need 4 animations. 3. I decided the timing of each animation upfront, so they drop into the game as is. 4. Handed all of it to GPT-6 with Blender MCP. A couple of hours and a couple of feedback rounds later I have working animations I'm taking into the game. I fought this with Fable and the automation always came out crooked. This time it just worked. If you've been stuck on animations for a creature like this, try that route. And if anyone wants my workflow MD for GPT-6, I'll share it.

90,850 views • 1 month ago

kimodo.cpp is live. NVIDIA's Kimodo, the best AI animation model right now, running natively on CPU or Vulkan. Type a sentence, get character animation, locally on your own machine. Before, you needed the whole PyTorch and CUDA stack standing up before you could generate a single motion. Now it is a native C++/GGML build that loads GGUF models and comes with a local web demo. No Python environment to fight. It gives you SMPL-X, and from there you retarget onto pretty much any skeleton you want, like Mixamo. Great piece of work Richard Palethorpe

kimodo.cpp is live. NVIDIA's Kimodo, the best AI animation model right now, running natively on CPU or Vulkan. Type a sentence, get character animation, locally on your own machine. Before, you needed the whole PyTorch and CUDA stack standing up before you could generate a single motion. Now it is a native C++/GGML build that loads GGUF models and comes with a local web demo. No Python environment to fight. It gives you SMPL-X, and from there you retarget onto pretty much any skeleton you want, like Mixamo. Great piece of work Richard Palethorpe

108,986 views • 2 months ago

Day 20. Building the game I've dreamed of for 15 years with AI. When I started this game, what excited me most was the variety of creatures you can meet and claim for your army. Today that idea got two new pieces: a tavern and the Stone Golem. The golem is my favorite kind of surprise. On the second level there are piles of stones lying in the fields and at the foot of the mountains. You walk past them like they're part of the landscape. Get too close and the stones pull themselves together into a three-meter golem, and he goes straight for whoever woke him. The funniest moment of the day: the first golem I placed ended up too close to an Urs guard post. The guards woke him and killed him within seconds. I had to find him a quieter spot. His size changed too. At first he was about a head taller than a soldier, and once I saw him next to them, that wasn't enough. I gave him another head and a half, and now he really looks like a rock you shouldn't wake. He fights with wide sweeps of his arms. When enemies crowd around him, he slams both fists into the ground and sends rocks and dust flying. When he dies, he falls apart into stones again. His waking and his death are physics simulations in Blender, so the stones really fall, roll and settle. The tavern stands on the first level, by the road right next to your castle. You can hire characters there to fight for you. Whoever you hire stays with you until he falls, and nobody comes back. I wanted it to feel warm. At night the windows glow like there's a fire inside, and the light flickers and spills onto the ground. On the dark moor it's the first thing you notice. But the best part of today was watching a pile of rocks stand up right in front of my soldiers.

Day 20. Building the game I've dreamed of for 15 years with AI. When I started this game, what excited me most was the variety of creatures you can meet and claim for your army. Today that idea got two new pieces: a tavern and the Stone Golem. The golem is my favorite kind of surprise. On the second level there are piles of stones lying in the fields and at the foot of the mountains. You walk past them like they're part of the landscape. Get too close and the stones pull themselves together into a three-meter golem, and he goes straight for whoever woke him. The funniest moment of the day: the first golem I placed ended up too close to an Urs guard post. The guards woke him and killed him within seconds. I had to find him a quieter spot. His size changed too. At first he was about a head taller than a soldier, and once I saw him next to them, that wasn't enough. I gave him another head and a half, and now he really looks like a rock you shouldn't wake. He fights with wide sweeps of his arms. When enemies crowd around him, he slams both fists into the ground and sends rocks and dust flying. When he dies, he falls apart into stones again. His waking and his death are physics simulations in Blender, so the stones really fall, roll and settle. The tavern stands on the first level, by the road right next to your castle. You can hire characters there to fight for you. Whoever you hire stays with you until he falls, and nobody comes back. I wanted it to feel warm. At night the windows glow like there's a fire inside, and the light flickers and spills onto the ground. On the dark moor it's the first thing you notice. But the best part of today was watching a pile of rocks stand up right in front of my soldiers.

36,945 views • 22 days ago