Build and play AI mods and games

San Francisco
NPCs can talk back now! Introducing NPCTalk: make the NPCs of any game talk in realtime. I made every NPC in GTA V answer to me in character, in their own cloned voice, in under 1s, and they act on what you say. We packaged all the skills Claude learned into a single repo, built on open models: NVIDIA Nemotron ASR for transcription, Qwen 3.8 27B for realtime dialogue, and Fish Audio Drama 3 for the cloned voices, self-hosted on a serverless GPU. github.com/christos-antono/N…
160
596
9,842
799,434
universal-modder retweeted
Prompt to 3D character animation, now with high fidelity hand + finger tracking✌️ FLUX 3 Max video → WiLoR for hands + GVHMR for body tracking → any animated character! open source: github.com/blendi-remade/pro…
Prompt → animation at realtime speed 🕺 FLUX 3 Max generates the video, GVHMR pulls clean 3D motion from it on one GPU, and it's retargeted live onto any mixamo character. Fully automated flow! Open source: github.com/blendi-remade/pro…
6
69
3,651
with FLUX 3 Max + GVHMR, you can get any animation retargeted LIVE onto any Mixamo character! Try it out: github.com/blendi-remade/pro…
Introducing FLUX 3 Max, the latest post-trained video model from fal Research in partnership with @bfl_ai. FLUX 3 Max is tied for #1 in image-to-video quality on independent third-party benchmarks, generating a 10-second, 720/768p video in ~12 seconds. For the next three weeks, FLUX 3 Max is 75% off, making it the most affordable frontier video model at its quality level.
2
19
1,010
universal-modder retweeted
Prompt → animation at realtime speed 🕺 FLUX 3 Max generates the video, GVHMR pulls clean 3D motion from it on one GPU, and it's retargeted live onto any mixamo character. Fully automated flow! Open source: github.com/blendi-remade/pro…
Introducing FLUX 3 Max, the latest post-trained video model from fal Research in partnership with @bfl_ai. FLUX 3 Max is tied for #1 in image-to-video quality on independent third-party benchmarks, generating a 10-second, 720/768p video in ~12 seconds. For the next three weeks, FLUX 3 Max is 75% off, making it the most affordable frontier video model at its quality level.
17
50
562
30,173
You can now recreate any meme in GTA V
1
6
125
6,880
We compared Haiku, Sonnet and Opus 5.5 models on a simple rigging & animation task! We tracked time taken and total token cost! We'll be releasing a more in depth benchmarking and evaluation for a range of headless blender tasks!
2
4
34
1,963
universal-modder retweeted
NPCs can talk back now! Introducing NPCTalk: make the NPCs of any game talk in realtime. I made every NPC in GTA V answer to me in character, in their own cloned voice, in under 1s, and they act on what you say. We packaged all the skills Claude learned into a single repo, built on open models: NVIDIA Nemotron ASR for transcription, Qwen 3.8 27B for realtime dialogue, and Fish Audio Drama 3 for the cloned voices, self-hosted on a serverless GPU. github.com/christos-antono/N…
160
596
9,842
799,434
universal-modder retweeted
This mod is extremely fun! Talk to any NPC in GTA V
NPCs can talk back now! Introducing NPCTalk: make the NPCs of any game talk in realtime. I made every NPC in GTA V answer to me in character, in their own cloned voice, in under 1s, and they act on what you say. We packaged all the skills Claude learned into a single repo, built on open models: NVIDIA Nemotron ASR for transcription, Qwen 3.8 27B for realtime dialogue, and Fish Audio Drama 3 for the cloned voices, self-hosted on a serverless GPU. github.com/christos-antono/N…
12
90
4,924
NPCs can talk back now! Introducing NPCTalk: make the NPCs of any game talk in realtime. I made every NPC in GTA V answer to me in character, in their own cloned voice, in under 1s, and they act on what you say. We packaged all the skills Claude learned into a single repo, built on open models: NVIDIA Nemotron ASR for transcription, Qwen 3.8 27B for realtime dialogue, and Fish Audio Drama 3 for the cloned voices, self-hosted on a serverless GPU. github.com/christos-antono/N…
160
596
9,842
799,434
Tesla Roadster, in Rocket League, in the browser ⚽ try it out: soccar-nine.vercel.app/?car=…
Real life, baby
53
145
2,497
163,647
coming soon to universal modder with multiplayer, for free! We'll also be open-sourcing the whole thing (just like any game we publish) so you can build anything you like on top of it
2
26
5,024
Step by step walkthrough on how to get a rigged Homelander character into GTA V!
Step by step process on how to get a rigged Thanos character into GTA V!
3
5
46
3,577
how our gopniks learned to squat: 1. ai video of a guy doing a slav squat 2. pull his skeleton out of the video (mediapipe, open-source) 3. Retarget it onto the slav warfare rigs in blender
they kill you, then they dance on you with kalinka playing 💀 slav warfare is dropping soon, free + multiplayer, on @universalmodhq
2
2
16
2,261
universal-modder retweeted
they kill you, then they dance on you with kalinka playing 💀 slav warfare is dropping soon, free + multiplayer, on @universalmodhq
6
23
3,944
3d gen "models" are pipelines: shape diffusion → mesh → remesh → uv unwrap → texture → bake. each vendor packs different steps.
SOTA 3D Diffusion Model comparison! If you were wondering which model to choose for your game assets, this video will help!
1
5
29
3,001
avg of 5 generations: trellis.2: 57 s tripo p2: 105 s meshy 7.1: 153 s hunyuan3d: 177 s rodin: 184 s hi3d: 678 s
3
1,272
Tripo P2 and Meshy 7.1 are two of the best image-to-3d models out right now
SOTA 3D Diffusion Model comparison! If you were wondering which model to choose for your game assets, this video will help!
5
6
72
4,229
SOTA 3D Diffusion Model comparison! If you were wondering which model to choose for your game assets, this video will help!
3
9
124
12,865