Alex

@alexfredo87 • 4,100 subscribers

Indie game dev, working on a standalone VR multiplayer game.

Shorts

For the facial animations in my game, I use a technique that yields results similar to L.A. Noire. To keep it simple: I first generate a facial animation video using AI like LTX 2. Then, I create a video depth map from that animation and project it onto a face mask. Using vertex displacement, the depth map dynamically deforms the face as the character speaks. The result looks good in standalone VR. I actually created this workflow long time ago:

For the facial animations in my game, I use a technique that yields results similar to L.A. Noire. To keep it simple: I first generate a facial animation video using AI like LTX 2. Then, I create a video depth map from that animation and project it onto a face mask. Using vertex displacement, the depth map dynamically deforms the face as the character speaks. The result looks good in standalone VR. I actually created this workflow long time ago:

48,189 次观看

A quick video preview of my "Photorealistic Shenmue AI texture pack" #Shenmue

A quick video preview of my "Photorealistic Shenmue AI texture pack" #Shenmue

63,701 次观看

Do you guys want me to make a long video featuring popular games from the PS2/Dreamcast era using Gen-3, like the example below?

Do you guys want me to make a long video featuring popular games from the PS2/Dreamcast era using Gen-3, like the example below?

69,748 次观看

References by Runway is so useful for creating Start and End frame. Cristóbal Valenzuela

References by Runway is so useful for creating Start and End frame. Cristóbal Valenzuela

13,559 次观看

I'm testing rotating around objects, like a table for example, with my Point & Click script.

I'm testing rotating around objects, like a table for example, with my Point & Click script.

12,471 次观看

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

A quick test to see what results an AI animated sprite can achieve using normal maps and depth maps. I tried it with DOOM style sprites just for fun. #Doom

A quick test to see what results an AI animated sprite can achieve using normal maps and depth maps. I tried it with DOOM style sprites just for fun. #Doom

51,982 次观看 • 14 天前

My extended video of Shenmue 1 using Gen-3 vid2vid is done. Hope you guys like it! Shenmue Forever #Shenmue Runway #LetsGetShenmue4

My extended video of Shenmue 1 using Gen-3 vid2vid is done. Hope you guys like it! Shenmue Forever #Shenmue Runway #LetsGetShenmue4

2,055,015 次观看 • 1 年前

I'm experimenting with improving the shader by adding dynamic self-shadowing driven by the depth map. This creates dynamic shadows directly on the sprite.

Sensitive content

This media may contain sensitive content.

I'm experimenting with improving the shader by adding dynamic self-shadowing driven by the depth map. This creates dynamic shadows directly on the sprite.

22,650 次观看 • 13 天前

For those interested in Gaussian Splatting, I just found a awesome free open-source tool that generates high-quality GS. You can download it here:

For those interested in Gaussian Splatting, I just found a awesome free open-source tool that generates high-quality GS. You can download it here:

80,604 次观看 • 2 个月前

I'm testing out Gaussian splatting generation using LTX 2.3 and Postshot. It’s working pretty well, though there are still a few minor glitches. LTX

I'm testing out Gaussian splatting generation using LTX 2.3 and Postshot. It’s working pretty well, though there are still a few minor glitches. LTX

66,309 次观看 • 2 个月前

After a lot of research, I managed to create a tool for Godot that makes it possible to animate Gaussian Splatting with bones, especially for human bodies using Godot’s Skeleton3D. There are still a few small bugs when importing animations, but I’m definitely on the right track.

After a lot of research, I managed to create a tool for Godot that makes it possible to animate Gaussian Splatting with bones, especially for human bodies using Godot’s Skeleton3D. There are still a few small bugs when importing animations, but I’m definitely on the right track.

42,086 次观看 • 2 个月前

Big news I found a way to convert Gaussian Splatting into a standard mesh while preserving all the visual advantages of Gaussian Splatting, such as reflections, shadows, and lighting that changes depending on the viewing angle. The result is excellent performance, even on an old laptop or a VR headset. And of course, the mesh can be animated like any regular 3D mesh, while still keeping the visual benefits of GS. I’ll soon show a full-body character animated using this technique.

Big news I found a way to convert Gaussian Splatting into a standard mesh while preserving all the visual advantages of Gaussian Splatting, such as reflections, shadows, and lighting that changes depending on the viewing angle. The result is excellent performance, even on an old laptop or a VR headset. And of course, the mesh can be animated like any regular 3D mesh, while still keeping the visual benefits of GS. I’ll soon show a full-body character animated using this technique.

37,137 次观看 • 2 个月前

Ok guys, I’m going to make videos of old well-known games. I’ll post them one by one, not all at once because that would take too long to do. The first game will be GTA Vice City, a little preview below : #GTA6 Rockstar Games Runway

Ok guys, I’m going to make videos of old well-known games. I’ll post them one by one, not all at once because that would take too long to do. The first game will be GTA Vice City, a little preview below : #GTA6 Rockstar Games Runway

236,219 次观看 • 1 年前

I'm testing tree generation using only two reference images. Basically, my Gaussian Splatting generation technique works with almost anything. I can't wait to see the final result once I’ve gathered a huge library of realistic assets for my game. For optimization, I’m planning to use a LOD system that dynamically reduces the number of Gaussian splats based on the distance from the camera.

I'm testing tree generation using only two reference images. Basically, my Gaussian Splatting generation technique works with almost anything. I can't wait to see the final result once I’ve gathered a huge library of realistic assets for my game. For optimization, I’m planning to use a LOD system that dynamically reduces the number of Gaussian splats based on the distance from the camera.

30,539 次观看 • 2 个月前

📢 I’m testing ViggleAI new AI tool, PINOC, and it’s seriously impressive. You can create 3D Gaussian splatting models from just one image and animate them with a video! It’s the first AI I’ve tried that can animate Gaussian splatting models. I also talked to someone from Viggle, and they might add the option to import your own Gaussian splatting models and animate them. If that happens, I’ll probably make a video tutorial showing how to boost the detail level of a Gaussian splatting model by 4x to create highly realistic animated characters.

📢 I’m testing ViggleAI new AI tool, PINOC, and it’s seriously impressive. You can create 3D Gaussian splatting models from just one image and animate them with a video! It’s the first AI I’ve tried that can animate Gaussian splatting models. I also talked to someone from Viggle, and they might add the option to import your own Gaussian splatting models and animate them. If that happens, I’ll probably make a video tutorial showing how to boost the detail level of a Gaussian splatting model by 4x to create highly realistic animated characters.

29,776 次观看 • 2 个月前

For the facial animations in my game, I use a technique that yields results similar to L.A. Noire. To keep it simple: I first generate a facial animation video using AI like LTX 2. Then, I create a video depth map from that animation and project it onto a face mask. Using vertex displacement, the depth map dynamically deforms the face as the character speaks. The result looks good in standalone VR. I actually created this workflow long time ago:

For the facial animations in my game, I use a technique that yields results similar to L.A. Noire. To keep it simple: I first generate a facial animation video using AI like LTX 2. Then, I create a video depth map from that animation and project it onto a face mask. Using vertex displacement, the depth map dynamically deforms the face as the character speaks. The result looks good in standalone VR. I actually created this workflow long time ago:

48,189 次观看 • 4 个月前

I'm testing AI projection texturing on mobile devices like the Meta Quest and Samsung phones. I'm using a technique similar to Carmack's Virtual/MegaTexture to optimize the texture projections (quite a few projections are missing in this scene). I think I'm going to make a Counter-Strike like for mobile VR with AI projection texturing.

I'm testing AI projection texturing on mobile devices like the Meta Quest and Samsung phones. I'm using a technique similar to Carmack's Virtual/MegaTexture to optimize the texture projections (quite a few projections are missing in this scene). I think I'm going to make a Counter-Strike like for mobile VR with AI projection texturing.

53,991 次观看 • 5 个月前

I'm testing a shader that adds a detail texture at close range in VR, so it doesn't get blurry even if the player sticks their face right up against a wall. Note that the detail texture used here is just a quick placeholder the transition and details will be better in the final build.

I'm testing a shader that adds a detail texture at close range in VR, so it doesn't get blurry even if the player sticks their face right up against a wall. Note that the detail texture used here is just a quick placeholder the transition and details will be better in the final build.

51,523 次观看 • 5 个月前

I'm testing AI texture projection on low poly characters for my mobile VR game.

I'm testing AI texture projection on low poly characters for my mobile VR game.

51,638 次观看 • 5 个月前

Wednesday Addams generated using only 3 reference images.

Wednesday Addams generated using only 3 reference images.

19,885 次观看 • 2 个月前

I've improved my Point & Click video game system, the animations look better now, among other enhancements.

I've improved my Point & Click video game system, the animations look better now, among other enhancements.

84,050 次观看 • 1 年前

I just tested a new plugin called StableGen for Blender. It's open-source and automatically textures 3D objects in one click using AI. It's magical, I highly recommend it!

I just tested a new plugin called StableGen for Blender. It's open-source and automatically textures 3D objects in one click using AI. It's magical, I highly recommend it!

79,817 次观看 • 1 年前

A comparison between my script, which converts a single image into Gaussian Splatting, and Apple’s Sharp. I’m getting better and more consistent results, with no deformation, and I can generate as many viewing angles as I want. The only downside is that it takes more time to compute.

A comparison between my script, which converts a single image into Gaussian Splatting, and Apple’s Sharp. I’m getting better and more consistent results, with no deformation, and I can generate as many viewing angles as I want. The only downside is that it takes more time to compute.

14,355 次观看 • 2 个月前

I'm testing my AI render projection shader on de_dust2 from CS 1.6. I updated the shader again so it works well with large open spaces, not just interiors.

I'm testing my AI render projection shader on de_dust2 from CS 1.6. I updated the shader again so it works well with large open spaces, not just interiors.

28,604 次观看 • 5 个月前

*Warning* the video is somewhat NSFW, I'm testing another new technique that can generate a Gaussian Splatting model using only three viewing angles! It already works, but there's still a kind of ghosting/doubling effect that I need to fix.

Warning the video is somewhat NSFW, I'm testing another new technique that can generate a Gaussian Splatting model using only three viewing angles! It already works, but there's still a kind of ghosting/doubling effect that I need to fix.

13,425 次观看 • 2 个月前