Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

I started using Blender through MCP about two weeks ago, and I quickly realized that you can build almost anything with AI. This model was created using Blender, Hunyuan3D, Gemini, and ChatGPT. Here’s how I did it: I opened Gemini, uploaded an image of the Gundam model, and asked... it to generate a clean front-view image. I uploaded that front view to ChatGPT and asked it to generate two additional angles: a back view and a 45-degree front-left view. I went to: I signed up with my email and translated the page into English. Then I opened Image to 3D and selected the multi-image option. You’ll see a diagram of a whale from several angles. Upload each reference image in its corresponding position, such as front, 45-degree front-left, and back. I selected the 1.5M-face option. This produces a very high-poly model, but don’t worry, we’ll fix that next. Once the generation is complete, download the model as a GLB file. From the Hunyuan homepage, open 3D Studio using one of the dropdown menus. Select the topology or retopology tool and upload your GLB. I chose the High setting to preserve as much detail as possible. After a few seconds, the model was retopologized. It kept most of its visual detail while using far fewer polygons. The original head and rifle didn’t look very good, so I generated them separately. I returned to ChatGPT and created dedicated reference images for the Gundam’s head and rifle. I generated each part individually in Hunyuan at the 1.5M setting, then ran both through the same retopology process. Next came the textures. Open the texture section, select the multi-image option, and upload the same reference images according to the whale orientation indicators. However, instead of using the original clean textures, I asked ChatGPT to recreate them with wear, rust stains, scratches, and other surface damage. This gave the Gundam a much older and more authentic appearance. Once every part was textured, I imported everything into Blender. You can ask Codex through MCP to remove the original head and rifle, or you can do it manually. Select the main model and press Tab to enter Edit Mode. Press 3 to enable face selection, then press C to activate Circle Select. Paint over the faces belonging to the original helmet or rifle. You can press X to delete those faces or P to separate them into another object. Then position the newly generated, more detailed head and rifle in their place. I demonstrate this process in one of my older videos. And that’s it. You now have a very cool 3D Gundam model! Afterward, I created the cockpit, separated the model into movable sections, and rigged everything for use in my Three.js game. That process deserves its own tutorial, though. If anyone wants to see it, let me know. Or just ask your AI, I guess. They seem to know everything these days. xDshow more

Spectro

3,520 subscribers

82,151 Aufrufe • vor 3 Monaten •via X (Twitter)

Kunst Wissenschaft & Technologie Gaming

Anya Rossi• Live Now

Private livecam show

46 Kommentare

Profilbild von Spectro

Spectrovor 3 Monaten

testing gameplay

Profilbild von Arifi Labs

Arifi Labsvor 3 Monaten

That's insane between 1999 and 2004, I worked on a Dragon Ball Z Quake 3 Total Conversion and a Gundam Quake 3 Total Conversion and this brings back memories of the models we pushed at the time. We were pushing around 5000 polygons and growing which at the time was quite high for 3D engines!

Profilbild von Kevin Ngo

Kevin Ngovor 3 Monaten

Looks nice! I also made mech like yours in my game using blender mcp

Profilbild von Spectro

Spectrovor 3 Monaten

that was amazing! love the retro graphics

Profilbild von Stinky the Slime

Stinky the Slimevor 3 Monaten

I think @IsThisA3DModel is going to have a bad time with this

Profilbild von Adrian

Adrianvor 3 Monaten

The topology and textures are pure shit. Congrats.

Profilbild von Supernal

Supernalvor 3 Monaten

Need this in my life but I'm already doing so much fuck

Profilbild von Spectro

Spectrovor 3 Monaten

Dont worry, im making a video tutorial, you can just feed the tutorial into your coding Ai and i believe he will be able to do it all autonomously lol

Profilbild von Rob Lenza

Rob Lenzavor 3 Monaten

I’d love to see that tutorial

Profilbild von Eason @ flick.art

Eason @ flick.artvor 3 Monaten

You should also try out @flickartHQ ‘s new 3D Stage, blender like creation but the agent creates for you in seconds.

Profilbild von ni-zav

ni-zavvor 3 Monaten

can i see the uv?

Profilbild von SabSnake

SabSnakevor 3 Monaten

Now the worst part, weight painted, bones, animation.

Profilbild von IMTNF.eth

IMTNF.ethvor 3 Monaten

Now the rogging and three.js tutorial pls

Profilbild von Spectro

Spectrovor 3 Monaten

Chatgpt did the rigging for me lol

Profilbild von Marx Charle

Marx Charlevor 3 Monaten

Wow

Profilbild von Superhero "Crypto" Ninja

Superhero "Crypto" Ninjavor 3 Monaten

How much is the tencent service? Is it the same as

Profilbild von Spectro

Spectrovor 3 Monaten

it was free in ten ent

Profilbild von Duke

Dukevor 3 Monaten

this is pretty cool. Would love to see it!

Profilbild von ChrisMac

ChrisMacvor 3 Monaten

Neat you can do that. But every game dev standard, that model is just horrendous. A lot of unnecessary geometry in places resulting to: Not subdiv ready. Shading errors Hard surface modeling nightmare. Bad optimization

Profilbild von Spectro

Spectrovor 3 Monaten

The model is already low poly, made with polygen, its running on 60fps on a browser, with shadows, vfx etc

Profilbild von ChrisMac

ChrisMacvor 3 Monaten

Low poly hides the issues and constrains the model to a single purpose. Shield, chest vents & circles on shoulders have so much geometry. N-gons on many parts of the model.

Profilbild von wohe

wohevor 3 Monaten

i have a question, i don't know much about 3d unfortunately but i'm trying to have ai create a simple orbit swish in retract and orbit swish out motion on a can product commercial that i'm trying to make, i genuinely do not know how to drive the blender mcp to achieve this.

Profilbild von Spectro

Spectrovor 3 Monaten

like, product animation? i think you can tell mcp to set the origin of the camera to the can, or set thje camera itself as parent, so you can animate the orbit motion and then animation the camera closing in on an axis from the camera to the parent object, although i never done anything like this so im just guessing

Profilbild von 工具家

工具家vor 3 Monaten

😇😇😇😇感觉好麻烦

Profilbild von Sebastiano Mandalà

Sebastiano Mandalàvor 3 Monaten

A simpler workflow would be nicer but it looks cool

Profilbild von One Node Lab

One Node Labvor 3 Monaten

Thanks for open sourcing your workflows

Profilbild von DeStatistical One Ton Noodles

DeStatistical One Ton Noodlesvor 3 Monaten

Sick

Profilbild von Robert Baker

Robert Bakervor 3 Monaten

Yes, it’s great … I can use ChatGPT to help write a storyline, then generate concept art for characters by reading the storyline and then generate multiple views of characters than can be used by a 3d model generator like Meshy AI that can be edited by ChatGPT over the blender or Unity3d MCP interfaces.

Profilbild von Spectro

Spectrovor 3 Monaten

yup, essentially a ford style production pipeline

Profilbild von Robert Baker

Robert Bakervor 3 Monaten

Yeah, and it’s not a replacement for human artistry or talent as many people think - AI augments those things. I’ll be honest, I’ve been using Blender for about 8 years now and I LOVE not having to spend hours, days and weeks crafting 3d models from scratch anymore and to be able to go from 2d images to 3d models with ease! Reworking topology and textures sometimes, is much better than starting from scratch and the MCP interfaces are wonderful for a lot of things like repetitive tasks!😃💙👍

Profilbild von Spectro

Spectrovor 3 Monaten

I started using belnder because of mcp and often i find myself doing stuff manually rather than using ai because its so satisfying

Profilbild von Robert Baker

Robert Bakervor 3 Monaten

Yeah, I needed to simplify the geometry of a building done by a talented environment artist so I asked for a blend file containing planes with rendered from all sides applied to planes after switching all the textures to emissive. The original building mesh had lots of meshes for individual boards, so the vertex count was very high. ChatGPT did it all in one shot in just a few minutes. 😅🤣 But “cutting out” the walls and adding back normal maps, from the generated planes having the new textures, was a lot of fun. I know what you mean! 😃

Profilbild von Nick Venturi

Nick Venturivor 3 Monaten

this is cheating at 3d

Profilbild von Spectro

Spectrovor 3 Monaten

pretty much, lol. i just spawned another 3 mechs in the blink of an eye too, right now separating the limbs to animate and then install the cockpit in them, i could make them super high detail too, but since im using threejs the low poly is fine

Profilbild von Court Reinland

Court Reinlandvor 3 Monaten

Great process. Thanks for sharing. “Ai enhanced” workflows are the hardest to find on here it seems. It’s either “I one-shotted this game with AI blah” or “watch me spend 300 hours of my life modeling this detail” haha 😆

Profilbild von Creadev

Creadevvor 3 Monaten

Looks cool. You can take it to the next level and import this model and use it as an FBX/GLB inside Creadev ( which is a no-code platform for developing AA/Triple-i quality games, animations and simulations.

Profilbild von Kostya | AI

Kostya | AIvor 3 Monaten

First candidate: Using Gemini to upload a Gundam model demonstrates how AI can transform simple images into complex 3D models.

Profilbild von Galactus García

Galactus Garcíavor 3 Monaten

Thanks for the explanation, but you skipped the rig and the animation parts. Why don't you share your process for doing so too?

Profilbild von cko

ckovor 3 Monaten

Been using this workflow for a while now. The latest 3.1 model is very good. I’m still shocked we get 20 free generations per day for free at this level of quality.

Profilbild von smoker bruda

smoker brudavor 3 Monaten

Looks good

Profilbild von Daniel onyejefu

Daniel onyejefuvor 3 Monaten

Am using chatgbt to generate frames for characteristics for 2d animation. Looking for interested fellows to do projects

Profilbild von dillzilla99

dillzilla99vor 3 Monaten

WTF is that topology? Jesus fucking Christ that is bad.

Profilbild von mmsdaus

mmsdausvor 2 Monaten

Absolute cinema! I am experimenting with unity cli, codex, Gemini 3.7 flash and ChatGpt, made a playable 5min 2d space shooter level in around 8h total

Profilbild von Aledandrea

Aledandreavor 3 Monaten

does it all for you

Profilbild von Sebastian Buzdugan

Sebastian Buzduganvor 3 Monaten

the hard part is mesh cleanup after hunyuan3d not the first model generation

Profilbild von Balazs Nemeth 🇭🇺

Balazs Nemeth 🇭🇺vor 1 Monat

Can you share which Blender MCP and how you use?

Ähnliche Videos

✨ I made a little demo of #vibejam sponsor Tripo and how you can use it to generate assets for your games In this case I'm generating an apartment flat that's half destroyed and open for my drone sim to fly around, take cover and shoot at enemies from First I write the prompt and select Nano Banana to generate an image first, I get a few different ones, and I select the one I like Then that one is converted into a 3d object called a Smart Mesh Smart Mesh is different than regular image-to-3d models because usually you get issues with uneven polygon distribution, too dense geometry and poor edge flow, so while you think you save time with generating it with AI you end up doing lots of editing after to fix the topology which kinda defeats the point Smart Mesh doesn't have any of this, it's fast and clean low-poly models you can drop into your game Anyway, after generating the model I can then see it in 3d, and if I don't like it, regenerate it, or if I like it start texturing it Once that's done, I export it as a GLB, FBX or OBJ and drop it in (usually I use GLB as ThreeJS seems to prefer that), in my case I just drop the URL into Cursor and let it figure out the placement of the asset into my game!

✨ I made a little demo of #vibejam sponsor Tripo and how you can use it to generate assets for your games In this case I'm generating an apartment flat that's half destroyed and open for my drone sim to fly around, take cover and shoot at enemies from First I write the prompt and select Nano Banana to generate an image first, I get a few different ones, and I select the one I like Then that one is converted into a 3d object called a Smart Mesh Smart Mesh is different than regular image-to-3d models because usually you get issues with uneven polygon distribution, too dense geometry and poor edge flow, so while you think you save time with generating it with AI you end up doing lots of editing after to fix the topology which kinda defeats the point Smart Mesh doesn't have any of this, it's fast and clean low-poly models you can drop into your game Anyway, after generating the model I can then see it in 3d, and if I don't like it, regenerate it, or if I like it start texturing it Once that's done, I export it as a GLB, FBX or OBJ and drop it in (usually I use GLB as ThreeJS seems to prefer that), in my case I just drop the URL into Cursor and let it figure out the placement of the asset into my game!

@levelsio

72,338 Aufrufe • vor 6 Monaten

Dreamina Seedance 2.0 is by far the best video model I've tried, and Dreamina makes it even better. You can try it in the link below. It's not just about the quality of the output, but about how much control you have over your video's look. Watch my video here. I'm attaching reference images and asking the model to generate a video using them. I can reference each image using the @ symbol to instruct the model which image to use. You can even upload a clip and use its camera movement, styles from an image, and audio vibe from a track. By the way, you can take an existing video and replace, remove, or add elements to it while the model preserves everything else. This is the closest we've gotten to "editing videos like photos".

Dreamina Seedance 2.0 is by far the best video model I've tried, and Dreamina makes it even better. You can try it in the link below. It's not just about the quality of the output, but about how much control you have over your video's look. Watch my video here. I'm attaching reference images and asking the model to generate a video using them. I can reference each image using the @ symbol to instruct the model which image to use. You can even upload a clip and use its camera movement, styles from an image, and audio vibe from a track. By the way, you can take an existing video and replace, remove, or add elements to it while the model preserves everything else. This is the closest we've gotten to "editing videos like photos".

Santiago

46,795 Aufrufe • vor 7 Monaten

I got this custom scorpion rigged, animated and running in my game in one full day with AI. GPT-6 built the entire rig. My part was preparing the model and motion references, then giving feedback. After trying a few approaches, I found a workflow that worked: 1. Give it a model that makes sense. I generated the model with Tripo P2.0, then cleaned it up myself. Low-poly, optimized, split into logical parts. I think that preparation mattered a lot. GPT-6 works on the mesh through code. A manageable vertex count and sensible parts give it a clearer starting point for bone placement and skinning. 2. Show it the movement you want. I took a reference image of the character and used Seedance to generate side-view animation videos. I decided which animations the game needed and selected the takes with the movements I liked. Then I gave GPT-6 the model, the videos and that animation list. There was no existing rig to start from. 3. Compare the animation frame by frame. This was the idea I wanted to test: ask GPT-6 to compare its Blender animation against the reference video frame by frame, from the same view. That gave it concrete poses and timing to work toward. I could point to where the feet should be planted or when the tail should strike. 4. Expect to give feedback. A generated run can look like hopping. An attack can start with a jump you never wanted. Choosing the references matters, and a side view still leaves depth and hidden legs to figure out. It took several iterations. I explained what looked wrong and how I wanted it to move, and GPT-6 kept refining the animation. Once the walk worked, I also had it create left and right strafe animations procedurally from that walk. Those didn't need their own reference videos. By the end of the day, the creature was in Unity. I've recorded the full workflow, including the Blender setup and feedback process:

I got this custom scorpion rigged, animated and running in my game in one full day with AI. GPT-6 built the entire rig. My part was preparing the model and motion references, then giving feedback. After trying a few approaches, I found a workflow that worked: 1. Give it a model that makes sense. I generated the model with Tripo P2.0, then cleaned it up myself. Low-poly, optimized, split into logical parts. I think that preparation mattered a lot. GPT-6 works on the mesh through code. A manageable vertex count and sensible parts give it a clearer starting point for bone placement and skinning. 2. Show it the movement you want. I took a reference image of the character and used Seedance to generate side-view animation videos. I decided which animations the game needed and selected the takes with the movements I liked. Then I gave GPT-6 the model, the videos and that animation list. There was no existing rig to start from. 3. Compare the animation frame by frame. This was the idea I wanted to test: ask GPT-6 to compare its Blender animation against the reference video frame by frame, from the same view. That gave it concrete poses and timing to work toward. I could point to where the feet should be planted or when the tail should strike. 4. Expect to give feedback. A generated run can look like hopping. An attack can start with a jump you never wanted. Choosing the references matters, and a side view still leaves depth and hidden legs to figure out. It took several iterations. I explained what looked wrong and how I wanted it to move, and GPT-6 kept refining the animation. Once the walk worked, I also had it create left and right strafe animations procedurally from that walk. Those didn't need their own reference videos. By the end of the day, the creature was in Unity. I've recorded the full workflow, including the Blender setup and feedback process:

Stefan 3D AI

12,563 Aufrufe • vor 1 Monat

GPT-6 made GTA 6 beach house using MCP tools! Running Astra only through Blender MCP didn’t work for me, since it was mainly using primitive shapes to build the assets. Now, with Atlas workflows and Tripo, that changed! Initially, I thought Tripo P2 would be the way to go: low-poly results straight into Blender. I tried it, but I didn’t get the results I wanted. Don’t get me wrong, P2 is great and a big improvement over P1, I just wanted more detail for this project. So I ended up using Tripo 3.1. First, I needed a good starting point. I gave Astra some concept art and YouTube links, and it generated great reference images to work with. With Atlas workflows, I used those references to generate images for all the individual parts. Using Atlas MCP, I exported them and automatically renamed everything based on the prompts. The next step was feeding the images into Atlas Batch Composer so it could run all the 3D generations in one go. I asked Astra to optimize the generated assets to either 5K or 1K triangles, depending on their form and size. After a few tests, Astra made the process faster and faster. I gave it all 70 high-poly assets and let it run. Astra then took care of the whole build. It imported the optimized assets into Blender and used the reference images to start recreating the house. I only had to give it directional feedback twice and manually rescale a few things. There were still a lot of parts, though. Each beam was a separate object, and I knew that wasn’t ideal if I wanted to export the house to UEFN or Unreal Engine. So I asked Astra to export only the unique assets. Then, using UEFN MCP, it rebuilt everything 1:1 while reusing modular parts like beams and windows. I really enjoyed watching it place all the pieces in UEFN, almost like watching a timelapse of the house being built!

GPT-6 made GTA 6 beach house using MCP tools! Running Astra only through Blender MCP didn’t work for me, since it was mainly using primitive shapes to build the assets. Now, with Atlas workflows and Tripo, that changed! Initially, I thought Tripo P2 would be the way to go: low-poly results straight into Blender. I tried it, but I didn’t get the results I wanted. Don’t get me wrong, P2 is great and a big improvement over P1, I just wanted more detail for this project. So I ended up using Tripo 3.1. First, I needed a good starting point. I gave Astra some concept art and YouTube links, and it generated great reference images to work with. With Atlas workflows, I used those references to generate images for all the individual parts. Using Atlas MCP, I exported them and automatically renamed everything based on the prompts. The next step was feeding the images into Atlas Batch Composer so it could run all the 3D generations in one go. I asked Astra to optimize the generated assets to either 5K or 1K triangles, depending on their form and size. After a few tests, Astra made the process faster and faster. I gave it all 70 high-poly assets and let it run. Astra then took care of the whole build. It imported the optimized assets into Blender and used the reference images to start recreating the house. I only had to give it directional feedback twice and manually rescale a few things. There were still a lot of parts, though. Each beam was a separate object, and I knew that wasn’t ideal if I wanted to export the house to UEFN or Unreal Engine. So I asked Astra to export only the unique assets. Then, using UEFN MCP, it rebuilt everything 1:1 while reusing modular parts like beams and windows. I really enjoyed watching it place all the pieces in UEFN, almost like watching a timelapse of the house being built!

Jerome | InsaneUnreal

79,583 Aufrufe • vor 1 Monat

New clean 3D AI workflow Control Rig physics in UEFN! Been exploring some more hybrid AI workflows lately, and for 3D assets splitting the model into parts is kinda essential. This video shows my first test using AssetHub, one of the cleanest ways i've used to keep the whole generation process organized. It auto-detected the pose in my main image and broke it down into parts, then generated images for each. From there I can just iterate on each piece separately and generate the 3D models in one workflow. AssetHub is still in closed beta atm, so let me know if you want to try it out. Main reference image came from Grok Imagine. All the part images and high poly meshes were done in AssetHub, selected Tripo 3.1 as the main model. After that I ran it through Hunyuan 3D for retopo + unwrap. Final assembly in Blender. Baked normals from high to low poly. End result: under 60K tris, 3 materials, 2K textures. Also Control Rig physics in Unreal Engine are insane. It finally validates in UEFN too, so of course I had to test it out.

New clean 3D AI workflow Control Rig physics in UEFN! Been exploring some more hybrid AI workflows lately, and for 3D assets splitting the model into parts is kinda essential. This video shows my first test using AssetHub, one of the cleanest ways i've used to keep the whole generation process organized. It auto-detected the pose in my main image and broke it down into parts, then generated images for each. From there I can just iterate on each piece separately and generate the 3D models in one workflow. AssetHub is still in closed beta atm, so let me know if you want to try it out. Main reference image came from Grok Imagine. All the part images and high poly meshes were done in AssetHub, selected Tripo 3.1 as the main model. After that I ran it through Hunyuan 3D for retopo + unwrap. Final assembly in Blender. Baked normals from high to low poly. End result: under 60K tris, 3 materials, 2K textures. Also Control Rig physics in Unreal Engine are insane. It finally validates in UEFN too, so of course I had to test it out.

Jerome | InsaneUnreal

83,778 Aufrufe • vor 6 Monaten

Only if education could be this interactive ❤️‍🔥 I've had a looong wish to build something genuinely useful through vibe coding, and I finally did it. A 3D human anatomy application built with Three.js using GPT 5.6 Sol. It all started with a single design image that I created using GPT Image 2.0. I then used it to generate every 3D organ image, one by one. Next, I converted each of those images into 3D models using Tripo (and no, they didn't sponsor this 😄). After that, I opened Codex, wrote a master prompt based on the design, and gave it the prompt, the design image, and all the 3D models. Codex built the first version beautifully, but there was one big problem. Every single 3D model was nearly 120-150 MB. That obviously wasn't practical for the web and was giving a performance of 16fps. After a few iterations, Codex optimized each model down to roughly 2–5.5 MB while preserving the visual quality, reducing the total asset size from ~900 MB to just 28.6 MB. And each model loads on demand. Along the way, Codex also generated those anatomical illustrations showing where each organ sits in the human body, and even created the interactive hotspot markers that explain different parts of every organ. It handled all of that. The process wasn't exactly one shot, but it also wasn't difficult. You just have to do it step by step. It genuinely felt like building something that could make learning anatomy much more engaging. The inspiration came from Dilum Sanjaya's 3D animal plant cell project. I remember seeing it and thinking, "I want to build something like this one day." And I did it :D Live: Code:

Only if education could be this interactive ❤️‍🔥 I've had a looong wish to build something genuinely useful through vibe coding, and I finally did it. A 3D human anatomy application built with Three.js using GPT 5.6 Sol. It all started with a single design image that I created using GPT Image 2.0. I then used it to generate every 3D organ image, one by one. Next, I converted each of those images into 3D models using Tripo (and no, they didn't sponsor this 😄). After that, I opened Codex, wrote a master prompt based on the design, and gave it the prompt, the design image, and all the 3D models. Codex built the first version beautifully, but there was one big problem. Every single 3D model was nearly 120-150 MB. That obviously wasn't practical for the web and was giving a performance of 16fps. After a few iterations, Codex optimized each model down to roughly 2–5.5 MB while preserving the visual quality, reducing the total asset size from ~900 MB to just 28.6 MB. And each model loads on demand. Along the way, Codex also generated those anatomical illustrations showing where each organ sits in the human body, and even created the interactive hotspot markers that explain different parts of every organ. It handled all of that. The process wasn't exactly one shot, but it also wasn't difficult. You just have to do it step by step. It genuinely felt like building something that could make learning anatomy much more engaging. The inspiration came from Dilum Sanjaya's 3D animal plant cell project. I remember seeing it and thinking, "I want to build something like this one day." And I did it :D Live: Code:

The Bugged Dev

2,128,092 Aufrufe • vor 3 Monaten

The battle of the Text/Image to 3D Model 👍- To make this fair, I tested the same image across all platforms and used the first generated result. No cherry picking allowed! I also tested what I think are the 4 top services to use right now. Let me know what you think is the best 3D mesh generation from these platforms however I think it's quite obvious that Tencent Hy 2.5 is currently the king 👑 It wins in overall detail and sharpness, accuracy in relation to the input image, as well as texture generation and projection. Tripo 2.5 comes in second and Rodin 3rd with Trellis in 4th place. However, Rodin has the best topology since it can generate a mesh in quads BUT I left all of them in triangles to keep it fair. Hi3DGen can't be counted as it can't even generate textures and it has no multi-image support. Meshy was another option but the results were not great. Is there any other AI 3D Gen services that you know of that you want me to test as well?

The battle of the Text/Image to 3D Model 👍- To make this fair, I tested the same image across all platforms and used the first generated result. No cherry picking allowed! I also tested what I think are the 4 top services to use right now. Let me know what you think is the best 3D mesh generation from these platforms however I think it's quite obvious that Tencent Hy 2.5 is currently the king 👑 It wins in overall detail and sharpness, accuracy in relation to the input image, as well as texture generation and projection. Tripo 2.5 comes in second and Rodin 3rd with Trellis in 4th place. However, Rodin has the best topology since it can generate a mesh in quads BUT I left all of them in triangles to keep it fair. Hi3DGen can't be counted as it can't even generate textures and it has no multi-image support. Meshy was another option but the results were not great. Is there any other AI 3D Gen services that you know of that you want me to test as well?

Travis Davids

61,232 Aufrufe • vor 1 Jahr

I had an early access to GPT-6 Astra and I can say, everyone in the world now has a 3D designer at their fingertips. I gave it an image of a house and asked to create it in 3D with all the details including toys, appliances and furniture. This a full 3D model reconstruction in Blender with geometry that you can manually tweak and run 60fps as a locally rendered "game" on device.

I had an early access to GPT-6 Astra and I can say, everyone in the world now has a 3D designer at their fingertips. I gave it an image of a house and asked to create it in 3D with all the details including toys, appliances and furniture. This a full 3D model reconstruction in Blender with geometry that you can manually tweak and run 60fps as a locally rendered "game" on device.

Tom Krcha

1,445,541 Aufrufe • vor 2 Monaten

Created an animated convertible car with AI! The part that got me excited from the house experiment was watching Blender assemble everything. Initially I tried the same workflow for the car, but as you can see, assembling a bunch of separately generated parts doesn’t really give a great result here. So I went with a simpler setup. Now Atlas has a new Blender Node, which basically runs Blender MCP inside the workflow. This meant I didn’t have to leave the canvas. It created the reference images, generated the high-poly Tripo 3.1 mesh, baked the low-poly version with the Blender Node, and did the full assembly of the car with the body and wheels. I could even give it images of the badges and license plate, and it created the geometry and placed everything correctly inside the node. The convertible roof rig needed a bit more directing though. But still, I didn’t have to do any weight painting or manually place bones. With some back and forth, Astra created a working skeletal mesh for me to use. In UEFN / Unreal Engine i made everything work together with Control Rig and Level Sequencer.

Created an animated convertible car with AI! The part that got me excited from the house experiment was watching Blender assemble everything. Initially I tried the same workflow for the car, but as you can see, assembling a bunch of separately generated parts doesn’t really give a great result here. So I went with a simpler setup. Now Atlas has a new Blender Node, which basically runs Blender MCP inside the workflow. This meant I didn’t have to leave the canvas. It created the reference images, generated the high-poly Tripo 3.1 mesh, baked the low-poly version with the Blender Node, and did the full assembly of the car with the body and wheels. I could even give it images of the badges and license plate, and it created the geometry and placed everything correctly inside the node. The convertible roof rig needed a bit more directing though. But still, I didn’t have to do any weight painting or manually place bones. With some back and forth, Astra created a working skeletal mesh for me to use. In UEFN / Unreal Engine i made everything work together with Control Rig and Level Sequencer.

Jerome | InsaneUnreal

12,963 Aufrufe • vor 1 Monat

Here's how to do a bit of VFX work using Seedance 2: If you generate with Seedance 2 you often get a great shot but unfortunately with one or more minor artefacts. Instead of discarding the generation, you can actually edit the video using Seedance 2. In my case it i had to remove a character and I did this using simply as the prompt and using the original video as reference: "Remove boy from video". I then regenerated the missing detail (the boy) using an isolated version of the boy that I removed. And then animated using Seedance 2: "the boy runs sideways and stops. white background. he stays in the center of the screen." In the tutorial below, I'll show how I got rid of an artefact in a shot I liked, and used good old compositing to combine a two videos. As always I'll share the link to the Space below.

Here's how to do a bit of VFX work using Seedance 2: If you generate with Seedance 2 you often get a great shot but unfortunately with one or more minor artefacts. Instead of discarding the generation, you can actually edit the video using Seedance 2. In my case it i had to remove a character and I did this using simply as the prompt and using the original video as reference: "Remove boy from video". I then regenerated the missing detail (the boy) using an isolated version of the boy that I removed. And then animated using Seedance 2: "the boy runs sideways and stops. white background. he stays in the center of the screen." In the tutorial below, I'll show how I got rid of an artefact in a shot I liked, and used good old compositing to combine a two videos. As always I'll share the link to the Space below.

Martin LeBlanc

18,312 Aufrufe • vor 5 Monaten

🚨You can now use the new upcoming OpenAI model GPT 5.2 inside Cursor. Here is the full walkthrough. - Open the editor, go to settings and then the model tab. Add a custom model and enter the text "gpt-5.2-high" and "gpt-5.2". - After that you can select the model and ask questions. To verify, I started my test on the usage page which had zero gpt-5.2-high requests and consumption. After the test I could see the details in usage and the cost incurred while using it. Enjoy

🚨You can now use the new upcoming OpenAI model GPT 5.2 inside Cursor. Here is the full walkthrough. - Open the editor, go to settings and then the model tab. Add a custom model and enter the text "gpt-5.2-high" and "gpt-5.2". - After that you can select the model and ask questions. To verify, I started my test on the usage page which had zero gpt-5.2-high requests and consumption. After the test I could see the details in usage and the cost incurred while using it. Enjoy

AshutoshShrivastava

424,035 Aufrufe • vor 11 Monaten

I asked Astra to create a Catan game in three.js and it came out incredibly well. I played it, and the animations make it so much fun. The instructions and info cards make the game easy to learn. It even has AI players and trading. Astra used another game I had started building as a reference. The more games I build, the more skills and assets I have for the next one. It can remix the UI, 3D models, pages, and sounds instead of rebuilding everything. Now I want to see how many other board games I can make from this foundation.

I asked Astra to create a Catan game in three.js and it came out incredibly well. I played it, and the animations make it so much fun. The instructions and info cards make the game easy to learn. It even has AI players and trading. Astra used another game I had started building as a reference. The more games I build, the more skills and assets I have for the next one. It can remix the UI, 3D models, pages, and sounds instead of rebuilding everything. Now I want to see how many other board games I can make from this foundation.

Meng To

583,628 Aufrufe • vor 2 Monaten

It took me less than 10 minutes to create this scene. The longest part was finding the style for my initial image. I used Grok Imagine's extension video to ensure perfect continuity of style, voice, and music. Then I animated it, prompting in my native language without asking for any dialogue. Grok understood everything I asked and created a dialogue between the children in perfect French. I later posted the same children with a prompt in English, and this time, the dialogue was in English. I used Grok Imagine to create the image, animate it, and then extend the video to 30 seconds. I then started again with an image that I modified through editing and used it to tell another story.

It took me less than 10 minutes to create this scene. The longest part was finding the style for my initial image. I used Grok Imagine's extension video to ensure perfect continuity of style, voice, and music. Then I animated it, prompting in my native language without asking for any dialogue. Grok understood everything I asked and created a dialogue between the children in perfect French. I later posted the same children with a prompt in English, and this time, the dialogue was in English. I used Grok Imagine to create the image, animate it, and then extend the video to 30 seconds. I then started again with an image that I modified through editing and used it to tell another story.

Déborah

501,573 Aufrufe • vor 8 Monaten

You can now generate, edit, and convert a reference image into 3D inside one tool. Tripo's Image Generation runs Nano Banana and GPT to build the reference, then turns it into a model. Text or photo in, 3D out. One pipeline, zero handoffs.

You can now generate, edit, and convert a reference image into 3D inside one tool. Tripo's Image Generation runs Nano Banana and GPT to build the reference, then turns it into a model. Text or photo in, 3D out. One pipeline, zero handoffs.

Alvaro Cintas

56,246 Aufrufe • vor 5 Monaten

img2threejs 1.5.1 is out 🚀 Checkout: This release introduces a new approach to image → 3D → Three.js. Image → Tripo → img2threejs → reconstructed geometry → Three.js Instead of using the generated 3D model as the final asset, img2threejs uses it as a reference to rebuild the character into a representation that can be generated and rendered directly in Three.js. No Blender workflow, and no GLB required as the final output. The animation in the demo is still a bit rough because this release is focused on reconstruction, not animation. I’ll be improving that in the next release. Still experimental, but this is a big step toward where I want img2threejs to go.

img2threejs 1.5.1 is out 🚀 Checkout: This release introduces a new approach to image → 3D → Three.js. Image → Tripo → img2threejs → reconstructed geometry → Three.js Instead of using the generated 3D model as the final asset, img2threejs uses it as a reference to rebuild the character into a representation that can be generated and rendered directly in Three.js. No Blender workflow, and no GLB required as the final output. The animation in the demo is still a bit rough because this release is focused on reconstruction, not animation. I’ll be improving that in the next release. Still experimental, but this is a big step toward where I want img2threejs to go.

Nick

117,760 Aufrufe • vor 2 Monaten

Probably I vibe coded a lil startup here? 😭 It has been such a loooong wish of mine to build some kind of 3D experience where I could customize a T-shirt in literally any way possible and it’s finally here. Built with Three.js using GPT 6 Astra, this is a full 3D T-shirt customization studio where you can visualize and customize a realistic shirt directly in the browser. That T-shirt itself was modeled by Astra using Tripo right inside Codex through Tripo Plugin. And you can pretty much do anything with it. You can paint directly on any side of the shirt using different brushes and colors, or even spray paint it in real time just like you would spray on a wall. There are also stickers generated using GPT Image 2.5 that you can place anywhere on the T-shirt, resize, reposition, recolor, layer, and customize however you want. On top of that, there’s support for things like fabric customization, sizing, layers, colors, and even wind simulation to push the realism a little further. Once you’re done, you can export the entire design as a 3D view or export individual images of the T-shirt so you could technically take the design, print it, and maybe even sell it. One of my favorite parts is how the spray painting effect works directly on the 3D T-shirt in real time. I also loved seeing how Astra managed to keep the whole experience performant across devices using a custom BVH implementation along with several CPU side optimizations. And the process of building it was super simple. I generated the initial studio design using GPT Image 2.5, gave that image to Astra with the Tripo Plugin enabled, and it basically handled everything from there. I didn’t have to separately generate a 3D reference, upload it to Tripo, download the asset, give it back to Astra, or manually coordinate any of that. Astra handled the entire flow on its own without needing any additional input from me. Really happy with both the process and how the final result turned out. Live:

Probably I vibe coded a lil startup here? 😭 It has been such a loooong wish of mine to build some kind of 3D experience where I could customize a T-shirt in literally any way possible and it’s finally here. Built with Three.js using GPT 6 Astra, this is a full 3D T-shirt customization studio where you can visualize and customize a realistic shirt directly in the browser. That T-shirt itself was modeled by Astra using Tripo right inside Codex through Tripo Plugin. And you can pretty much do anything with it. You can paint directly on any side of the shirt using different brushes and colors, or even spray paint it in real time just like you would spray on a wall. There are also stickers generated using GPT Image 2.5 that you can place anywhere on the T-shirt, resize, reposition, recolor, layer, and customize however you want. On top of that, there’s support for things like fabric customization, sizing, layers, colors, and even wind simulation to push the realism a little further. Once you’re done, you can export the entire design as a 3D view or export individual images of the T-shirt so you could technically take the design, print it, and maybe even sell it. One of my favorite parts is how the spray painting effect works directly on the 3D T-shirt in real time. I also loved seeing how Astra managed to keep the whole experience performant across devices using a custom BVH implementation along with several CPU side optimizations. And the process of building it was super simple. I generated the initial studio design using GPT Image 2.5, gave that image to Astra with the Tripo Plugin enabled, and it basically handled everything from there. I didn’t have to separately generate a 3D reference, upload it to Tripo, download the asset, give it back to Astra, or manually coordinate any of that. Astra handled the entire flow on its own without needing any additional input from me. Really happy with both the process and how the final result turned out. Live:

The Bugged Dev

52,858 Aufrufe • vor 1 Monat

Apple built a large foundation model and fine-tuned it on multiple tasks. But they are doing something very clever: They load a single model in memory and use different adapters to specialize the model on the fly. I recorded a video to show you how to write the code to do the same thing Apple is doing. I explain everything step by step. Here is what I'll show you in the video: 1. We'll load two datasets 2. Then load a large model 3. Then, we'll fine-tune the model on both datasets I'll use LoRA to fine-tune the model. This process creates two small adapters, each specializing in solving one of the datasets. The base model's original parameters will remain unchanged. From here: 4. We'll generate a list of tasks 5. We'll load the correct adapter to solve each task The large model I'm using needs 346 MB of memory, but I only need to load it once. Each adapter is only 2.7 MB. I only need to load the base model once and pair it with any of the fine-tuned adapters. Minimum memory footprint and I can solve multiple tasks. Hope this helps!

Apple built a large foundation model and fine-tuned it on multiple tasks. But they are doing something very clever: They load a single model in memory and use different adapters to specialize the model on the fly. I recorded a video to show you how to write the code to do the same thing Apple is doing. I explain everything step by step. Here is what I'll show you in the video: 1. We'll load two datasets 2. Then load a large model 3. Then, we'll fine-tune the model on both datasets I'll use LoRA to fine-tune the model. This process creates two small adapters, each specializing in solving one of the datasets. The base model's original parameters will remain unchanged. From here: 4. We'll generate a list of tasks 5. We'll load the correct adapter to solve each task The large model I'm using needs 346 MB of memory, but I only need to load it once. Each adapter is only 2.7 MB. I only need to load the base model once and pair it with any of the fine-tuned adapters. Minimum memory footprint and I can solve multiple tasks. Hope this helps!

Santiago

84,747 Aufrufe • vor 2 Jahren