正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Now this ComfyUI experiment has some potential! #3 Tested the new Trellis 2 Image to 3D and i’m getting decent results. Separating the head and body helped a bit with some details. Also discovering useful helper workflows like removing backgrounds, upscaling and creating Normal maps. Still crazy how it... show more

Jerome | InsaneUnreal

3,790 subscribers

21,077 次观看 • 5 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Not bad! 2K triangles and a bit of manual cleanup. This was a quick test creating a lowpoly 3D model. Tried Tripo for retopology and it did a good job. It does render some inverted normals though. For this lowpoly model it’s fine but inverted normals are a pain when working on highpoly models. I’m going to test some other options like the remesh tool in Blender sculpting. It’s crazy how this Trellis Texturing node works btw, It understands the geometry very well. Watch the end where I made the worst version of an Axe in Blender and it was able to wrap the texture on that model! I would probably spend a bit more time splitting the image up and generating the main parts separately. Also making any signs readable or just remove them.

Not bad! 2K triangles and a bit of manual cleanup. This was a quick test creating a lowpoly 3D model. Tried Tripo for retopology and it did a good job. It does render some inverted normals though. For this lowpoly model it’s fine but inverted normals are a pain when working on highpoly models. I’m going to test some other options like the remesh tool in Blender sculpting. It’s crazy how this Trellis Texturing node works btw, It understands the geometry very well. Watch the end where I made the worst version of an Axe in Blender and it was able to wrap the texture on that model! I would probably spend a bit more time splitting the image up and generating the main parts separately. Also making any signs readable or just remove them.

Jerome | InsaneUnreal

15,052 次观看 • 5 个月前

Tested this concepting workflow. ▶️ Converting a level design image to a 3D asset gallery image ▶️ re-generating segmented subjects into separate high quality images. ▶️ using these images to generate the 3D meshes. First time using 'for loops' in ComfyUI, works great and the prompts are updated for every segment. I used the Nano Banana 2 API node in ComfyUI to generate the final high quality images. Those SAM3 nodes are crazy btw, just set some points and it creates a mask! For the 3D model generation I used the new Tripo Smart Mesh tool, which is fast! The output is not perfect yet. I think in a lot of cases not production ready right now but that depends on the input image and the goal as well. For pre-production / concepting phase it's perfect and for far distance meshes it’s fine. I’m sure these tools keep improving, curious what we can work with in 3-6 months. Minimal cleanup and scaling in Blender and tested the meshes in UEFN / Unreal Engine. After creating the ComfyUI workflow it took less than an hour to do everything.

Tested this concepting workflow. ▶️ Converting a level design image to a 3D asset gallery image ▶️ re-generating segmented subjects into separate high quality images. ▶️ using these images to generate the 3D meshes. First time using 'for loops' in ComfyUI, works great and the prompts are updated for every segment. I used the Nano Banana 2 API node in ComfyUI to generate the final high quality images. Those SAM3 nodes are crazy btw, just set some points and it creates a mask! For the 3D model generation I used the new Tripo Smart Mesh tool, which is fast! The output is not perfect yet. I think in a lot of cases not production ready right now but that depends on the input image and the goal as well. For pre-production / concepting phase it's perfect and for far distance meshes it’s fine. I’m sure these tools keep improving, curious what we can work with in 3-6 months. Minimal cleanup and scaling in Blender and tested the meshes in UEFN / Unreal Engine. After creating the ComfyUI workflow it took less than an hour to do everything.

Jerome | InsaneUnreal

17,267 次观看 • 3 个月前

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 Hunyuan 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 Hunyuan 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

60,813 次观看 • 1 年前

In this experiment I wanted to try something with facial expressions and have it work with native Unreal Engine tools. I did find that generating the head with an open mouth helped to get some extra details. Creating those blend shapes was still not easy and this result is far from perfect. Ideally i want 58 generated expression references and have AI figure that out haha. btw first time baking the high poly details onto the low poly generated character. That worked surprisingly well! Endresult has 34k triangles! Built this character in 4 separate parts in Blender and generated each part in Hunyuan 3D Studio. The original references came from Nano Banana 2 and Grok. Trellis 2 in ComfyUI for the texturing. The animation was done with Control Rig in UEFN / Unreal Engine. With all the experiments so far, file and version management start to become a challenge. Getting files from different platforms with each platform having their own filename logic. I’ll have to find something to keep it more organized. Any suggestions?

In this experiment I wanted to try something with facial expressions and have it work with native Unreal Engine tools. I did find that generating the head with an open mouth helped to get some extra details. Creating those blend shapes was still not easy and this result is far from perfect. Ideally i want 58 generated expression references and have AI figure that out haha. btw first time baking the high poly details onto the low poly generated character. That worked surprisingly well! Endresult has 34k triangles! Built this character in 4 separate parts in Blender and generated each part in Hunyuan 3D Studio. The original references came from Nano Banana 2 and Grok. Trellis 2 in ComfyUI for the texturing. The animation was done with Control Rig in UEFN / Unreal Engine. With all the experiments so far, file and version management start to become a challenge. Getting files from different platforms with each platform having their own filename logic. I’ll have to find something to keep it more organized. Any suggestions?

Jerome | InsaneUnreal

45,921 次观看 • 3 个月前

I've been playing The Killing Antidote by OUR VIDEO GAME IS OUT NOW! and I know it looks like yet another eye-candy game but it actually has some solid gameplay. The combat feels decent, the world is fun to explore and it is not just about the aesthetic… though I have to admit, it doesn't hurt (I am biased, I like fan service). Still a bit rough since it is in Early Access but definitely has potential!

I've been playing The Killing Antidote by OUR VIDEO GAME IS OUT NOW! and I know it looks like yet another eye-candy game but it actually has some solid gameplay. The combat feels decent, the world is fun to explore and it is not just about the aesthetic… though I have to admit, it doesn't hurt (I am biased, I like fan service). Still a bit rough since it is in Early Access but definitely has potential!

Ruby

38,003 次观看 • 1 年前

Currently testing Hunyuan brand new 2.5 model for image to 3D. YUP! It's MAJOR improvement over 2.0, especially with making details look sharper, it can also reconstruct more detail. It also generates PBR materials now and you can automatically rig the character on the website. It's much better than Trellis and Tripo from my testing! Took it into Blender as well to compare Hunyuan 2.5 (on the left) and Hunyuan 2.0 (on the right). I wanted to see the mesh with a solid and material preview. If you're doing 3D printing, these would probably work very well. However...the biggest issue here is still topology which is a complete and utter mess, there's also still issues with texture projection...and the entire model is a single mesh, there needs to be a method to generate the model in parts BUT this tech is certainly improving. As someone that is also a 3D artist, I actually want to see what this tech is capable of generating to output 3D models.

Travis Davids

45,357 次观看 • 1 年前

From generated reference images to riding a robot raptor in Fortnite 🦖 For now mostly the same workflow, but I also used Nano Banana to get that toe claw in the image lol. Other steps: Images from Grok Imagine, Tripo for raw 3D generation, Hunyuan 3D Studio for lowpoly and UV unwrap, Trellis2 in ComfyUI for texturing and AI upscaling. Blender for cleanup, rigging and weight painting. Splitting up the body parts helped to get a more mid-poly result. Also with better control during cleanup. The final result has 28K triangles. Again with the awesome retargeting tools in Unreal Engine / UEFN. I’ll be testing different AI texturing approaches soon. Some parts can get a bit wobbly at times, most notable in hard-surface objects. Also curious if there are any upcoming weight painting tools 😄

From generated reference images to riding a robot raptor in Fortnite 🦖 For now mostly the same workflow, but I also used Nano Banana to get that toe claw in the image lol. Other steps: Images from Grok Imagine, Tripo for raw 3D generation, Hunyuan 3D Studio for lowpoly and UV unwrap, Trellis2 in ComfyUI for texturing and AI upscaling. Blender for cleanup, rigging and weight painting. Splitting up the body parts helped to get a more mid-poly result. Also with better control during cleanup. The final result has 28K triangles. Again with the awesome retargeting tools in Unreal Engine / UEFN. I’ll be testing different AI texturing approaches soon. Some parts can get a bit wobbly at times, most notable in hard-surface objects. Also curious if there are any upcoming weight painting tools 😄

Jerome | InsaneUnreal

40,169 次观看 • 4 个月前

LOVERRUKK ELIXIR NEW ERA #ELIXIRxLoverrukk 💖: #GirlRulesSeries is going to get more and more intense. From Ep.1–4, it’s just the appetizer starting to have some flavor, but it’s not spicy-hot yet. You’ll have to wait a bit longer. 🎤: This still isn’t spicy yet? 💖: Not yet. It’s spicy to some extent, but let’s say it’s elementary-school level spicy for now…like 4–5 chilies. Still around late elementary level. Let’s wait until middle school, high school, and university level first.🌶️🥵🔥 🎤: So after this it’s going to keep leveling up? 💖: Yes. I have to say that the relationships definitely don’t stop at just this. There are still a lot of things that will make you curious and want to keep following the story.

LOVERRUKK ELIXIR NEW ERA #ELIXIRxLoverrukk 💖: #GirlRulesSeries is going to get more and more intense. From Ep.1–4, it’s just the appetizer starting to have some flavor, but it’s not spicy-hot yet. You’ll have to wait a bit longer. 🎤: This still isn’t spicy yet? 💖: Not yet. It’s spicy to some extent, but let’s say it’s elementary-school level spicy for now…like 4–5 chilies. Still around late elementary level. Let’s wait until middle school, high school, and university level first.🌶️🥵🔥 🎤: So after this it’s going to keep leveling up? 💖: Yes. I have to say that the relationships definitely don’t stop at just this. There are still a lot of things that will make you curious and want to keep following the story.

sᴀᴘᴘʜᴏʀɪᴀ #แม่น้องกอหญ้า🍷

91,930 次观看 • 2 个月前

FIRST TEST Seedance 2.0! From my initial tests, this is one of the more impressive AI video models I’ve tried so far. Dynamic motion feels fluid, prompt adherence is solid, and the efficiency really stood out, very little iteration needed. Everything you see here was generated using just one reference image + one prompt. I also tested a 3×3 image grid with no prompt at all, and the results stayed surprisingly consistent. Another highlight: sound design is already included, and it actually works really well. Tested via BytePlus 👉 More detail and access link to try Seedance 2.0 is in the comments.

FIRST TEST Seedance 2.0! From my initial tests, this is one of the more impressive AI video models I’ve tried so far. Dynamic motion feels fluid, prompt adherence is solid, and the efficiency really stood out, very little iteration needed. Everything you see here was generated using just one reference image + one prompt. I also tested a 3×3 image grid with no prompt at all, and the results stayed surprisingly consistent. Another highlight: sound design is already included, and it actually works really well. Tested via BytePlus 👉 More detail and access link to try Seedance 2.0 is in the comments.

Dinda Prasetyo

45,450 次观看 • 4 个月前

MOTHER OF GOD. Lobotomy just got RUNESCAPE running and connecting to the server on a freaking SEGA DREAMCAST. This is still so so so early that it just literally barely started compiling, runs like ass, and of course requires the 32MB double RAM mod and has only been tested so far on an emulator. ...but that is exactly how a some of the most impressive, ambitious DC ports out there started, including Grand Theft Auto 3 and now Counterstrike... Here's the fork for this port:

MOTHER OF GOD. Lobotomy just got RUNESCAPE running and connecting to the server on a freaking SEGA DREAMCAST. This is still so so so early that it just literally barely started compiling, runs like ass, and of course requires the 32MB double RAM mod and has only been tested so far on an emulator. ...but that is exactly how a some of the most impressive, ambitious DC ports out there started, including Grand Theft Auto 3 and now Counterstrike... Here's the fork for this port:

Falco Girgis

21,321 次观看 • 1 年前

Phoenix GenAI’s new generative AI model Image-to-3D is now online. Create high fidelity 3D models importable to Unreal Engine 5 or Unity simply by sending an original image into PhoenixLLM. Better yet, generate the source image using Phoenix GenAI’s Flux and feed it into Image-to-3D. This release marks yet another upgrade of GenAI’s arsenal of capabilities, getting it ready for multi-workflow GenAI agents, in which users will be able to combine text-to-image, image-to-prompt, text-to-video, text-to-3D, and image-to-3D into complex multi-step workflows with simple commands via PhoenixLLM. Image-to-3D is yet another addition to Phoenix’s Vertical AI Solutions for gaming, content, and metaverse. Users are able to use it as a Phoenix-native alternative to SkyNet AI Marketplace’s Tripo Integration earlier this year. #Phoenix $PHB

Phoenix GenAI’s new generative AI model Image-to-3D is now online. Create high fidelity 3D models importable to Unreal Engine 5 or Unity simply by sending an original image into PhoenixLLM. Better yet, generate the source image using Phoenix GenAI’s Flux and feed it into Image-to-3D. This release marks yet another upgrade of GenAI’s arsenal of capabilities, getting it ready for multi-workflow GenAI agents, in which users will be able to combine text-to-image, image-to-prompt, text-to-video, text-to-3D, and image-to-3D into complex multi-step workflows with simple commands via PhoenixLLM. Image-to-3D is yet another addition to Phoenix’s Vertical AI Solutions for gaming, content, and metaverse. Users are able to use it as a Phoenix-native alternative to SkyNet AI Marketplace’s Tripo Integration earlier this year. #Phoenix $PHB

Phoenix AI

30,853 次观看 • 1 年前

This is so bad… and I’m not buying the “Glinda is supposed to act like this” excuse. And it’s concerning for the industry that some critics are saying this could win an Oscar.

This is so bad… and I’m not buying the “Glinda is supposed to act like this” excuse. And it’s concerning for the industry that some critics are saying this could win an Oscar.

.

3,011,473 次观看 • 6 个月前

Running some more tests with Adobe’s new 3D model viewer, Gaussian Splatting generator, and AI image generator, 'Substance 3D Viewer.' It’s still in beta, but it’s already pretty awesome and very easy to use! 🔥 Check out what I was able to create. The models in this video were made with Tripo AI using text-to-3D, and the animations were brought to life using Hailuo and Luma Dream. This tech just keeps getting more useful! #AIArt #3DModeling #Substance3DViewer

Running some more tests with Adobe’s new 3D model viewer, Gaussian Splatting generator, and AI image generator, 'Substance 3D Viewer.' It’s still in beta, but it’s already pretty awesome and very easy to use! 🔥 Check out what I was able to create. The models in this video were made with Tripo AI using text-to-3D, and the animations were brought to life using Hailuo and Luma Dream. This tech just keeps getting more useful! #AIArt #3DModeling #Substance3DViewer

Martin Nebelong

87,635 次观看 • 1 年前

Oh my gosh this was so hard to film! I got it a little bit! 🥰💜🩵🌈🌈🌈 It took forever to get a decent view of the rainbow and it’s still nothing like irl haha I’m so happy with the shift though! I think I might be able to do better this weekend with some natural light!

Sensitive content

Oh my gosh this was so hard to film! I got it a little bit! 🥰💜🩵🌈🌈🌈 It took forever to get a decent view of the rainbow and it’s still nothing like irl haha I’m so happy with the shift though! I think I might be able to do better this weekend with some natural light!

Knotty Myths Toys

12,377 次观看 • 1 年前

SSGI has received a lot of updates like better denoising, improved temporal reprojection, less smearing. Also fixed some device issues. The new version is up to 90% faster than the last version. 🎊 Test it: Still some work and bug fixing to do...

SSGI has received a lot of updates like better denoising, improved temporal reprojection, less smearing. Also fixed some device issues. The new version is up to 90% faster than the last version. 🎊 Test it: Still some work and bug fixing to do...

0beqz

17,316 次观看 • 2 年前

I won't say that this movie is playing out before our eyes even though it is and has been for some time. Made for a reason. Made at certain locations for a reason. Real. Who is protecting the pedos for personal gain and who is willing to do the right thing. Not many are so far, Nobody pretty much. Knowingly protecting pedos and criminals sends the world like an unstoppable train on its way to a satanic world order and it is real. We are in it. Someone in the know MUST do the right thing but they have so much (money and power) to lose so they keep quiet. They often blame and defame the victims even. It's bad. Their free will has been used for personal gain and nothing more. Volume up is needed for several parts TY. The odds of Trump being involved in this movie and the situation we are in now are a billion to 1. This was all intentional without a doubt. They're being tested. And they're all failing.

I won't say that this movie is playing out before our eyes even though it is and has been for some time. Made for a reason. Made at certain locations for a reason. Real. Who is protecting the pedos for personal gain and who is willing to do the right thing. Not many are so far, Nobody pretty much. Knowingly protecting pedos and criminals sends the world like an unstoppable train on its way to a satanic world order and it is real. We are in it. Someone in the know MUST do the right thing but they have so much (money and power) to lose so they keep quiet. They often blame and defame the victims even. It's bad. Their free will has been used for personal gain and nothing more. Volume up is needed for several parts TY. The odds of Trump being involved in this movie and the situation we are in now are a billion to 1. This was all intentional without a doubt. They're being tested. And they're all failing.

Invisidon

15,622 次观看 • 3 个月前

Retopoflow 4 now has several themes to choose from for the retopology overlay and also lets you bump up the vertex and edge size while in Retopoflow mode.

Retopoflow 4 now has several themes to choose from for the retopology overlay and also lets you bump up the vertex and edge size while in Retopoflow mode.

Retopoflow

27,777 次观看 • 4 个月前

My top 3 in voting was 1. cs_alpine 2. de_golden 3. de_warden This is Golden; a very interesting layout that takes a little getting used to, hence me dying a lot at the start of this playtest but it gets better. This is the map I want to play the most due to the layout. This contest had a number of daring and unique layouts (contact is also worth a look); for me this one was the most intriguing and perhaps offers something new to CS2 . Perhaps Overpass stans will get the mental juices flowing on this map. Maps like these offer something new and challenging to CS, beyond the tried and tested layout formula that we are all familiar with. When CS2 add new community maps in updates, I think a video should accompany the changes with fly-throughs and some words on the type of map it is to encourage people to test the waters of these new maps and potentially shape the future of the active duty map pool.

My top 3 in voting was 1. cs_alpine 2. de_golden 3. de_warden This is Golden; a very interesting layout that takes a little getting used to, hence me dying a lot at the start of this playtest but it gets better. This is the map I want to play the most due to the layout. This contest had a number of daring and unique layouts (contact is also worth a look); for me this one was the most intriguing and perhaps offers something new to CS2 . Perhaps Overpass stans will get the mental juices flowing on this map. Maps like these offer something new and challenging to CS, beyond the tried and tested layout formula that we are all familiar with. When CS2 add new community maps in updates, I think a video should accompany the changes with fly-throughs and some words on the type of map it is to encourage people to test the waters of these new maps and potentially shape the future of the active duty map pool.

James Bardolph

18,185 次观看 • 1 年前