Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Some scenes and characters were modeled using Tripo🔜SIGGRAPH2026 . I also used ViggleAI to generate the movements for a guard and a girl, then converted them into an anime style using DomoAI official .#ProjectOdyssey

Ruiholy

61,092 subscribers

24,568 views • 1 year ago •via X (Twitter)

#ProjectOdyssey

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

For “Neoghost” I just wanted to test out a pipeline using World Labs for environments, upres them with Magnific.ai, and then run the characters through ViggleAI.

For “Neoghost” I just wanted to test out a pipeline using World Labs for environments, upres them with Magnific.ai, and then run the characters through ViggleAI.

Jon Finger

35,831 views • 1 year ago

I also designed a reunion scene for the ending, inspired by Japanese independent animator.I used @SunoMusic to draw from his style and incorporated. The tone is warm,I want to convey a sense of hope. PixVerse ProjectOdyssey.ai #aianime

I also designed a reunion scene for the ending, inspired by Japanese independent animator.I used @SunoMusic to draw from his style and incorporated. The tone is warm,I want to convey a sense of hope. PixVerse ProjectOdyssey.ai #aianime

Ruiholy

25,621 views • 1 year ago

You know a technology is good when you don't even realize you've used it. For this scene, - I created the character as an image with Grok Imagine, then the landscape with Grok, and combined everything using Grok Imagine's image references. - I then used video extensions to avoid cuts and style changes. The character is perfectly integrated into the scene, proportions respected and style preserved.

You know a technology is good when you don't even realize you've used it. For this scene, - I created the character as an image with Grok Imagine, then the landscape with Grok, and combined everything using Grok Imagine's image references. - I then used video extensions to avoid cuts and style changes. The character is perfectly integrated into the scene, proportions respected and style preserved.

Déborah

18,892,689 views • 5 months ago

I'm using an ESP32 to sample the car's existing signal, turn, backup, and stop lamps, and then generate the waveform for a hidden, addressable LED strip:

I'm using an ESP32 to sample the car's existing signal, turn, backup, and stop lamps, and then generate the waveform for a hidden, addressable LED strip:

Dave W Plummer

58,432 views • 2 months ago

Built this in 2 hours 😂 I asked chatGPT to generate the 2d assets, used Tripo to generate the 3d version, then I used #threejs for the game dev. its just starting, a lot can be done here.

Built this in 2 hours 😂 I asked chatGPT to generate the 2d assets, used Tripo to generate the 3d version, then I used #threejs for the game dev. its just starting, a lot can be done here.

Ibrahim Boona

41,591 views • 3 months ago

This is a powerful combination: 1) Directing an AI agent to generate characters, locations and all the angles I need for my dialogue shots 2) Using human actors to drive the performance of my characters The agent handles the technical side and I can focus on performance:

This is a powerful combination: 1) Directing an AI agent to generate characters, locations and all the angles I need for my dialogue shots 2) Using human actors to drive the performance of my characters The agent handles the technical side and I can focus on performance:

Halim Alrasihi

51,221 views • 5 months ago

Thanks for the likes!😘 I posed the bird using a rig 🐤 The wings were tricky, so I modeled them with fewer vertices. #blender #b3d

Thanks for the likes!😘 I posed the bird using a rig 🐤 The wings were tricky, so I modeled them with fewer vertices. #blender #b3d

どんぐり眼子

18,965 views • 5 months ago

You can make an entire retro anime style OVA series using AI. MidJourney for perfect retro anime style frames and images. Seedance 2.0 to nail the animation style. Suno for your sound tracks. Never been a better time to explore your ideas.

You can make an entire retro anime style OVA series using AI. MidJourney for perfect retro anime style frames and images. Seedance 2.0 to nail the animation style. Suno for your sound tracks. Never been a better time to explore your ideas.

jboogx.creative

43,075 views • 2 months ago

Kling 2.6 is out, so I tested its image-to-video capabilities. I first visited Higgsfield AI 🧩 and used Nano Banana Pro to generate images of several unique characters. Then I uploaded each image into Kling 2.6 on Higgsfield and converted them into videos one by one. I generated five videos, each 10 seconds long. The quality, expressions, dialogue delivery, and motion are solid. The voice still lacks realism. PS:) Like & Repost Overall, it's impressive. I combined all scenes into a single video. Watch it and share your thoughts...

Kling 2.6 is out, so I tested its image-to-video capabilities. I first visited Higgsfield AI 🧩 and used Nano Banana Pro to generate images of several unique characters. Then I uploaded each image into Kling 2.6 on Higgsfield and converted them into videos one by one. I generated five videos, each 10 seconds long. The quality, expressions, dialogue delivery, and motion are solid. The voice still lacks realism. PS:) Like & Repost Overall, it's impressive. I combined all scenes into a single video. Watch it and share your thoughts...

Beginnersblog

123,782 views • 8 months ago

I was able to create a prompt that helps me generate bulks of images using flow agent. this is a 61 image I generated in one go just by using one character image and it used the style across every 61 prompt And everything was done on mobile.. Yt automators this is for you😎

I was able to create a prompt that helps me generate bulks of images using flow agent. this is a 61 image I generated in one go just by using one character image and it used the style across every 61 prompt And everything was done on mobile.. Yt automators this is for you😎

Peter Buildweb | Al

20,664 views • 1 month ago

How mind blowing is my Pixar-Style intro video? I used Hailuo AI (MiniMax) new #HailuoUnlimitedFrames (Start / End Frames) after training a LoRA on my animated character and used Black Forest Labs 's Flux to generate the images. I also used Freepik (now Magnific) for image editing & video generation (before MiniMax gave the free 7 days!) I wrote the script by myself. Then, used to generate a custom voice. Edited everything in CapCut and created a background soundtrack using Suno This blows my mind. An idea becomes a real thing. Knowledge is power. Know your AI tools -> get MIND BLOWING results! Imagine it -> Acheive it!

How mind blowing is my Pixar-Style intro video? I used Hailuo AI (MiniMax) new #HailuoUnlimitedFrames (Start / End Frames) after training a LoRA on my animated character and used Black Forest Labs 's Flux to generate the images. I also used Freepik (now Magnific) for image editing & video generation (before MiniMax gave the free 7 days!) I wrote the script by myself. Then, used to generate a custom voice. Edited everything in CapCut and created a background soundtrack using Suno This blows my mind. An idea becomes a real thing. Knowledge is power. Know your AI tools -> get MIND BLOWING results! Imagine it -> Acheive it!

Yuval Avidani (יובל אבידני)

16,836 views • 11 months ago

Grok used to for the boys and now every pretty girl I know is using it.

Grok used to for the boys and now every pretty girl I know is using it.

Brittany Hugoboom

12,149 views • 3 months ago

This was way too easy... I created a cute 3D character in minutes instead of hours using this combo: Unbound + Tripo I’m not a 3D artist, but this made the whole process feel simple, playful, and actually accessible. Unbound helped me shape the character idea, then Tripo turned it into a 3D model without the usual complicated workflow If you are a 3D artist or you are just starting, try Unbound. It’s free, open for everyone to experiment with, and a fun way to create characters, creatures, and 3D models without feeling overwhelmed I had so much fun using it today, and I think many visual creators are going to love it. Link in the first comment 👇🏻

This was way too easy... I created a cute 3D character in minutes instead of hours using this combo: Unbound + Tripo I’m not a 3D artist, but this made the whole process feel simple, playful, and actually accessible. Unbound helped me shape the character idea, then Tripo turned it into a 3D model without the usual complicated workflow If you are a 3D artist or you are just starting, try Unbound. It’s free, open for everyone to experiment with, and a fun way to create characters, creatures, and 3D models without feeling overwhelmed I had so much fun using it today, and I think many visual creators are going to love it. Link in the first comment 👇🏻

Amira Zairi

186,621 views • 3 months ago

A1: Here is an example of using #ai tools #midjourney and #D-ID to create Poe introducing himself. I used #CHATGPT to write an intro in his style. Students then fact check, and compare to his style. #AppleEDULeaderChat #AppleEDUCommunity #AIClassroom

A1: Here is an example of using #ai tools #midjourney and #D-ID to create Poe introducing himself. I used #CHATGPT to write an intro in his style. Students then fact check, and compare to his style. #AppleEDULeaderChat #AppleEDUCommunity #AIClassroom

Amanda Fox ✈️Cincy✈️Vegas ✈️ Palo Alto ✈️ATL

34,250 views • 3 years ago

On their way back from spelunking, they found an old dry well and decided to climb down. At the bottom was an opening that led further underground into more caves. They were converted into a dungeon and someone had been using them recently. There are so many caves in The South.

On their way back from spelunking, they found an old dry well and decided to climb down. At the bottom was an opening that led further underground into more caves. They were converted into a dungeon and someone had been using them recently. There are so many caves in The South.

Blonde of War (JJ)

160,535 views • 1 month ago

I just made a Tesla Ad video using Grok Imagine used last frame to extend video clips and than took a blank dark image to generate official Tesla-style logo video with Tesla name Tesla logo prompt: "Animate Tesla logo with Tesla name below in red"

X Freeze

1,122,252 views • 1 year ago

☪️ Muslim men in Japan named Mohammed and Ali were arrested for trying to sell meth with anime characters on them (to trick people into using them). Apparently they had tens of kilograms of methamphetamine which they planned to make money from selling.

☪️ Muslim men in Japan named Mohammed and Ali were arrested for trying to sell meth with anime characters on them (to trick people into using them). Apparently they had tens of kilograms of methamphetamine which they planned to make money from selling.

鈴森はるか『haruka suzumori』 🇯🇵

18,904 views • 9 months ago

💙~MODEL SHOWCASE~❤️ Model is ready for the debut~! I also used Gillies Warudo addon to improve the movements! I also made sure to add some stretchiness and and a lot of flowy physics to everything~!!❤️‍🔥

Sensitive content

💙~MODEL SHOWCASE~❤️ Model is ready for the debut~! I also used Gillies Warudo addon to improve the movements! I also made sure to add some stretchiness and and a lot of flowy physics to everything~!!❤️‍🔥

FindingANest

27,046 views • 10 months ago

Seedance 2.5 Test 480p - 720p I created a fight scene in a Chinese donghua style. For my prompt tests, I usually generate 5-second clips at 480p just to see how the style and overall look turn out. Interestingly, action scenes look cleaner at 480p. At 720p, they become noticeably blurrier or noisier, even though both were generated with the exact same prompt. The timing also seems much more consistent across generations now. Seedance 2.0 wasn't following timestamps reliably, so I rarely used them back then. With 2.5, I have started using timestamps again. I upscaled the 480p with Topaz. What do you think? Also you can check the prompt below.

Seedance 2.5 Test 480p - 720p I created a fight scene in a Chinese donghua style. For my prompt tests, I usually generate 5-second clips at 480p just to see how the style and overall look turn out. Interestingly, action scenes look cleaner at 480p. At 720p, they become noticeably blurrier or noisier, even though both were generated with the exact same prompt. The timing also seems much more consistent across generations now. Seedance 2.0 wasn't following timestamps reliably, so I rarely used them back then. With 2.5, I have started using timestamps again. I upscaled the 480p with Topaz. What do you think? Also you can check the prompt below.

Kōda

27,668 views • 15 days ago

Kitbashed a base body for Chun Li using her different body parts, converted to quads, and modeled the missing parts to fit her proportions. Her original body texture has the parts that were deleted in-game (like feet, crotch area), so it was easy to reunwrap to match.

Kitbashed a base body for Chun Li using her different body parts, converted to quads, and modeled the missing parts to fit her proportions. Her original body texture has the parts that were deleted in-game (like feet, crotch area), so it was easy to reunwrap to match.

A$AP BERG

28,225 views • 1 year ago