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.

Showing some hair details✨ Each strand has multiple adjustable parameters for better customization. A quick Live2D 5.2 vs 5.3 coloring comparison is added at the end, 5.3 handles gradients and dark hair more nicely. We’ll update once VTube Studio supports it 💛 #Live2D #Vtuber

Kyoki_studio@Art&Live2D

31,106 subscribers

25,025 views • 9 months ago •via X (Twitter)

Gaming Arts Science & Technology #Live2D #Vtuber

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Live2D 5.3 is officially here with groundbreaking features! While VTube Studio (VTS) support might take some time, you can actually use 5.3 features RIGHT NOW using #NizimaLIVE (nizima LIVE - Live2D公式VTuberアプリ )! Here is my model made in 5.3 running smoothly!!!👇 ✅Pros: -Official App: Developed by Live2D themselves. -5.3 Beta Support: Includes new Blend Modes and Off-screen Rendering! -Perfect Sync: Full iOS support. -Precision: Extremely fine-tuned parameter adjustments. -Effects: Built-in preset effects. ⚠️Notes: -Commercial use requires a paid subscription. -No direct Vbridger support (though parameters like JawOpen, Funnel, Pucker, and Shrug are compatible! Plenty of room for expressions). -Lacks YouTube/Twitch integration plugins. Give the free version a try! If you have any questions, feel free to ask me👍

Live2D 5.3 is officially here with groundbreaking features! While VTube Studio (VTS) support might take some time, you can actually use 5.3 features RIGHT NOW using #NizimaLIVE (nizima LIVE - Live2D公式VTuberアプリ )! Here is my model made in 5.3 running smoothly!!!👇 ✅Pros: -Official App: Developed by Live2D themselves. -5.3 Beta Support: Includes new Blend Modes and Off-screen Rendering! -Perfect Sync: Full iOS support. -Precision: Extremely fine-tuned parameter adjustments. -Effects: Built-in preset effects. ⚠️Notes: -Commercial use requires a paid subscription. -No direct Vbridger support (though parameters like JawOpen, Funnel, Pucker, and Shrug are compatible! Plenty of room for expressions). -Lacks YouTube/Twitch integration plugins. Give the free version a try! If you have any questions, feel free to ask me👍

Noy Ururuka🎀🐺illust/rigger

29,257 views • 8 months ago

Mochi-chan is now officially available 🥹! Enjoy 25% off for the first week of launch — don’t let this deal slip away! Boasting 397 adjustable parameters, this model can achieve far more effects than the ones displayed in the showcase. All presets are also configured as one-click buttons for quick transformations, promising a fun and seamless customization experience ✨. More updates for this model are coming your way soon! Purchase link: #CustomizableVtuber #Live2D #Chibi

Mochi-chan is now officially available 🥹! Enjoy 25% off for the first week of launch — don’t let this deal slip away! Boasting 397 adjustable parameters, this model can achieve far more effects than the ones displayed in the showcase. All presets are also configured as one-click buttons for quick transformations, promising a fun and seamless customization experience ✨. More updates for this model are coming your way soon! Purchase link: #CustomizableVtuber #Live2D #Chibi

MochiNeko🐈️🐾LIVE2D

56,724 views • 8 months ago

Coming soon! Someone requested a sleeved version of my exisiting controller asset a few weeks ago and with the timing and the new vtube studio native controller support, I decided it was time for an overall upgrade! I still have a few kinks to work through but I have huge respect for live2d artists working on a controller asset right now because the parameters ( along with the amount of things that go wrong ) are crazy with this one. Anyways so excited for all these new updates, stick to the end of the video to see all the customization options! Oh and this is with 0 camera tracking and best used with gyro controller! #live2dwip #vtubestudio

Coming soon! Someone requested a sleeved version of my exisiting controller asset a few weeks ago and with the timing and the new vtube studio native controller support, I decided it was time for an overall upgrade! I still have a few kinks to work through but I have huge respect for live2d artists working on a controller asset right now because the parameters ( along with the amount of things that go wrong ) are crazy with this one. Anyways so excited for all these new updates, stick to the end of the video to see all the customization options! Oh and this is with 0 camera tracking and best used with gyro controller! #live2dwip #vtubestudio

Chisa ♡ Live2D Artist

96,352 views • 6 months ago

Creating the outfits of your dreams is about to get even easier! ♡ Dress Up View: Tired of asking your friends if your hair looks ok in the back!? Freely control your view while in Dress Up Mode, helping you zoom into small details while coloring/toggling, seeing how your hair looks from behind, and perfecting accessories like back bows and backpacks! ♡ New Multiselect Color Button: Use this special setting while in Coloring Mode to select and change multiple colors at the same time, (works for furniture too!) and a new "Reset Colors" button for accessories when you need a fresh start! ♡ New "Expand" button for Designs! See more patterns at once and scroll through them easier to find the perfect textures for your outfits, located in 99 Colors & Designs Palette! P.S.... ❤️RED BUTTON!!❤️ ♡ Toggles Interface Cutesy Glow-Up! Includes a Back and Next button on the "Cycle Through Variations" feature to make designing an item exactly how you want it easier! These helpful new features will be released in the upcoming update to Royale High! ✨

Creating the outfits of your dreams is about to get even easier! ♡ Dress Up View: Tired of asking your friends if your hair looks ok in the back!? Freely control your view while in Dress Up Mode, helping you zoom into small details while coloring/toggling, seeing how your hair looks from behind, and perfecting accessories like back bows and backpacks! ♡ New Multiselect Color Button: Use this special setting while in Coloring Mode to select and change multiple colors at the same time, (works for furniture too!) and a new "Reset Colors" button for accessories when you need a fresh start! ♡ New "Expand" button for Designs! See more patterns at once and scroll through them easier to find the perfect textures for your outfits, located in 99 Colors & Designs Palette! P.S.... ❤️RED BUTTON!!❤️ ♡ Toggles Interface Cutesy Glow-Up! Includes a Back and Next button on the "Cycle Through Variations" feature to make designing an item exactly how you want it easier! These helpful new features will be released in the upcoming update to Royale High! ✨

Royale High ✨

467,394 views • 2 years ago

Hello everyone! 👋 I'm the Assistant of Chaliz! 🛠️ The second episode of recreating your OCs with LizMeta is here! 🎉 To those whose OCs weren't selected this time, it might be for various reasons, for example: We thought your OC required texture modifications. The specific features involved are still under development. We simply ran out of time and could only do this many customizations! etc... Please note that this doesn't mean your OC can't be created at all! Everyone's OCs are just too adorable! 🥰 I'm a bit scared I didn't do them justice, boo-hoo... 😭 (Haha, actually, I tried my best! I looked at your reference pictures, avatars, and even checked your profiles to guess your favorite styles... 👀) In fact, you can probably tell that the model has a huge potential range. If the OC I created looks different from your style, ahhhhh, please don't doubt the model!! 😱 It might just be a problem with my customization skills: ( A huge thank you to everyone who sent in pictures for our testing! Don't be discouraged if you weren't chosen this time! There is one last chance! For the final round, I will show the entire customization process, and the number of participants might not be very high this time, so I hope you can help by liking, following, and sharing! Thank you so much!! A Small Note Regarding Gradients As you can see, the hair texture of our model is excellent and looks just like hand-drawn art by an artist. All the highlights are separate layers, ensuring they move naturally with the hair and preventing any separation issues. The rigging of the entire model is also very natural and dynamic. ✨ However, precisely because of this high quality, the Live2D production software is struggling to handle the load and is almost at its limit. Therefore, we regret to inform you that we cannot add gradients to the model's base mesh. 🙅‍♂️ You will only be able to achieve a gradient effect by modifying the textures. To help with this, we will provide a gradient hair texture for easy modification. If you have more specific needs, you will need to modify the textures yourself or ask another artist to do it for you. Currently, we are working on adding easy-to-adjust gradients to the "Head-Only" model, but it is still in the testing phase and might be included in the second wave of updates. Ahhhhh, we really hope the Live2D team optimizes this stuff ASAP!!! 😫 We really want to add everything into the model, but the truth is, we're just out of space... so sad. When Live2D gets optimized, we can finally add gradients directly into the model itself! #Live2D #vtuber #LizMetaCustomizableVtuber

Hello everyone! 👋 I'm the Assistant of Chaliz! 🛠️ The second episode of recreating your OCs with LizMeta is here! 🎉 To those whose OCs weren't selected this time, it might be for various reasons, for example: We thought your OC required texture modifications. The specific features involved are still under development. We simply ran out of time and could only do this many customizations! etc... Please note that this doesn't mean your OC can't be created at all! Everyone's OCs are just too adorable! 🥰 I'm a bit scared I didn't do them justice, boo-hoo... 😭 (Haha, actually, I tried my best! I looked at your reference pictures, avatars, and even checked your profiles to guess your favorite styles... 👀) In fact, you can probably tell that the model has a huge potential range. If the OC I created looks different from your style, ahhhhh, please don't doubt the model!! 😱 It might just be a problem with my customization skills: ( A huge thank you to everyone who sent in pictures for our testing! Don't be discouraged if you weren't chosen this time! There is one last chance! For the final round, I will show the entire customization process, and the number of participants might not be very high this time, so I hope you can help by liking, following, and sharing! Thank you so much!! A Small Note Regarding Gradients As you can see, the hair texture of our model is excellent and looks just like hand-drawn art by an artist. All the highlights are separate layers, ensuring they move naturally with the hair and preventing any separation issues. The rigging of the entire model is also very natural and dynamic. ✨ However, precisely because of this high quality, the Live2D production software is struggling to handle the load and is almost at its limit. Therefore, we regret to inform you that we cannot add gradients to the model's base mesh. 🙅‍♂️ You will only be able to achieve a gradient effect by modifying the textures. To help with this, we will provide a gradient hair texture for easy modification. If you have more specific needs, you will need to modify the textures yourself or ask another artist to do it for you. Currently, we are working on adding easy-to-adjust gradients to the "Head-Only" model, but it is still in the testing phase and might be included in the second wave of updates. Ahhhhh, we really hope the Live2D team optimizes this stuff ASAP!!! 😫 We really want to add everything into the model, but the truth is, we're just out of space... so sad. When Live2D gets optimized, we can finally add gradients directly into the model itself! #Live2D #vtuber #LizMetaCustomizableVtuber

茶粒子kokoda

48,602 views • 9 months ago

Everyone's support of our customizable model has been so encouraging and pushes me to learn more, not just as a 3D artist, but also as a programmer! 🩷 Unlike a live2D customizable model, there's no existing framework for a customizable 3D model. I had to learn how to code in each slider, parameter, color picker, and asset selection menu. I continue to push myself with every update I post here! -^u^- Now, the body sliders no longer cause clipping, each individual clothing item has their own parameters to prevent clipping! 💕 The arms, shoulders, and wrists are also now more effected by the plus size slider.✨ And I made a slider for the face/neck, but I haven't coded it in yet. These new features (along with a lot more!) will all be available for free in our first update!🩷

Everyone's support of our customizable model has been so encouraging and pushes me to learn more, not just as a 3D artist, but also as a programmer! 🩷 Unlike a live2D customizable model, there's no existing framework for a customizable 3D model. I had to learn how to code in each slider, parameter, color picker, and asset selection menu. I continue to push myself with every update I post here! -^u^- Now, the body sliders no longer cause clipping, each individual clothing item has their own parameters to prevent clipping! 💕 The arms, shoulders, and wrists are also now more effected by the plus size slider.✨ And I made a slider for the face/neck, but I haven't coded it in yet. These new features (along with a lot more!) will all be available for free in our first update!🩷

Pastell & Palette🤍 3D Customizable Model!

22,291 views • 11 months ago

The biggest update to DefiLlama's dashboard editor ever. Building and customizing dashboards is now more intuitive and faster. Some highlights from the new version our llamas cooked: 1) Quick add: cmd+k in edit mode, type "uniswap fees" or "aave vs compound revenue" and the card is added 2) Parameters: dashboard level chain / protocol switch in the top bar, all connected cards update; build one dashboard and use it for multiple protocols or chains 3) Sections and tabs: group cards into collapsible sections or split the dashboard into tabs 4) Custom data: upload CSVs and chart them ui polish kit for the whole dashboards area 5) Hover tooltips sync between charts, add annotations, and more Reminder that you can create one custom dashboard for free:

The biggest update to DefiLlama's dashboard editor ever. Building and customizing dashboards is now more intuitive and faster. Some highlights from the new version our llamas cooked: 1) Quick add: cmd+k in edit mode, type "uniswap fees" or "aave vs compound revenue" and the card is added 2) Parameters: dashboard level chain / protocol switch in the top bar, all connected cards update; build one dashboard and use it for multiple protocols or chains 3) Sections and tabs: group cards into collapsible sections or split the dashboard into tabs 4) Custom data: upload CSVs and chart them ui polish kit for the whole dashboards area 5) Hover tooltips sync between charts, add annotations, and more Reminder that you can create one custom dashboard for free:

DefiLlama.com

15,105 views • 19 days ago

🍟#Live2D #Live2DWIP🌭 Progress Update!! Lately, I've been a bit lazy, so it took me quite a bit of time to finish the coloring for the back and additional parts. That said, I'm really satisfied with the overall results! As shown in the video, aside from the 3D effect, the chest size and outfit switching features are functioning well. (I’m not showing the outfit switching this time.) I also used physics settings to drive the full-body motion parameters, so now the posture movement logic is the same as traditional Live2D dolls—controlled entirely by head coordinates. Currently, I'm using only the culling feature for 3D simulation, which is why some Live2D-specific clipping issues appear in the visuals. The 2D clipping mainly happens in areas like the sides of the arms and legs. I plan to address this by adding Draw Order settings later, which should greatly improve the situation. Additionally, there's a gap where the ArtMeshes for the front and back connect. It seems that even though I've meticulously aligned the original warp deformers, this issue still persists. I suspect the problem lies with the PSD artwork. If I extend the range of the graphics a bit more, this should be resolved. Overall, I'm feeling really optimistic about the progress so far! The only downside is that I might not finish this Halloween outfit until Christmas, hahaha🫠🫠🫠

🍟#Live2D #Live2DWIP🌭 Progress Update!! Lately, I've been a bit lazy, so it took me quite a bit of time to finish the coloring for the back and additional parts. That said, I'm really satisfied with the overall results! As shown in the video, aside from the 3D effect, the chest size and outfit switching features are functioning well. (I’m not showing the outfit switching this time.) I also used physics settings to drive the full-body motion parameters, so now the posture movement logic is the same as traditional Live2D dolls—controlled entirely by head coordinates. Currently, I'm using only the culling feature for 3D simulation, which is why some Live2D-specific clipping issues appear in the visuals. The 2D clipping mainly happens in areas like the sides of the arms and legs. I plan to address this by adding Draw Order settings later, which should greatly improve the situation. Additionally, there's a gap where the ArtMeshes for the front and back connect. It seems that even though I've meticulously aligned the original warp deformers, this issue still persists. I suspect the problem lies with the PSD artwork. If I extend the range of the graphics a bit more, this should be resolved. Overall, I'm feeling really optimistic about the progress so far! The only downside is that I might not finish this Halloween outfit until Christmas, hahaha🫠🫠🫠

📐Hephaestus📏Live2D匠人魂

62,232 views • 1 year ago

Review: The Witcher 3 Remastered is a massive overhaul to an all time classic RPG - but I have some thoughts. ▫️ Remaster looks sharper, with much higher quality assets across the board ▫️ Ray tracing has been massively improved. Bounce lighting is way better, water reflections finally look amazing, and the shadows are sharper and more accurate ▫️ I do think the lighting needs another pass in a few key areas like Kaer Morhen ▫️ The original has more contrast while the remaster has an overall brighter look (which some may prefer) ▫️ While the remaster is probably more 'accurate' overall, it does lose some of that stylized look from the original ▫️ Performance is definitely much heavier, especially with ray tracing ▫️ The dynamic camera during combat is a big improvement ▫️ Dodging feels smoother and animations are a lot snappier and more responsive ▫️ Meditation is a lot better, it happens in realtime so you can cancel it exactly at the right moment ▫️ Roach handles better and doesn't get stuck on objects quite as much ▫️ Skill tree system has been overhauled ▫️ Transmog has been added (unlocked at Skellige) ▫️ Photo Mode has been greatly improved ▫️ Movement feels better and more responsive There are a lot more changes, but overall it's a nice improvement to an already amazing game. Nothing groundbreaking but some pretty good changes for a free update! The visuals are absolutely stunning in places like Skellige and Toussaint. And it does look much sharper and higher resolution overall. But the lighting needs a few more tweaks in the areas I mentioned to retain the look and feel of the original. It certainly doesn't look bad, just not quite as punchy. Overall, I really enjoyed my time with it and was immediately hooked back into the world of The Witcher. Can't wait for Songs of the Past next year, and of course, The Witcher IV! Final Score: 9.5/10 Thanks to CD Projekt Red for providing code for review. #TheWitcher #TheWitcher3 #Witcher3Remastered

Review: The Witcher 3 Remastered is a massive overhaul to an all time classic RPG - but I have some thoughts. ▫️ Remaster looks sharper, with much higher quality assets across the board ▫️ Ray tracing has been massively improved. Bounce lighting is way better, water reflections finally look amazing, and the shadows are sharper and more accurate ▫️ I do think the lighting needs another pass in a few key areas like Kaer Morhen ▫️ The original has more contrast while the remaster has an overall brighter look (which some may prefer) ▫️ While the remaster is probably more 'accurate' overall, it does lose some of that stylized look from the original ▫️ Performance is definitely much heavier, especially with ray tracing ▫️ The dynamic camera during combat is a big improvement ▫️ Dodging feels smoother and animations are a lot snappier and more responsive ▫️ Meditation is a lot better, it happens in realtime so you can cancel it exactly at the right moment ▫️ Roach handles better and doesn't get stuck on objects quite as much ▫️ Skill tree system has been overhauled ▫️ Transmog has been added (unlocked at Skellige) ▫️ Photo Mode has been greatly improved ▫️ Movement feels better and more responsive There are a lot more changes, but overall it's a nice improvement to an already amazing game. Nothing groundbreaking but some pretty good changes for a free update! The visuals are absolutely stunning in places like Skellige and Toussaint. And it does look much sharper and higher resolution overall. But the lighting needs a few more tweaks in the areas I mentioned to retain the look and feel of the original. It certainly doesn't look bad, just not quite as punchy. Overall, I really enjoyed my time with it and was immediately hooked back into the world of The Witcher. Can't wait for Songs of the Past next year, and of course, The Witcher IV! Final Score: 9.5/10 Thanks to CD Projekt Red for providing code for review. #TheWitcher #TheWitcher3 #Witcher3Remastered

KAMI

1,318,023 views • 6 days ago

Finally got our hands on Seedance 2.0 (through YouArt) and ran it head-to-head with Kling AI 3.0. Here’s what stood out: Seedance 2.0’s physics feel stronger right away. The movement just looks more natural and realistic, especially in bigger physical actions. It also handles continuity across multiple shots from a single prompt better than I expected, which makes scene building a lot easier. And on the audio side, the lip sync generally holds up better than Kling. But here’s the tradeoff: Both models struggle with fine details. Background faces and smaller elements still get a bit messy. Seedance currently outputs at 720p, while Kling 3.0 supports 1080p, so Kling has the edge in overall sharpness. Even with upscaling, Seedance doesn’t fully recover those tiny details. Verdict🏆: Seedance 2.0 is a real step forward, especially for motion realism, but it’s definitely not the “end of Hollywood.” Check out our latest tutorial where we show you how to get access to this new model and take a deep look at the quality of this new AI Video Generator:

Finally got our hands on Seedance 2.0 (through YouArt) and ran it head-to-head with Kling AI 3.0. Here’s what stood out: Seedance 2.0’s physics feel stronger right away. The movement just looks more natural and realistic, especially in bigger physical actions. It also handles continuity across multiple shots from a single prompt better than I expected, which makes scene building a lot easier. And on the audio side, the lip sync generally holds up better than Kling. But here’s the tradeoff: Both models struggle with fine details. Background faces and smaller elements still get a bit messy. Seedance currently outputs at 720p, while Kling 3.0 supports 1080p, so Kling has the edge in overall sharpness. Even with upscaling, Seedance doesn’t fully recover those tiny details. Verdict🏆: Seedance 2.0 is a real step forward, especially for motion realism, but it’s definitely not the “end of Hollywood.” Check out our latest tutorial where we show you how to get access to this new model and take a deep look at the quality of this new AI Video Generator:

Curious Refuge

58,989 views • 7 months ago

✨"Cubism Editor 5.4.00 alpha1" limited release until September 14, 2026✨ We are also releasing Cubism 5 SDK for Unity R7 alpha1, which supports these new features, at the same time. Check out the accompanying digest video to learn about the main new features. 🔥[New Features] ✏️ [Parameter Controller SDK Support] Parameter controllers (IK) are now supported in the SDK. You can configure them directly on the model and export them as runtime files. Additionally, a new "target-only" controller can be defined to allow the controller to follow a path. ✏️ [Model State Set] A new model state set feature has been added. You can register working states in a dedicated palette, enabling you to recall specific states of visibility, lock, and parameter values with a single click. This helps you work more efficiently by allowing you to switch between states tailored to different tasks. ✏️[Expanded Editing Support for External Application Integration API ] The external application integration API has been expanded to include object editing and more. You can now integrate an API to directly add and edit parts, deformers, and parameters on models in the editor. ✏️[Enhanced automatic layout for texture atlases] The automatic layout algorithm for texture atlas editing has been completely redesigned. This enables more efficient packing with less unused space. You can configure the layout settings individually for each texture, allowing for flexible layouts. [How to use Cubism 5.4 alpha] Please see the announcement page for details on downloading and feedback. ⚠Notes on using the alpha version - The alpha version is provided for the purpose of gathering feedback on the usability and performance of new features. - Usage Period: Until September 14, 2026. - Please be sure to create a backup, as there is a possibility of data corruption. - Alpha version data and SDK outputs are not guaranteed to function properly and we do not provide support for it. #Live2D #cubism54_alpha

✨"Cubism Editor 5.4.00 alpha1" limited release until September 14, 2026✨ We are also releasing Cubism 5 SDK for Unity R7 alpha1, which supports these new features, at the same time. Check out the accompanying digest video to learn about the main new features. 🔥[New Features] ✏️ [Parameter Controller SDK Support] Parameter controllers (IK) are now supported in the SDK. You can configure them directly on the model and export them as runtime files. Additionally, a new "target-only" controller can be defined to allow the controller to follow a path. ✏️ [Model State Set] A new model state set feature has been added. You can register working states in a dedicated palette, enabling you to recall specific states of visibility, lock, and parameter values with a single click. This helps you work more efficiently by allowing you to switch between states tailored to different tasks. ✏️[Expanded Editing Support for External Application Integration API ] The external application integration API has been expanded to include object editing and more. You can now integrate an API to directly add and edit parts, deformers, and parameters on models in the editor. ✏️[Enhanced automatic layout for texture atlases] The automatic layout algorithm for texture atlas editing has been completely redesigned. This enables more efficient packing with less unused space. You can configure the layout settings individually for each texture, allowing for flexible layouts. [How to use Cubism 5.4 alpha] Please see the announcement page for details on downloading and feedback. ⚠Notes on using the alpha version - The alpha version is provided for the purpose of gathering feedback on the usability and performance of new features. - Usage Period: Until September 14, 2026. - Please be sure to create a backup, as there is a possibility of data corruption. - Alpha version data and SDK outputs are not guaranteed to function properly and we do not provide support for it. #Live2D #cubism54_alpha

Live2D

103,790 views • 2 months ago

A programmer with 30+ years of experience stopped writing most of his code For the past 32 days, he’s been building Brutal Derby for 10–12 hours a day using mostly GPT. Instead of coding, he spends his time designing systems, testing, profiling performance and telling the AI what needs to change. The result already has: > 24 cars running at once > real-time vehicle deformation > destructible parts and debris > dynamic weather > weapons and explosions > multiple arenas + customization And this definitely isn’t a one-shot project. Some systems went through 4–5 complete implementations, and the creator describes the whole game as more like “1000+ shot.” I think this is a much better example of where AI coding is heading. Developers won’t stop working. They’ll spend less time typing code and more time deciding what should actually be built.

A programmer with 30+ years of experience stopped writing most of his code For the past 32 days, he’s been building Brutal Derby for 10–12 hours a day using mostly GPT. Instead of coding, he spends his time designing systems, testing, profiling performance and telling the AI what needs to change. The result already has: > 24 cars running at once > real-time vehicle deformation > destructible parts and debris > dynamic weather > weapons and explosions > multiple arenas + customization And this definitely isn’t a one-shot project. Some systems went through 4–5 complete implementations, and the creator describes the whole game as more like “1000+ shot.” I think this is a much better example of where AI coding is heading. Developers won’t stop working. They’ll spend less time typing code and more time deciding what should actually be built.

Hakimi Eiqbal

34,809 views • 29 days ago

✨"Cubism Editor 5.4.00 alpha2" limited release until October 18, 2026✨ Check out the accompanying digest video to learn about the main new features. 🔥[New Features Added] ✏️[The PSD Import feature has been significantly enhanced] The merging process previously performed in paint tools has been integrated into the editor, allowing you to proceed with model creation in simple steps. You can merge multiple layers and handle them as a single Model image. You can also change how they are merged after importing, and perform preparation steps such as cleaning up stray pixels etc., all within the editor. If there are changes to the composition of the Mode Guide Image, you can also select the replacement image directly. Please give alpha2 a try! [How to use Cubism 5.4 alpha] Please see the announcement page for details on downloading and feedback. ⚠Notes on using the alpha version - alpha1 Usage Period: Until September 15, 2026. - alpha2 Usage Period: Until October 18, 2026. - The alpha version is provided for the purpose of gathering feedback on the usability and performance of new features. - Please be sure to create a backup, as there is a possibility of data corruption. - Alpha version data and SDK outputs are not guaranteed to function properly and we do not provide support for it. #Live2D #cubism54_alpha

✨"Cubism Editor 5.4.00 alpha2" limited release until October 18, 2026✨ Check out the accompanying digest video to learn about the main new features. 🔥[New Features Added] ✏️[The PSD Import feature has been significantly enhanced] The merging process previously performed in paint tools has been integrated into the editor, allowing you to proceed with model creation in simple steps. You can merge multiple layers and handle them as a single Model image. You can also change how they are merged after importing, and perform preparation steps such as cleaning up stray pixels etc., all within the editor. If there are changes to the composition of the Mode Guide Image, you can also select the replacement image directly. Please give alpha2 a try! [How to use Cubism 5.4 alpha] Please see the announcement page for details on downloading and feedback. ⚠Notes on using the alpha version - alpha1 Usage Period: Until September 15, 2026. - alpha2 Usage Period: Until October 18, 2026. - The alpha version is provided for the purpose of gathering feedback on the usability and performance of new features. - Please be sure to create a backup, as there is a possibility of data corruption. - Alpha version data and SDK outputs are not guaranteed to function properly and we do not provide support for it. #Live2D #cubism54_alpha

Live2D

25,139 views • 27 days ago

The Genie 3 release is a perfect moment to have a discussion about the future of 3D But first it would be nice to make the terminology more clear, specifically: What is a “spatial representation” Implicit vs Explicit Generalization vs Specialization Reconstruction vs Generation Production vs Execution Let’s start: For me, a spatial representation is just a way to describe a thing in the physical world The core property that makes it useful is consistency You can enforce consistency explicitly via rendering equations, geometric constraints, and physics Or implicitly, purely through training data Then, your representation parameters can be explicit, like points, gaussians, triangles, voxels, etc. Or implicit, weights or latent vectors Parameters alone are not the representation. It’s a combination of the parameters, the process that produces them, and the way you materialize them through a function (physics-based rendering, simulation, neural network, etc.) Generalization means you take data from multiple scene observations, and then produce a map from desired input to representation parameters Specialization means you take single-scene observations and directly fit a function parameters to describe thar scene Many representations can serve both of the approaches, as long as you keep them differentiable Both of the above can be used for reconstruction, where the main goal is to explain observations through a lens of physics (hard constraint) On the other hand, generation needs generalization, and its task is to produce statistically plausible results that could be conditioned on observations (soft constraint) Both tasks are not solved yet and they can complement each other in various ways Yet another important aspect is the difference between production and execution Production = process of going from inputs to parameters Execution = process of going from parameters to result It’s important to separate these, because most usecases require fast execution to be viable which is severely constrained by the hardware So, are *world models* like Genie an important step forward? Yes Do they make other representations obsolete? Maybe some of them - but there are tons of economically valuable tasks that won’t be solved by it, at least in any observable future

The Genie 3 release is a perfect moment to have a discussion about the future of 3D But first it would be nice to make the terminology more clear, specifically: What is a “spatial representation” Implicit vs Explicit Generalization vs Specialization Reconstruction vs Generation Production vs Execution Let’s start: For me, a spatial representation is just a way to describe a thing in the physical world The core property that makes it useful is consistency You can enforce consistency explicitly via rendering equations, geometric constraints, and physics Or implicitly, purely through training data Then, your representation parameters can be explicit, like points, gaussians, triangles, voxels, etc. Or implicit, weights or latent vectors Parameters alone are not the representation. It’s a combination of the parameters, the process that produces them, and the way you materialize them through a function (physics-based rendering, simulation, neural network, etc.) Generalization means you take data from multiple scene observations, and then produce a map from desired input to representation parameters Specialization means you take single-scene observations and directly fit a function parameters to describe thar scene Many representations can serve both of the approaches, as long as you keep them differentiable Both of the above can be used for reconstruction, where the main goal is to explain observations through a lens of physics (hard constraint) On the other hand, generation needs generalization, and its task is to produce statistically plausible results that could be conditioned on observations (soft constraint) Both tasks are not solved yet and they can complement each other in various ways Yet another important aspect is the difference between production and execution Production = process of going from inputs to parameters Execution = process of going from parameters to result It’s important to separate these, because most usecases require fast execution to be viable which is severely constrained by the hardware So, are world models like Genie an important step forward? Yes Do they make other representations obsolete? Maybe some of them - but there are tons of economically valuable tasks that won’t be solved by it, at least in any observable future

Lucky Iyinbor

13,959 views • 8 months ago

What’s one of the best ways a wife can make life easier for her husband? 👀👀👀 What helps more than keeping the house in order, even when the mess was his? Cleanliness is objectively important, and something everyone should appreciate regardless of how much they show it or prioritize it themselves. Marriage is teamwork. Sometimes you make the mess. Sometimes she does. Sometimes life gets busy and everything gets a little out of control. That’s just reality when you have kids, work, errands, and a hundred things happening at once. A wife who sees a mess and simply handles it without keeping score is showing something valuable. She’s saying we’re in this together. And husbands notice that. There’s something deeply appreciated about coming home and seeing that your wife has taken care of things. The house feels calmer. Life feels a little more organized. You feel taken care of. The same should go the other direction. A husband shouldn’t expect his wife to clean up after him while he sits around doing nothing. If she needs help, he should get up and help. If she’s carrying a heavy load, he should carry some of it. That’s what marriage is supposed to look like. Two people looking for ways to make each other’s lives better. And honestly, sometimes the strongest thing you can do is just grab the broom, pick up the toys, wipe down the counter, and get it done. No speech. No scorekeeping. Just taking care of your family. How much better would marriage be if both husband and wife spent more time looking for ways to serve each other continually?

What’s one of the best ways a wife can make life easier for her husband? 👀👀👀 What helps more than keeping the house in order, even when the mess was his? Cleanliness is objectively important, and something everyone should appreciate regardless of how much they show it or prioritize it themselves. Marriage is teamwork. Sometimes you make the mess. Sometimes she does. Sometimes life gets busy and everything gets a little out of control. That’s just reality when you have kids, work, errands, and a hundred things happening at once. A wife who sees a mess and simply handles it without keeping score is showing something valuable. She’s saying we’re in this together. And husbands notice that. There’s something deeply appreciated about coming home and seeing that your wife has taken care of things. The house feels calmer. Life feels a little more organized. You feel taken care of. The same should go the other direction. A husband shouldn’t expect his wife to clean up after him while he sits around doing nothing. If she needs help, he should get up and help. If she’s carrying a heavy load, he should carry some of it. That’s what marriage is supposed to look like. Two people looking for ways to make each other’s lives better. And honestly, sometimes the strongest thing you can do is just grab the broom, pick up the toys, wipe down the counter, and get it done. No speech. No scorekeeping. Just taking care of your family. How much better would marriage be if both husband and wife spent more time looking for ways to serve each other continually?

Declaration of Memes

20,015 views • 7 days ago

BREAKING: Anthropic just dropped Fable 5.1—and CLAUDE IS SO BACK. We’ve spent the last week testing it at Every 📧 across coding, writing, and knowledge work. Our verdict: It's finally Fable for everyone. It’s the strongest coding model we’ve used, but now it's fast, token-efficient, and CRUCIALLY actually speaks like a normal person. Here’s our vibe check: - A monster at coding. Kieran Klaassen rebuilt a working version of Proof, our document editor, from one prompt. It added useful details he hadn’t requested, and it handles enormous coding jobs that run for days at a time. It built a computer use Mac app for me called Hands in one-shot that other models failed at. - A Claude our writers want to use again. It has clearer prose, fewer AI tells, and it takes an edit without arguing. It's a significant upgrade over Opus 5. And won Katie Parrott's heart back. - About half the tokens as Opus 5, and much faster. In our Slack-agent tests, it delivered comparable results to Opus 5 using about half as many tokens, in about 60% of the time. - Knowledge work you can delegate. It can produce great knowledge work—like slide decks—end to end without making slop. And flew threw hammer's tests with flying colors. - It now supports zero-data-retention agreements. Now businesses can actually use it! A big barrier to Fable adoption is gone. Net Result: It's obviously an Opus 5 killer. If that was your daily driver you should switch today. If you're using GPT-5.6 in ChatGPT for Work, it's spinning the wheels on for big delegated tasks. I still use ChatGPT for Work more day to day, but I use way more tokens in Fable 5.1. I send it off at the beginning of the day to do big programming projects, like end to end MVP builds, and check in every once in a while. State of Play: The big knock on Anthropic was they built a supergenius in a datacenter that was almost unusable. It was too slow, argued back, and talked in technical gibberish. They've managed to solve those problems and more with Fable 5.1!

BREAKING: Anthropic just dropped Fable 5.1—and CLAUDE IS SO BACK. We’ve spent the last week testing it at Every 📧 across coding, writing, and knowledge work. Our verdict: It's finally Fable for everyone. It’s the strongest coding model we’ve used, but now it's fast, token-efficient, and CRUCIALLY actually speaks like a normal person. Here’s our vibe check: - A monster at coding. Kieran Klaassen rebuilt a working version of Proof, our document editor, from one prompt. It added useful details he hadn’t requested, and it handles enormous coding jobs that run for days at a time. It built a computer use Mac app for me called Hands in one-shot that other models failed at. - A Claude our writers want to use again. It has clearer prose, fewer AI tells, and it takes an edit without arguing. It's a significant upgrade over Opus 5. And won Katie Parrott's heart back. - About half the tokens as Opus 5, and much faster. In our Slack-agent tests, it delivered comparable results to Opus 5 using about half as many tokens, in about 60% of the time. - Knowledge work you can delegate. It can produce great knowledge work—like slide decks—end to end without making slop. And flew threw hammer's tests with flying colors. - It now supports zero-data-retention agreements. Now businesses can actually use it! A big barrier to Fable adoption is gone. Net Result: It's obviously an Opus 5 killer. If that was your daily driver you should switch today. If you're using GPT-5.6 in ChatGPT for Work, it's spinning the wheels on for big delegated tasks. I still use ChatGPT for Work more day to day, but I use way more tokens in Fable 5.1. I send it off at the beginning of the day to do big programming projects, like end to end MVP builds, and check in every once in a while. State of Play: The big knock on Anthropic was they built a supergenius in a datacenter that was almost unusable. It was too slow, argued back, and talked in technical gibberish. They've managed to solve those problems and more with Fable 5.1!

Dan Shipper

205,060 views • 1 month ago

‼️BREAKING: Resurfaced Footage Captures New SUSPECT In All Black Fleeing UVU — Looks MORE Like Lance Twiggs Than Tyler Robinson New video has resurfaced showing a man running from the UVU crime scene on 9/10, filmed by a witness who believed he was the real suspect. The man is seen wearing all black, with a black backpack and long dark hair — matching multiple descriptions from that day. Construction worker Dylan Hope previously described coming into contact with a man right after the shooting who said “someone’s been shot.” He described him as wearing a black trench coat, black cargo pants, black COVID mask, black sunglasses, and having long greasy black hair while carrying a small backpack. That description also closely matches what was broadcast over police dispatch that day: a suspect wearing all black, black mask, and carrying a long gun. The only known footage of a person on the roof also shows someone dressed entirely in black in a prone position on the Losee building. This new video does not appear to show Tyler Robinson — however, the man in the video bears a noticeable resemblance to Lance Twiggs — particularly in hair length, color, and profile, though the footage is too blurry to make a positive identification. If this is the same person seen on the roof and the same individual who approached the construction crew, it raises serious questions about who was actually at the scene that day. The descriptions of the person seen running, the person on the roof, and the individual who approached the construction crew are all consistent with each other… and inconsistent with Tyler Robinson. Watch the video. Does this look like Lance Twiggs to you… or someone else? More questions than answers. Watch the video and tell me what you see. CC: Candace Owens Baron Coleman

Project Constitution

446,981 views • 2 months ago