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.

Ever wished you could have sprites that could move like 3D models, without actually needing to be boring old 3D models? Then look no further! #screenshotsaturday

D.O.R.F. Real-Time Strategic Conflict

16,333 subscribers

43,932 views • 1 year ago •via X (Twitter)

Science & Technology Gaming #screenshotsaturday

Anya Rossi• Live Now

Private livecam show

10 Comments

D.O.R.F. Real-Time Strategic Conflict1 year ago

Watch on Youtube:

kingbdogz1 year ago

This looks incredible. Love to see improvement on old rendering techniques.

Punished Norm1 year ago

Beautiful stuff as always, but I'll be very honest: those black triangles at the top are kind of annoying. I get that there's a rendering distance limit, but still, it's a little irritating. I'm still excited for this game, though. Keep it up!

D.O.R.F. Real-Time Strategic Conflict1 year ago

That’s actually an ancient bug we’ve been trying to figure out for a while. It’s still unclear what is causing it

Uncle Sponge1 year ago

This looks sick. I love the HUD. Graphic system is similar to brigador. Do you have a target release date?

Sid1 year ago

Sprite Sheet? Like an image with all the different views?

D.O.R.F. Real-Time Strategic Conflict1 year ago

The sprite sheet is just an image that has all the different sprite frames of every different view rendered onto it, with metadata to tell the game where every frame is located

Jussi Kemppainen | Drivers of the Apocalypse1 year ago

Perfection 👌

Kay🔮🧙‍♂️1 year ago

Been saying forever RTS should go back to this style of rendering; it lets low end computers (such as ones with integrated gpus) play without pathfinding calculation being heavily impacted.

Noble Six1 year ago

Aircraft handling looks amazing!!

Related Videos

🚨 NEW drawtactics.com feature Introducing Player's Eye Ever watched a game and wished you could look at the scene from a player's perspective? now allows exactly that Simply upload a screenshot and then choose your player (I'll work on making the 3D models look better lol)

🚨 NEW drawtactics.com feature Introducing Player's Eye Ever watched a game and wished you could look at the scene from a player's perspective? now allows exactly that Simply upload a screenshot and then choose your player (I'll work on making the 3D models look better lol)

JM

18,051 views • 26 days ago

The two bad things about supporting arbitrary 3d models as characters is that I have to actually learn how to use the unity animator, and character sprites interact incredibly poorly with other 3d geometry that gets really close to them.

The two bad things about supporting arbitrary 3d models as characters is that I have to actually learn how to use the unity animator, and character sprites interact incredibly poorly with other 3d geometry that gets really close to them.

TheDoddlerRO

25,448 views • 6 months ago

New version of The Models Resource just dropped adding an awesome 3D model viewer right into the website so you can now preview models without needing to download them!

New version of The Models Resource just dropped adding an awesome 3D model viewer right into the website so you can now preview models without needing to download them!

Yahya Danboos🌙Kickstarter Launch Soon

287,844 views • 1 year ago

What if your textbook could move? Ours does. Smart Biology’s Animated Textbooks use 3D models to explain biology like never before. Not flat. Not static. Just smart. Learn more at #Biology #Science #3D #Animations #STEME #EdTech

What if your textbook could move? Ours does. Smart Biology’s Animated Textbooks use 3D models to explain biology like never before. Not flat. Not static. Just smart. Learn more at #Biology #Science #3D #Animations #STEME #EdTech

Smart Biology

14,032 views • 1 year ago

What if your AI character could move beyond the screen? Create unique characters with SeaArt. Transform them into high-detail 3D models with Tripo. From 2D imagination to 3D creation, bring your characters closer to life. SeaArt × Tripo Create beyond the screen.

What if your AI character could move beyond the screen? Create unique characters with SeaArt. Transform them into high-detail 3D models with Tripo. From 2D imagination to 3D creation, bring your characters closer to life. SeaArt × Tripo Create beyond the screen.

SeaArt.Ai🐋

43,734 views • 3 months ago

Ever driven through the mountains and wished you could just look around? Tesla FSD lets you do exactly that.

Ever driven through the mountains and wished you could just look around? Tesla FSD lets you do exactly that.

Mario Nawfal

84,556 views • 7 months ago

I tested Union Alpha again. It’s really bad at 3D and even SVGs. Not even close to the Flash models. Just look at the difference between them lol. I read that it’s from Spain. If that’s true, it could be a Mistral model, since many of their models use 256K context.

I tested Union Alpha again. It’s really bad at 3D and even SVGs. Not even close to the Flash models. Just look at the difference between them lol. I read that it’s from Spain. If that’s true, it could be a Mistral model, since many of their models use 256K context.

Bhavy☄️

15,523 views • 23 days ago

Holy crap, NVIDIA just made it drastically easier to create large scale explorable 3d worlds. No manual stitching of smaller 3d generations like other 3d models. Lyra 2.0 looks pretty damn impressive.

Holy crap, NVIDIA just made it drastically easier to create large scale explorable 3d worlds. No manual stitching of smaller 3d generations like other 3d models. Lyra 2.0 looks pretty damn impressive.

Bilawal Sidhu

95,689 views • 5 months ago

ALL EIGHT X1 MAVERICKS 🤖 And no, these are not real models, it's all 3D rendered. Made in blender. No AI. But you can print them. And with a good paint job, these could look like that 😉 Btw: all print files are on sale 🛒30% off. 🔗 below #b3d #megaman #mavericks

ALL EIGHT X1 MAVERICKS 🤖 And no, these are not real models, it's all 3D rendered. Made in blender. No AI. But you can print them. And with a good paint job, these could look like that 😉 Btw: all print files are on sale 🛒30% off. 🔗 below #b3d #megaman #mavericks

DemNikoArt ➡️ BCON 26

34,969 views • 26 days ago

3D-LLM: Injecting the 3D World into Large Language Models paper page: Large language models (LLMs) and Vision-Language Models (VLMs) have been proven to excel at multiple tasks, such as commonsense reasoning. Powerful as these models can be, they are not grounded in the 3D physical world, which involves richer concepts such as spatial relationships, affordances, physics, layout, and so on. In this work, we propose to inject the 3D world into large language models and introduce a whole new family of 3D-LLMs. Specifically, 3D-LLMs can take 3D point clouds and their features as input and perform a diverse set of 3D-related tasks, including captioning, dense captioning, 3D question answering, task decomposition, 3D grounding, 3D-assisted dialog, navigation, and so on. Using three types of prompting mechanisms that we design, we are able to collect over 300k 3D-language data covering these tasks. To efficiently train 3D-LLMs, we first utilize a 3D feature extractor that obtains 3D features from rendered multi- view images. Then, we use 2D VLMs as our backbones to train our 3D-LLMs. By introducing a 3D localization mechanism, 3D-LLMs can better capture 3D spatial information. Experiments on ScanQA show that our model outperforms state-of-the-art baselines by a large margin (e.g., the BLEU-1 score surpasses state-of-the-art score by 9%). Furthermore, experiments on our held-in datasets for 3D captioning, task composition, and 3D-assisted dialogue show that our model outperforms 2D VLMs. Qualitative examples also show that our model could perform more tasks beyond the scope of existing LLMs and VLMs.

3D-LLM: Injecting the 3D World into Large Language Models paper page: Large language models (LLMs) and Vision-Language Models (VLMs) have been proven to excel at multiple tasks, such as commonsense reasoning. Powerful as these models can be, they are not grounded in the 3D physical world, which involves richer concepts such as spatial relationships, affordances, physics, layout, and so on. In this work, we propose to inject the 3D world into large language models and introduce a whole new family of 3D-LLMs. Specifically, 3D-LLMs can take 3D point clouds and their features as input and perform a diverse set of 3D-related tasks, including captioning, dense captioning, 3D question answering, task decomposition, 3D grounding, 3D-assisted dialog, navigation, and so on. Using three types of prompting mechanisms that we design, we are able to collect over 300k 3D-language data covering these tasks. To efficiently train 3D-LLMs, we first utilize a 3D feature extractor that obtains 3D features from rendered multi- view images. Then, we use 2D VLMs as our backbones to train our 3D-LLMs. By introducing a 3D localization mechanism, 3D-LLMs can better capture 3D spatial information. Experiments on ScanQA show that our model outperforms state-of-the-art baselines by a large margin (e.g., the BLEU-1 score surpasses state-of-the-art score by 9%). Furthermore, experiments on our held-in datasets for 3D captioning, task composition, and 3D-assisted dialogue show that our model outperforms 2D VLMs. Qualitative examples also show that our model could perform more tasks beyond the scope of existing LLMs and VLMs.

AK

249,798 views • 3 years ago

no one else could ever be like you.

no one else could ever be like you.

benzos

22,658 views • 8 months ago

AI video has a control problem. Most AI tools generate in 2D. Filmmakers think, stage, and direct in 3D. Today we're introducing Flow Studio 3D Editor + Canvas. Build and direct your scene in 3D. Then use Canvas to render and refine the final look with leading AI models. Stay in 2D when speed matters. Move into 3D when you need precision. AI can build the scene. You still call the shots. Start directing:

AI video has a control problem. Most AI tools generate in 2D. Filmmakers think, stage, and direct in 3D. Today we're introducing Flow Studio 3D Editor + Canvas. Build and direct your scene in 3D. Then use Canvas to render and refine the final look with leading AI models. Stay in 2D when speed matters. Move into 3D when you need precision. AI can build the scene. You still call the shots. Start directing:

Autodesk Flow Studio

35,641 views • 2 months ago

You don’t always have to be with somebody, bro. Sometimes being alone is the best thing that could ever happen to you. ’Cause when you’re alone, that’s when you really start hearing your own thoughts. That’s when you start learning who you are without outside opinions, without validation, without needing someone to make you feel whole.

You don’t always have to be with somebody, bro. Sometimes being alone is the best thing that could ever happen to you. ’Cause when you’re alone, that’s when you really start hearing your own thoughts. That’s when you start learning who you are without outside opinions, without validation, without needing someone to make you feel whole.

𖣂Prince𖣂

16,683 views • 11 months ago

3D Low-Poly Pollaxe Analytics suggest you guys REVILE and DESPISE my 3D models, but they're fun to make so that's all that matters to me. Music by LL

3D Low-Poly Pollaxe Analytics suggest you guys REVILE and DESPISE my 3D models, but they're fun to make so that's all that matters to me. Music by LL

𝖒𝖚𝖑𝖑

28,942 views • 4 months ago

MIXAR JUST PUT 400+ AI MODELS INSIDE ONE 3D WORKSPACE Mixar gives you access to LLMs, image-to-3D, texturing models and native 3D tools from the same environment: → One workspace → 400+ models → Agents can work directly inside the scene → Multiple agents can work across different scenes → Built on a fork of Blender, not another plugin No need to stitch together separate AI tools, scripts and 3D software. Try it now.

MIXAR JUST PUT 400+ AI MODELS INSIDE ONE 3D WORKSPACE Mixar gives you access to LLMs, image-to-3D, texturing models and native 3D tools from the same environment: → One workspace → 400+ models → Agents can work directly inside the scene → Multiple agents can work across different scenes → Built on a fork of Blender, not another plugin No need to stitch together separate AI tools, scripts and 3D software. Try it now.

marcus

19,367 views • 7 days ago

HOLY FUCKING SHIT WHAT what whatt???? we have been trying to get models to 3d model all wrong... this is 100% hand placed vertices by Fable... no procedural techniques, no Bezier patches, no loft modeling - nothing ... this is the best representation of a human I have EVER seen any LLM create from scratch without visual references.... this is just IN Fable's 3d worldmodeling

HOLY FUCKING SHIT WHAT what whatt???? we have been trying to get models to 3d model all wrong... this is 100% hand placed vertices by Fable... no procedural techniques, no Bezier patches, no loft modeling - nothing ... this is the best representation of a human I have EVER seen any LLM create from scratch without visual references.... this is just IN Fable's 3d worldmodeling

Utah teapot 🫖

101,205 views • 3 months ago