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.

FrankenMotion: Part-level human motion generation; - enables compositional synthesis by combining atomic body-part movements; - DiT + FrankenAgent LLM. Indie game devs/animators can make complex character animations via text without manual keyframing.

Wildminder

10,367 subscribers

33,890 views • 5 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Excited to share HOI-PAGE, to appear at #ICML2026! 🚀 Lei Li generates 4D human-object interactions zero-shot from text A part-affordance graph grounds interactions via LLM+video priors, enabling complex multi-person, multi-object interactions 👉

Excited to share HOI-PAGE, to appear at #ICML2026! 🚀 Lei Li generates 4D human-object interactions zero-shot from text A part-affordance graph grounds interactions via LLM+video priors, enabling complex multi-person, multi-object interactions 👉

Angela Dai

10,481 views • 2 months ago

Alibaba just announced FantasyTalking on Hugging Face Realistic Talking Portrait Generation via Coherent Motion Synthesis

Alibaba just announced FantasyTalking on Hugging Face Realistic Talking Portrait Generation via Coherent Motion Synthesis

AK

69,968 views • 1 year ago

Story-to-Motion: Synthesizing Infinite and Controllable Character Animation from Long Text Outperforms previous SotA motion synthesis methods across the board proj: abs:

Story-to-Motion: Synthesizing Infinite and Controllable Character Animation from Long Text Outperforms previous SotA motion synthesis methods across the board proj: abs:

Aran Komatsuzaki

38,401 views • 2 years ago

Multi-Track Timeline Control for Text-Driven 3D Human Motion Generation paper page: Recent advances in generative modeling have led to promising progress on synthesizing 3D human motion from text, with methods that can generate character animations from short prompts and specified durations. However, using a single text prompt as input lacks the fine-grained control needed by animators, such as composing multiple actions and defining precise durations for parts of the motion. To address this, we introduce the new problem of timeline control for text-driven motion synthesis, which provides an intuitive, yet fine-grained, input interface for users. Instead of a single prompt, users can specify a multi-track timeline of multiple prompts organized in temporal intervals that may overlap. This enables specifying the exact timings of each action and composing multiple actions in sequence or at overlapping intervals. To generate composite animations from a multi-track timeline, we propose a new test-time denoising method. This method can be integrated with any pre-trained motion diffusion model to synthesize realistic motions that accurately reflect the timeline. At every step of denoising, our method processes each timeline interval (text prompt) individually, subsequently aggregating the predictions with consideration for the specific body parts engaged in each action. Experimental comparisons and ablations validate that our method produces realistic motions that respect the semantics and timing of given text prompts.

Multi-Track Timeline Control for Text-Driven 3D Human Motion Generation paper page: Recent advances in generative modeling have led to promising progress on synthesizing 3D human motion from text, with methods that can generate character animations from short prompts and specified durations. However, using a single text prompt as input lacks the fine-grained control needed by animators, such as composing multiple actions and defining precise durations for parts of the motion. To address this, we introduce the new problem of timeline control for text-driven motion synthesis, which provides an intuitive, yet fine-grained, input interface for users. Instead of a single prompt, users can specify a multi-track timeline of multiple prompts organized in temporal intervals that may overlap. This enables specifying the exact timings of each action and composing multiple actions in sequence or at overlapping intervals. To generate composite animations from a multi-track timeline, we propose a new test-time denoising method. This method can be integrated with any pre-trained motion diffusion model to synthesize realistic motions that accurately reflect the timeline. At every step of denoising, our method processes each timeline interval (text prompt) individually, subsequently aggregating the predictions with consideration for the specific body parts engaged in each action. Experimental comparisons and ablations validate that our method produces realistic motions that respect the semantics and timing of given text prompts.

AK

126,548 views • 2 years ago

Got five papers accepted by #ECCV2024 European Conference on Computer Vision #ECCV2026 ! Huge thanks to all my collaborators! 😃 See you in Milan 🇮🇹 Summary of Selected Works (I made a fast-forward for them 😄) - [Shape Generation] Surf-D: Generating High-Quality Surfaces of Arbitrary Topologies Using Diffusion Models, ECCV 2024. - [Efficient Motion Generation] EMDM: Efficient Motion Diffusion Model for Fast, High-Quality Human Motion Generation, ECCV 2024. - [Controllable Motion Generation] TLControl: Trajectory and Language Control for Human Motion Synthesis, ECCV 2024. - [Avatar Generation] Disentangled Clothed Avatar Generation from Text Descriptions, ECCV 2024. Project Page: Surf-D: EMDM: TLControl: SOSMPL:

Zhiyang (Frank) Dou

18,182 views • 2 years ago

god indie devs will really make a game about *anything* these days

god indie devs will really make a game about anything these days

𝕸𝖔𝖓𝖌𝖗𝖊𝖑 | HAM HOLE DEMO OUT NOW

24,583 views • 1 month ago

Introducing StyleDrop, a model that allows a significantly higher level of stylized text-to-image synthesis by using a few style reference images that describe the style for text-to-image generation, bypassing the burden of text prompt engineering. More→

Introducing StyleDrop, a model that allows a significantly higher level of stylized text-to-image synthesis by using a few style reference images that describe the style for text-to-image generation, bypassing the burden of text prompt engineering. More→

Google AI

80,357 views • 2 years ago

Indie game devs be like:

Indie game devs be like:

Walaber

2,314,735 views • 2 years ago

This is freaking awesome 🔥 Uthana just launched a new AI for 3D character animation. It allows users to upload any rigged character, prompt motions via text or video. Great for game dev and animators.

This is freaking awesome 🔥 Uthana just launched a new AI for 3D character animation. It allows users to upload any rigged character, prompt motions via text or video. Great for game dev and animators.

AshutoshShrivastava

53,863 views • 1 year ago

Indie game devs prioritize FUN and APPEALING character design, while creating CHALLENGING gameplay that REWARDS the players for playing.

Indie game devs prioritize FUN and APPEALING character design, while creating CHALLENGING gameplay that REWARDS the players for playing.

Windpress

77,380 views • 4 months ago

Wan2.2-S2V is now natively supported in ComfyUI! Transform static images and audio into cinematic-quality videos with synchronized lip-sync and natural movements. 🔹 Audio-driven video generation 🔹 Cinematic-grade quality output 🔹 Minute-level long-form videos 🔹 Multi-format support (full/half-body) 🔹 Enhanced motion control via text 🧵👇

Wan2.2-S2V is now natively supported in ComfyUI! Transform static images and audio into cinematic-quality videos with synchronized lip-sync and natural movements. 🔹 Audio-driven video generation 🔹 Cinematic-grade quality output 🔹 Minute-level long-form videos 🔹 Multi-format support (full/half-body) 🔹 Enhanced motion control via text 🧵👇

ComfyUI

49,251 views • 10 months ago

Kling 2.6 just unlocked Motion Control 🎭Drive a character’s exact movements & expressions using: • 1 reference video • 1 image, hands, gestures, full-body motion, perfectly synced. This is next-level character animation. Kling AI

Kling 2.6 just unlocked Motion Control 🎭Drive a character’s exact movements & expressions using: • 1 reference video • 1 image, hands, gestures, full-body motion, perfectly synced. This is next-level character animation. Kling AI

OpenArt

19,970 views • 6 months ago

animators are not needed anymore this 3D AI motion capture plugin can convert character movement from real video to 3D data and.. you can apply the motion to any 3D character.. link in comments

animators are not needed anymore this 3D AI motion capture plugin can convert character movement from real video to 3D data and.. you can apply the motion to any 3D character.. link in comments

el.cine

64,514 views • 7 months ago

This is what happens when indie devs get fed up waiting for EA to make another Mirror's Edge game! First person parkour action in LIQUID LUNGS! Steam page: by indie dev Carlcadium

This is what happens when indie devs get fed up waiting for EA to make another Mirror's Edge game! First person parkour action in LIQUID LUNGS! Steam page: by indie dev Carlcadium

Alpha Beta Gamer

164,911 views • 2 months ago

Latest Experiment: Control a character in a video generation using a sketch with motion paths (Combining Runway Aleph and Image Reference) Builds on the last example: given that you can also add image references to Aleph gens you can also add extra instructions via an image (prompt in replies).

Latest Experiment: Control a character in a video generation using a sketch with motion paths (Combining Runway Aleph and Image Reference) Builds on the last example: given that you can also add image references to Aleph gens you can also add extra instructions via an image (prompt in replies).

Ray (movie arc)

47,420 views • 11 months ago

Another indie game that has FUN and CHARMING puzzles with ARTISTIC character design that rewards the player for solving the level. Triple A devs could ONLY DREAM of making something half as good as this.

Another indie game that has FUN and CHARMING puzzles with ARTISTIC character design that rewards the player for solving the level. Triple A devs could ONLY DREAM of making something half as good as this.

Windpress

64,308 views • 4 months ago

VideoComposer brings ControlNet guidance to text and video-to-video. The model enables to combine multiple modalities like text, sketch, style and even motion to drive video generation. The results look extremely good.

VideoComposer brings ControlNet guidance to text and video-to-video. The model enables to combine multiple modalities like text, sketch, style and even motion to drive video generation. The results look extremely good.

Dreaming Tulpa 🥓👑

18,045 views • 3 years ago

Ye Shunguang Gameplay Animations Part 1: via Reversed Rooms

Ye Shunguang Gameplay Animations Part 1: via Reversed Rooms

Zenless Zone Leaks

229,885 views • 7 months ago

This is the TYPE of ART that only Indie devs can create, while Triple A devs spend all their time making another Souls Like game

This is the TYPE of ART that only Indie devs can create, while Triple A devs spend all their time making another Souls Like game

Windpress

23,437 views • 6 months ago