@maximo2100.bsky.social
Lost somewhere in latent space where pixels have the memory of unformulated dreams.
Égaré quelque part dans l'espace latent où les pixels ont la mémoire de rêves non formulés.
Égaré quelque part dans l'espace latent où les pixels ont la mémoire de rêves non formulés.
December 24, 2025 at 7:15 AM
December 23, 2025 at 8:55 PM
github.com/thu-ml/Turbo...
TurboDiffusion: 100–200× Acceleration for Video Diffusion Models
TurboDiffusion: 100–200× Acceleration for Video Diffusion Models
December 21, 2025 at 8:04 AM
github.com/thu-ml/Turbo...
TurboDiffusion: 100–200× Acceleration for Video Diffusion Models
TurboDiffusion: 100–200× Acceleration for Video Diffusion Models
huggingface.co/papers/2512....
EgoX: Egocentric Video Generation from a Single Exocentric Video
EgoX: Egocentric Video Generation from a Single Exocentric Video
December 15, 2025 at 9:21 PM
huggingface.co/papers/2512....
EgoX: Egocentric Video Generation from a Single Exocentric Video
EgoX: Egocentric Video Generation from a Single Exocentric Video
github.com/zai-org/SCAIL
Character Animation/motion transfer
Character Animation/motion transfer
December 14, 2025 at 9:04 PM
github.com/zai-org/SCAIL
Character Animation/motion transfer
Character Animation/motion transfer
github.com/ssj9596/One-...
One-to-All Animation: Alignment-Free
Character Animation and Image Pose Transfer
One-to-All Animation: Alignment-Free
Character Animation and Image Pose Transfer
December 14, 2025 at 10:09 AM
github.com/ssj9596/One-...
One-to-All Animation: Alignment-Free
Character Animation and Image Pose Transfer
One-to-All Animation: Alignment-Free
Character Animation and Image Pose Transfer
github.com/ali-vilab/Wa...
Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance.
Indicate a trajectory.
Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance.
Indicate a trajectory.
December 14, 2025 at 9:58 AM
github.com/ali-vilab/Wa...
Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance.
Indicate a trajectory.
Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance.
Indicate a trajectory.
huggingface.co/papers/2512....
EMMA: Efficient Multimodal Understanding, Generation, and Editing with a Unified Architecture
EMMA: Efficient Multimodal Understanding, Generation, and Editing with a Unified Architecture
December 11, 2025 at 12:33 PM
huggingface.co/papers/2512....
EMMA: Efficient Multimodal Understanding, Generation, and Editing with a Unified Architecture
EMMA: Efficient Multimodal Understanding, Generation, and Editing with a Unified Architecture
videocof.github.io
Unified Video Editing with Temporal Reasoner
Unified Video Editing with Temporal Reasoner
December 9, 2025 at 8:15 PM
videocof.github.io
Unified Video Editing with Temporal Reasoner
Unified Video Editing with Temporal Reasoner
huggingface.co/papers/2511....
MotionV2V: Editing Motion in a Video
MotionV2V: Editing Motion in a Video
December 8, 2025 at 8:41 PM
huggingface.co/papers/2511....
MotionV2V: Editing Motion in a Video
MotionV2V: Editing Motion in a Video
huggingface.co/papers/2511....
One-to-All Animation: Alignment-Free Character Animation and Image Pose Transfer. Arxiv: 2511.22940
One-to-All Animation: Alignment-Free Character Animation and Image Pose Transfer. Arxiv: 2511.22940
December 8, 2025 at 8:39 PM
huggingface.co/papers/2511....
One-to-All Animation: Alignment-Free Character Animation and Image Pose Transfer. Arxiv: 2511.22940
One-to-All Animation: Alignment-Free Character Animation and Image Pose Transfer. Arxiv: 2511.22940
huggingface.co/dx8152/Qwen-...
Qwen-Edit-2509-Light-Migration Lora
Qwen-Edit-2509-Light-Migration Lora
December 8, 2025 at 1:04 PM
huggingface.co/dx8152/Qwen-...
Qwen-Edit-2509-Light-Migration Lora
Qwen-Edit-2509-Light-Migration Lora
huggingface.co/aquif-ai/aqu...
Text to image based on Wan 2.2.
Text to image based on Wan 2.2.
December 8, 2025 at 6:56 AM
huggingface.co/aquif-ai/aqu...
Text to image based on Wan 2.2.
Text to image based on Wan 2.2.
github.com/Tencent-Huny...
HunyuanVideo-1.5: A lightweight video generation model
HunyuanVideo-1.5: A lightweight video generation model
December 7, 2025 at 7:31 AM
github.com/Tencent-Huny...
HunyuanVideo-1.5: A lightweight video generation model
HunyuanVideo-1.5: A lightweight video generation model
kszpxxzmc.github.io/ViSAudio-pro...
ViSAudio: End-to-End Video-Driven Binaural Spatial Audio Generation
ViSAudio: End-to-End Video-Driven Binaural Spatial Audio Generation
December 7, 2025 at 7:27 AM
kszpxxzmc.github.io/ViSAudio-pro...
ViSAudio: End-to-End Video-Driven Binaural Spatial Audio Generation
ViSAudio: End-to-End Video-Driven Binaural Spatial Audio Generation
huggingface.co/meituan-long...
LongCat-Image-Edit (Qwen based)
LongCat-Image-Edit (Qwen based)
December 5, 2025 at 8:19 PM
huggingface.co/meituan-long...
LongCat-Image-Edit (Qwen based)
LongCat-Image-Edit (Qwen based)
lightx-ai.github.io
Light-X is a video generation framework that jointly controls camera trajectory and illumination from monocular videos.
Light-X is a video generation framework that jointly controls camera trajectory and illumination from monocular videos.
December 5, 2025 at 8:12 PM
lightx-ai.github.io
Light-X is a video generation framework that jointly controls camera trajectory and illumination from monocular videos.
Light-X is a video generation framework that jointly controls camera trajectory and illumination from monocular videos.
github.com/stuttlepress...
This workflow uses Wan VACE (Wan 2.2 Fun VACE or Wan 2.1 VACE, your choice!) to smooth out awkward motion transitions between video clips.
This workflow uses Wan VACE (Wan 2.2 Fun VACE or Wan 2.1 VACE, your choice!) to smooth out awkward motion transitions between video clips.
December 5, 2025 at 6:44 PM
github.com/stuttlepress...
This workflow uses Wan VACE (Wan 2.2 Fun VACE or Wan 2.1 VACE, your choice!) to smooth out awkward motion transitions between video clips.
This workflow uses Wan VACE (Wan 2.2 Fun VACE or Wan 2.1 VACE, your choice!) to smooth out awkward motion transitions between video clips.
firstframego.github.io
First Frame Go
First Frame Go
December 4, 2025 at 7:53 AM
firstframego.github.io
First Frame Go
First Frame Go
huggingface.co/papers/2512....
RELIC: Interactive Video World Model with Long-Horizon Memory
RELIC: Interactive Video World Model with Long-Horizon Memory
December 4, 2025 at 6:55 AM
huggingface.co/papers/2512....
RELIC: Interactive Video World Model with Long-Horizon Memory
RELIC: Interactive Video World Model with Long-Horizon Memory
magicquill.art/v2/
MagicQuill V2: Precise and Interactive Image Editing with Layered Visual Cues.
MagicQuill V2: Precise and Interactive Image Editing with Layered Visual Cues.
December 4, 2025 at 6:39 AM
magicquill.art/v2/
MagicQuill V2: Precise and Interactive Image Editing with Layered Visual Cues.
MagicQuill V2: Precise and Interactive Image Editing with Layered Visual Cues.
arxiv.org/abs/2512.03041
MultiShotMaster: A Controllable Multi-Shot Video Generation Framework
MultiShotMaster: A Controllable Multi-Shot Video Generation Framework
December 3, 2025 at 12:25 PM
arxiv.org/abs/2512.03041
MultiShotMaster: A Controllable Multi-Shot Video Generation Framework
MultiShotMaster: A Controllable Multi-Shot Video Generation Framework
tuna-ai.org
TUNA leverages unified visual representations to enable image/video understanding, image/video generation, and image editing within a single framework. By Meta.
TUNA leverages unified visual representations to enable image/video understanding, image/video generation, and image editing within a single framework. By Meta.
December 2, 2025 at 7:37 PM
tuna-ai.org
TUNA leverages unified visual representations to enable image/video understanding, image/video generation, and image editing within a single framework. By Meta.
TUNA leverages unified visual representations to enable image/video understanding, image/video generation, and image editing within a single framework. By Meta.
kr1sjfu.github.io/iMontage-web/
iMontage: Image editing, In-context Generation, storyboards.
iMontage: Image editing, In-context Generation, storyboards.
November 30, 2025 at 9:17 AM
kr1sjfu.github.io/iMontage-web/
iMontage: Image editing, In-context Generation, storyboards.
iMontage: Image editing, In-context Generation, storyboards.
Currently, Qwen Image Edit is your open source alternative to google's nano banana.
November 30, 2025 at 9:13 AM
Currently, Qwen Image Edit is your open source alternative to google's nano banana.