3DREGEN.JDIHLMANN.COMMEDIAMONTH DECEMBER
3dregen
3D-RE-GEN
Generates separable 3D ground aligned scenes from a single image
AN IN-DEPTH REPOSITORY
THE MONTHLY
SIGNAL
Every model, paper, media release, agent and tool from the month—in one source-linked archive.
COMPLETE MONTHLY ARCHIVE
December 2025
The year closed with faster frontier models, long-form video and 3D generation, real-time creative systems and more capable open releases.
THE COMPLETE MONTHLY INDEX
Every Signal
63ITEMS IN DECEMBER 2025
Every linked paper, product release, research project and article has been checked directly. Cards use the publication's own description, imagery and published date wherever the source supplied them.
The AI Search helps discover the wider field, while every available card opens the original publication. Dates come only from publication metadata or official source APIs—never from a video. A checked date records our review, not the release. Older undated entries show their archive month.
3DREGEN.JDIHLMANN.COMMEDIAMONTH DECEMBER
AniX
AniX is linked to its original publication. Open the source for the author’s release notes, demonstrations and technical details.
MEDIAMONTH DECEMBER
CARI4D
CARI4D is linked to its original publication. Open the source for the author’s release notes, demonstrations and technical details.
DREAMONTAGE.GITHUB.IOTOOLSMONTH DECEMBER
FlashPortrait
FlashPortrait: 6× Faster Infinite Portrait Animation
FlashPortrait: 6x Faster Infinite Portrait Animation with Adaptive Latent Prediction
GENERATIVE-REFOCUSING.GITHUB.IOTOOLSMONTH DECEMBER
Generative Refocusing
Generative Refocusing: Flexible Defocus Control from a Single Image
Generative Refocusing is linked to its original publication. Open the source for the author’s release notes, demonstrations and technical details.
MINIMAX.IOMODELSMONTH DECEMBER
Minimax M21
MiniMax M2.1: Significantly Enhanced Multi-Language Programming, Built for Real-World Complex Tasks
Minimax M21 is linked to its original publication. Open the source for the author’s release notes, demonstrations and technical details.
TOOLSMONTH DECEMBER
Mvinverse Page
Mvinverse Page is published at its original model or project page. Open the source for documentation, files, demonstrations and usage details.
MODELSMONTH DECEMBER
Nitrogen
NitroGen | A Foundation Model for Generalist Gaming Agents
Nitrogen is linked to its original publication. Open the source for the author’s release notes, demonstrations and technical details.
HUGGINGFACE.COMEDIAMONTH DECEMBER
Qwen Image Edit 2511
Qwen/Qwen-Image-Edit-2511 · Hugging Face
Qwen Image Edit 2511 is published at its original model or project page. Open the source for documentation, files, demonstrations and usage details.
TOOLSMONTH DECEMBER
Spatia
Spatia: Video Generation with Updatable Spatial Memory
Spatia: Video Generation with Updatable Spatial Memory.
TOOLSMONTH DECEMBER
StoryMem
StoryMem is linked to its original publication. Open the source for the author’s release notes, demonstrations and technical details.
BFL.AIMODELSMONTH DECEMBER
Flux 2 Max
FLUX.2 [max] - Top-Tier Quality Image Generation | Black Forest Labs
FLUX.2 [max] delivers the highest quality image generation and editing in the FLUX.2 family. Professional-grade output with unmatched photorealism.
MODELSMONTH DECEMBER
Klingai
Kling AI: Next-Gen AI Video & Image Generator
Create high-quality AI videos and images with Kling AI. Turn text, images, and references into multimodal creative content in one studio.
MEDIAMONTH DECEMBER
LongCat Video Avatar
LongCat-Video-Avatar
LongCat-Video-Avatar a unified model that delivers expressive and highly dynamic audio-driven character animation.
TOOLSMONTH DECEMBER
LongVie2 Project
LongVie 2
Project website for LongVie 2 - Multimodal Controllable Ultra-Long Video World Model
MODELSMONTH DECEMBER
Mimo V2 Flash
Mimo V2 Flash is linked to its original publication. Open the source for the author’s release notes, demonstrations and technical details.
HUGGINGFACE.COMEDIAMONTH DECEMBER
Qwen Image Layered
Qwen/Qwen-Image-Layered · Hugging Face
Qwen Image Layered is published at its original model or project page. Open the source for documentation, files, demonstrations and usage details.
LUMALABS.AIMODELSMONTH DECEMBER
Ray
Direct any frame. Finish every cut. | Luma
Ray3.2 transforms creative intent into scalable video workflows with richer control, continuity, and cinematic direction.
MEDIAMONTH DECEMBER
Realvideo
Realvideo is linked to its original publication. Open the source for the author’s release notes, demonstrations and technical details.
TEAL024.GITHUB.IOTOOLSMONTH DECEMBER
SCAIL
SCAIL: Towards Studio-Grade Character Animation via In-Context Learning of 3D-Consistent Pose Representations
SCAIL: Towards Studio-Grade Character Animation via In-Context Learning of 3D-Consistent Pose Representations.
MODELSMONTH DECEMBER
Seedance1 5 Pro
Seedance 1.5 pro
Seedance1 5 Pro is linked to its original publication. Open the source for the author’s release notes, demonstrations and technical details.
HUGGINGFACE.COMODELSMONTH DECEMBER
Stereospace Web
StereoSpace Project Page - a Hugging Face Space by prs-eth
Upload one regular photo and the app creates a matching left‑right pair that can be viewed as anaglyph or side‑by‑side 3D. You can also set the desired eye‑separation distance. The result is a read...
GITHUB.COMRESEARCHMONTH DECEMBER
SVG T2I
GitHub - KlingAIResearch/SVG-T2I: [Arxiv 2025] Official PyTorch Implementation of "SVG-T2I: Scaling up Text-to-Image Latent Diffusion Model Without Variational Autoencoder".
[Arxiv 2025] Official PyTorch Implementation of "SVG-T2I: Scaling up Text-to-Image Latent Diffusion Model Without Variational Autoencoder". - KlingAIResearch/SVG-T2I