LightNews LightNews
@maximo2100.bsky.social
150 followers 940 following 290 posts
I'm interested in science, arts, philosophy, geopolitics and many more. Here, I post about technologies related to image making (among others things, I teach in film schools/universities, mostly in Paris).
Posts Replies Media Videos
video generation using controlnets including camera moves
arxiv.org/html/2506.23...
July 13, 2025 at 6:39 AM
dynamic3dgaussians.github.io
Dynamic 3D Gaussians
July 12, 2025 at 3:54 PM
github.com/Kartel-ai/Co...
A custom node for ComfyUI providing an interactive 3D viewer for 8i volumetric videos (MPD format), allowing frame capture and integration into workflows.
July 10, 2025 at 9:31 AM
huggingface.co/collections/...
WAN Fun Control - AI Video Controlnet in ComfyUI
youtu.be/Cx33lpVAV74?...
July 10, 2025 at 8:48 AM
liuff19.github.io/LangScene-X/
A unified model that generates RGB, segmentation map, and normal map and the following reconstructed 3D field from sparse views input.
July 6, 2025 at 5:42 PM
tau-yihouxiang.github.io/projects/EX-...
Camera-controllable videos from monocular inputs.
July 6, 2025 at 11:31 AM
animateanymesh.github.io/AnimateAnyMe...
Animate a non rigged 3D model
June 29, 2025 at 5:26 AM
anima-x.github.io
Animate a rigged 3d model from a prompt
June 29, 2025 at 5:18 AM
research.nvidia.com/labs/dir/par...
3D Object Generation with segmentation fron nvidia
June 22, 2025 at 6:17 AM
github.com/Tencent-Huny...
Image to 3D
June 22, 2025 at 6:14 AM
cvlab-kaist.github.io/TAIR/
Image Restoration
June 22, 2025 at 6:13 AM
meigen-ai.github.io/multi-talk/?...
MultiTalk, a novel framework for audio-driven multi-person conversational video generation.
June 16, 2025 at 7:50 PM
weathermagician.github.io?ref=manuagi
Simulate rain, fog, snow, etc...
June 16, 2025 at 7:45 PM
nju-3dv.github.io/projects/Dir...
Direct3D-S2: High resolution 3D generation from image
June 16, 2025 at 7:36 PM
lizhihao6.github.io/Sparc3D/
Sparc3D: model generation
June 16, 2025 at 9:00 AM
wgsxm.github.io/projects/par...
PartCrafter: Structured 3D Mesh Generation.
Generates a segmented 3D mesh from a source image to later edit parts of it.
June 15, 2025 at 6:18 AM
sihuiji.github.io/LayerFlow-Pa...
LayerFlow: Layer Video Generation. Per-layer prompts, it generates videos for the transparent foreground, clean background, and blended scene. Supports variants like decomposing a blended video or generating the background for the given foreground and vice versa.
June 15, 2025 at 5:50 AM
vivocameraresearch.github.io/any2bokeh/
Video Bokeh/Rack focus/small depth of field
June 15, 2025 at 5:37 AM
iceclear.github.io/projects/see...
SeedVR2: 1080p Video Restoration/Sharpening
One-Step Video Restoration/Sharpening
June 15, 2025 at 5:24 AM
aistudynow.com/wan-2-1-fusi...
Improved version of Wan text to video.
June 13, 2025 at 6:29 AM
hunyuanvideo-avatar.github.io
github.com/deepbeepmeep...
youtu.be/ZpfhtonDML4?...
HunyuanVideo-Avatar: High-Fidelity Audio-Driven Human Animation
June 11, 2025 at 4:26 PM
Autoregressive (AR) image generation method that models images through a next-detail prediction strategy. Apparently requires a lot less tokens. By Bytedance. github.com/ByteFlow-AI/...
June 8, 2025 at 6:31 PM
simongiebenhain.github.io/pixel3dmm/
Single-Image 3D Face Reconstruction
June 8, 2025 at 2:27 PM
hunyuancustom.github.io
Hunyuan now also does driven videos from audio
June 8, 2025 at 2:21 PM
SkyReels-Audio: Omni Audio-Conditioned Talking Portraits in Video Diffusion Transformers
skyworkai.github.io/skyreels-aud...
Generation and editing of audio-conditioned talking portraits guided by multimodal inputs, including text, images, and videos.
June 8, 2025 at 2:14 PM