Jianyi Wang

🔍 SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Training 🎥 Jupyter Notebook 🥳 Thanks to @Iceclearwjy ❤ Shanchuan Lin ❤ Zhijie Lin ❤ Yuxi Ren ❤ Meng Wei ❤ Zongsheng Yue ❤ Shangchen Zhou ❤ Hao Chen ❤ Yang Zhao ❤ Ceyuan Yang ❤ Xuefeng Xiao ❤ Chen…

🚨 Call for Papers – Deadline Approaching! 📸 MIPI Workshop @ ICCV 2025 📅 Oct 20, 2025 | 📍 Honolulu, Hawai‘i Topics: low-level vision, enhancement, editing, efficient AI, camera systems & more! Don’t miss your chance to present—submit now: 🔗 openreview.net/group?id=thecv……

Introducing Seaweed APT2, a real-time, interactive, streaming video generation model. seaweed-apt.com/2 Adversarial training for autoregressive modeling! Streaming 1 minute videos, 1 diffusion step, 24fps real-time on 1xh100, with interactive controls!

ByteDance Seed is back with SeedVR2, now on Hugging Face! This one-step video restoration model leverages diffusion adversarial post-training for impressive results, even on high-resolution videos.

Glad to share Seaweed-7B, a cost-effective foundation model for video generation. Our tech report highlights the key designs that significantly improve compute efficiency and performance given limited resources, achieving comparable quality against other industry-level models. To…

Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolution paper page: huggingface.co/papers/2312.06… Text-based diffusion models have exhibited remarkable success in generation and editing, showing great promise for enhancing visual content with their…

Try StableSR, a diffusion model-based upscaler. We paid extra efforts to maintain fidelity. Code and model: github.com/IceClear/Stabl….

Our work on image super-resolution has been accepted by NeurIPS 2023 as a spotlight. It achieves impressive SR results only with 15 diffusion steps. Welcome to try our demo. @_akhaliq @ccloy @Iceclearwjy Demo: replicate.com/cjwbw/resshift Project page: zsyoaoa.github.io/projects/ressh…

Congrats to @GuangcongW @Iceclearwjy and @Frozen_Burning from MMLab@NTU!

HuggingFace Demo of StableSR is now available at huggingface.co/spaces/Iceclea… ! We would like to thank @huggingface and @_akhaliq for the generous support😊 See our Github repo github.com/IceClear/Stabl… for more demos.

Though unfortunately rejected by #ICCV2023, we are delighted to see that StableSR is becoming a popular choice for real-world SR. Now StableSR also supports WebUI and ModelScope. Check our github page for details!