🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Thanks, arXiv Daily for sharing our work. Excited to share our work has been accepted in #AAAI23 Our code will be soon released at github.com/IceClear/CLIP-… Feel free to have a try!

Exploiting Diffusion Prior for Real-World Image Super-Resolution abs: arxiv.org/abs/2305.07015 paper page: huggingface.co/papers/2305.07… project page: iceclear.github.io/projects/stabl…

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!

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

Congrats to Guangcong Wang Jianyi Wang and Zhaoxi Chen from MMLab@NTU!

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

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

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

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.

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!