AMD Hummingbird image-to-video Model

⚡️ In this work, we present AMD Hummingbird-I2V, a compact and efficient diffusion-based I2V model designed for high-quality video synthesis under limited computational budgets.
Hummingbird-I2V adopts a lightweight U-Net architecture with 0.9B parameters and a novel two-stage training strategy guided by reward-based feedback, resulting in substantial improvements in inference speed, model efficiency, and visual quality.
To further improve output resolution with minimal overhead, we introduce a super-resolution module at the end of the pipeline. Additionally, we leverage ReNeg, an AMD proposed reward-guided framework for learning negative embeddings via gradient descent, to further boost visual quality.
As a result, Hummingbird-I2V can generate high-quality 4K video in just 11 seconds with 16 inference steps on an AMD Radeon™ RX 7900 XTX GPU.
Quantitative results on the VBench-I2V benchmark show that Hummingbird-I2V achieves state-of-the-art performance among U-Net-based diffusion models and competitive results compared to significantly larger DiT-based models.
We provide a detailed analysis of the model architecture, training methodology, and benchmark performance.

table { width: auto; border-collapse: collapse; margin: 0 auto; } th, td { border: 1px solid #ddd; text-align: center; padding: 0; vertical-align: middle; width: 256px; } img { width: 384px; height: 240px; object-fit: cover; margin: 0 !important; padding: 0 !important; display: block; } .i2v_training_pipeline { width: 100%; max-width: 1200px; height: auto; object-fit: contain; margin: 0 auto; }