Bailian: wan2.2-i2v-plus:free
Wan2.2-i2v-plus (A14B) is a professional-grade image-to-video foundation model utilizing a novel Mixture-of-Experts (MoE) architecture. It consists of high-noise and low-noise expert sub-models that collaborate during the denoising process to ensure both global structural stability and fine-grained visual details. The "Plus" (A14B) version is trained on a significantly expanded dataset (+83% more video data than Wan2.1), delivering cinematic aesthetic control, superior motion coherence, and precise semantic alignment. It supports resolutions up to 720p/1080p and is highly capable of handling complex camera movements and multi-object interactions.
All providers for this model are busy right now
Every upstream provider has hit its rate limit. The model comes back automatically once limits lift, usually within hours. Try again in a little while or switch to another model.
Request this model on Discord