Wan2.2 Image to Video (2 images; video generation from start and end images, 2-stage sampling)

Input two static images (start and end) to generate anime-style videos using two-stage sampling and LoRA fusion technology.
Frame count and resolution are automatically adjusted, and it supports speech synthesis. Ideal for creation, video production, character PVs, and more.
- Quantization Model: GGUF Q4
- Specify output short side: Default = 480pixel
* Long side is determined by the aspect ratio of the input image
- Specify video duration and frame rate: Default = 5s * 24FPS (total frames automatically calculated)
- Configurable