Skip to content
Vladimir Mandic edited this page Mar 22, 2025 · 15 revisions

Video

SD.Next supports video creation using top-level Video tab
Supoport includes T2V: text-to-video and I2V: image-to-video

Tip

Latest video models use LLMs for prompting and due to that requires very long and descriptive prompt

Supported models

SD.Next supports following models out-of-the-box:

Note

All models are auto-downloaded upon first use
Download location uses system paths -> huggingface folder

Tip

Each model may require specific resolution or parameters to produce quality results
This also includes advanced paramters such as Sampler shift which would during normal text-to-image be considered not required to tweak
See individual model's author notes for recommendations on parameters

Legacy models

Additional video models are available as individually selectable scripts in either text or image interfaces

LoRA

SD.Next includes LoRA support for Hunyuan, LTX, WAN, Mochi, Cog

Optimizations

Warning

Any use on GPUs below 16GB and systems below 48GB RAM is experimental

Offloading

Enable offloading so model components can be moved in and out of VRAM as needed
Most models support all offloading types: Balanced, Model and Sequential
However, balanced offload may lead to CPU vs CUDA errors with some models, in which case try other offloading types

Quantization

Enable on-the-fly quantization during load in Settings -> Quantization for additional memory savings

  • BnB
  • TorchAO
  • Optimum-Quanto

You can enable quantization for both or either Transformers and Text-Encoder separately

  • Most T2V and I2V models support on-the-fly quantization of transformers module
  • Most T2V support quantization of text-encoder while I2V model may not due to inability to quantize image vectors

Decoding

Instead of using full VAE that is packaged with the model itself to decode final frames, SD.Next supports use of Tiny VAE as well as ability to use Remote VAE to decode video

  • Tiny VAE: support for Hunyuan, WAN, Mochi
  • Remote VAE: support for Hunyuan

Processing

SD.Next supports two types of optional processing acceleration:

Interpolation

For all video modules, SD.Next supports adding interpolated frames to video for smoother output

Clone this wiki locally