V1 API¶
FastVideo's V1 API provides a streamlined interface for video generation tasks with powerful customization options. This page documents the primary components of the API.
Video Generator¶
This class will be the primary Python API for generating videos and images.
VideoGenerator(fastvideo_args: FastVideoArgs, executor_class: type[Executor], log_stats: bool)
A unified class for generating videos using diffusion models.
This class provides a simple interface for video generation with rich customization options, similar to popular frameworks like HF Diffusers.
Initialize the video generator.
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
fastvideo_args
|
FastVideoArgs
|
The inference arguments |
required |
executor_class
|
type[Executor]
|
The executor class to use for inference |
required |
Functions¶
classmethod
¶
from_pretrained(model_path: str, device: str | None = None, torch_dtype: dtype | None = None, **kwargs) -> VideoGenerator
Create a video generator from a pretrained model.
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
model_path
|
str
|
Path or identifier for the pretrained model |
required |
device
|
str | None
|
Device to load the model on (e.g., "cuda", "cuda:0", "cpu") |
None
|
torch_dtype
|
dtype | None
|
Data type for model weights (e.g., torch.float16) |
None
|
pipeline_config
|
Pipeline config to use for inference |
required | |
**kwargs
|
Additional arguments to customize model loading, set any FastVideoArgs or PipelineConfig attributes here. |
{}
|
Returns:
| Type | Description |
|---|---|
VideoGenerator
|
The created video generator |
Priority level: Default pipeline config < User's pipeline config < User's kwargs
VideoGenerator.from_pretrained() should be the primary way of creating a new video generator.
Configuring FastVideo¶
The following two classes PipelineConfig and SamplingParam are used to configure initialization and sampling parameters, respectively.
PipelineConfig¶
dataclass
¶
PipelineConfig(model_path: str = '', pipeline_config_path: str | None = None, embedded_cfg_scale: float = 6.0, flow_shift: float | None = None, disable_autocast: bool = False, dit_config: DiTConfig = DiTConfig(), dit_precision: str = 'bf16', vae_config: VAEConfig = VAEConfig(), vae_precision: str = 'fp32', vae_tiling: bool = True, vae_sp: bool = True, image_encoder_config: EncoderConfig = EncoderConfig(), image_encoder_precision: str = 'fp32', text_encoder_configs: tuple[EncoderConfig, ...] = (lambda: (EncoderConfig(),))(), text_encoder_precisions: tuple[str, ...] = (lambda: ('fp32',))(), preprocess_text_funcs: tuple[Callable[[str], str], ...] = (lambda: (preprocess_text,))(), postprocess_text_funcs: tuple[Callable[[BaseEncoderOutput], tensor], ...] = (lambda: (postprocess_text,))(), pos_magic: str | None = None, neg_magic: str | None = None, timesteps_scale: bool | None = None, mask_strategy_file_path: str | None = None, STA_mode: STA_Mode = STA_INFERENCE, skip_time_steps: int = 15, dmd_denoising_steps: list[int] | None = None, ti2v_task: bool = False, boundary_ratio: float | None = None)
Base configuration for all pipeline architectures.
Functions¶
classmethod
¶
from_pretrained(model_path: str) -> PipelineConfig
use the pipeline class setting from model_path to match the pipeline config
SamplingParam¶
dataclass
¶
SamplingParam(data_type: str = 'video', image_path: str | None = None, video_path: str | None = None, prompt: str | list[str] | None = None, negative_prompt: str = 'Bright tones, overexposed, static, blurred details, subtitles, style, works, paintings, images, static, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, misshapen limbs, fused fingers, still picture, messy background, three legs, many people in the background, walking backwards', prompt_path: str | None = None, output_path: str = 'outputs/', output_video_name: str | None = None, num_videos_per_prompt: int = 1, seed: int = 1024, num_frames: int = 125, num_frames_round_down: bool = False, height: int = 720, width: int = 1280, fps: int = 24, num_inference_steps: int = 50, guidance_scale: float = 1.0, guidance_rescale: float = 0.0, boundary_ratio: float | None = None, enable_teacache: bool = False, save_video: bool = True, return_frames: bool = False, return_trajectory_latents: bool = False, return_trajectory_decoded: bool = False)
Sampling parameters for video generation.
Functions¶
classmethod
¶
from_pretrained(model_path: str) -> SamplingParam