ImageToVideoGenXLDiffusers
Python template · sinapsis_huggingface_diffusers.templates.image_to_video_gen_xl_diffusers
Overview
This class implements a specific template for image-to-video generation using Hugging Face's diffusers. The `ImageToVideoGenXLDiffusers` class inherits from the `ImageToImageDiffusers` template to define how to handle converting input images into videos with the I2VGen-XL pipeline.
Parameters to be used inside generation_params can be seen at HuggingFace documentation: https://huggingface.co/docs/diffusers/api/pipelines/i2vgenxl
Capabilities
Capabilities: not setInstallation
Install the published package using pip or uv.
pip install sinapsis-huggingface-diffusers==1.0.0uv pip install sinapsis-huggingface-diffusers==1.0.0uv add sinapsis-huggingface-diffusers==1.0.0Configuration
Effective fields from the inspector schema, including nested Pydantic model fields.
Optional
Default: null
Required
Default: null
Optional
Default: null
Optional
Default: "stable-diffusion-v1-5/stable-diffusion-v1-5"
Optional
Default: "float16"
Optional
Default: "/home/ariel/.cache/sinapsis"
Optional
Default: false
Task-specific parameters for video generation, such as `num_frames` and `target_fps`.
Optional
Default: null
Optional
Default: null
Optional
Default: null
Optional
Default: null
The total number of frames to generate in the video. Defaults to 16.
Optional
Default: 16
The target frames per second for the generated video.
Optional
Default: null
Optional
Default: 7.5
Optional
Default: null
Optional
Default: 50
Optional
Default: 1
The number of different videos to generate from the same input image and prompt.
Optional
Default: null
Optional
Default: false
Configuration example
Example from the Python docstring:
agent:
name: my_test_agent
templates:
- template_name: InputTemplate
class_name: InputTemplate
attributes: {}
- template_name: ImageToVideoGenXLDiffusers
class_name: ImageToVideoGenXLDiffusers
template_input: InputTemplate
attributes:
model_path: '/path/to/diffusers/model'
model_cache_dir: /path/to/cache/dir
device: 'cuda'
torch_dtype: float16
enable_model_cpu_offload: false
generation_params: {}
overwrite_images: falseShow schema-based configuration skeleton
templates:
- template_name: "ImageToVideoGenXLDiffusers"
class_name: "ImageToVideoGenXLDiffusers"
attributes:
seed: null
device: "<required>"
model_path: "stable-diffusion-v1-5/stable-diffusion-v1-5"
torch_dtype: "float16"
model_cache_dir: "/home/ariel/.cache/sinapsis"
overwrite_images: false
generation_params:
width: null
height: null
prompt: null
num_frames: 16
target_fps: null
guidance_scale: 7.5
negative_prompt: null
num_inference_steps: 50
num_images_per_prompt: 1
num_videos_per_prompt: null
enable_model_cpu_offload: false
Inheritance
sinapsis_huggingface_diffusers.templates.image_to_image_diffusers.ImageToImageDiffusersEnvironment variables
Environment definitions belong to their canonical Python modules.
No directly related environment variables listed.