Vidu Start End to Video 2.0

Create dynamic videos using just the first and last frame images, enhanced with text descriptions for seamless storytelling.

Features

Vidu2.0 Start end to Video creates coherent video by adding motion between the start and end frames, and is an effective tool for scene transitions and storytelling.

Key Features

Bi-frame guided synthesis
Strong narrative continuity
Object-aware and human-aware motion interpolation
Adaptive to camera movement and layout shifts

ComfyUI

vidu 2.0 Start end to Video is available on ComfyUI, providing local inference capabilities through a node-based workflow, ensuring flexible and efficient image generation on your system.

Use Cases

Storyboarding and concept animation
Scene interpolation in long-form content
Instructional visual sequences
Film previsualization

Accelerated Inference

Our accelerated inference approach leverages advanced optimization technology from WavespeedAI. This innovative fusion technique significantly reduces computational overhead and latency, enabling rapid image generation without compromising quality. The entire system is designed to efficiently handle large-scale inference tasks while ensuring that real-time applications achieve an optimal balance between speed and accuracy. For further details, please refer to the blog post.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result


# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/vidu/start-end-to-video-2.0" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "images": [
        "https://d2g64w682n9w0w.cloudfront.net/media/images/1745494594983907143_liqlhd9u.jpg",
        "https://d2g64w682n9w0w.cloudfront.net/media/images/1745494607637805608_31gIDzwr.jpg"
    ],
    "prompt": "the iron man transform into the sport car ",
    "duration": 4,
    "movement_amplitude": "auto",
    "seed": 0
}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"

Parameters

Task Submission Parameters

Request Parameters

Parameter	Type	Required	Default	Range	Description
images	array	Yes	https://d2g64w682n9w0w.cloudfront.net/media/images/1745494594983907143_liqlhd9u.jpghttps://d2g64w682n9w0w.cloudfront.net/media/images/1745494607637805608_31gIDzwr.jpg	-	Supports input of two images, with the first uploaded image considered as the start frame and the second image as the end frame. The model will use these provided images to generate the video. For fields that accept images: Only accept 2 images; The pixel density of the start frame and end frame should be similar. The pixel of the start frame divided by the end frame should be between 0.8 and 1.25; Images Assets can be provided via URLs or Base64 encode; You must use one of the following codecs: PNG, JPEG, JPG, WebP; The aspect ratio of the images must be less than 1:4 or 4:1; All images are limited to 50MB; The length of the base64 decode must be under 50MB, and it must include an appropriate content type string.
prompt	string	Yes	the iron man transform into the sport car	-	Text prompt: A textual description for video generation, with a maximum length of 1500 characters.
duration	integer	No	4	4, 8	The number of seconds of duration for the output video. Default to 4 accepted value: 4 8
movement_amplitude	string	No	auto	-	The movement amplitude of objects in the frame. Defaults to auto, accepted value: auto small medium large.
seed	integer	No	-	-1 ~ 9999999999	Random seed: Defaults to a random seed number; Manually set values will override the default random seed.

Response Parameters

Parameter	Type	Description
code	integer	HTTP status code (e.g., 200 for success)
message	string	Status message (e.g., “success”)
data.id	string	Unique identifier for the prediction, Task Id
data.model	string	Model ID used for the prediction
data.outputs	array	Array of URLs to the generated content (empty when status is not `completed`)
data.urls	object	Object containing related API endpoints
data.urls.get	string	URL to retrieve the prediction result
data.has_nsfw_contents	array	Array of boolean values indicating NSFW detection for each output
data.status	string	Status of the task: `created`, `processing`, `completed`, or `failed`
data.created_at	string	ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.error	string	Error message (empty if no error occurred)
data.timings	object	Object containing timing details
data.timings.inference	integer	Inference time in milliseconds

Result Query Parameters

Result Request Parameters

Parameter	Type	Required	Default	Description
id	string	Yes	-	Task ID

Result Response Parameters

Parameter	Type	Description
code	integer	HTTP status code (e.g., 200 for success)
message	string	Status message (e.g., “success”)
data	object	The prediction data object containing all details
data.id	string	Unique identifier for the prediction
data.model	string	Model ID used for the prediction
data.outputs	array	Array of URLs to the generated content (empty when status is not `completed`)
data.urls	object	Object containing related API endpoints
data.urls.get	string	URL to retrieve the prediction result
data.has_nsfw_contents	array	Array of boolean values indicating NSFW detection for each output
data.status	string	Status of the task: `created`, `processing`, `completed`, or `failed`
data.created_at	string	ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.error	string	Error message (empty if no error occurred)
data.timings	object	Object containing timing details
data.timings.inference	integer	Inference time in milliseconds

Vidu Reference to Video 2.0 Step1x Edit