Hunyuan Custom Ref2V 720p

HunyuanCustom, a multi-modal, conditional, and controllable generation model centered on subject consistency, built upon the Hunyuan Video generation framework. It enables the generation of subject-consistent videos conditioned on text, images, audio, and video inputs.

Features

hunyuan-custom-ref2v-720p is an open-source, multimodal-driven architecture for customized video generation, powered by HunyuanVideo-13B. Outperforming existing open-source models, it rivals top closed-source solutions!

Key Features

Single-Subject Video: Upload an image + text to videos with new actions, outfits, and scenes.
Multi-Subject Video: Generate videos with multiple subjects from separate image inputs.
Audio-Driven Video: Sync audio with visuals for talking or singing in any scene.
Video-Driven Video: Seamlessly insert or replace subjects into any video for creative enhancements.

ComfyUI

hunyuan-custom-ref2v-720p text + image 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

Virtual advertising and try-on: By accepting multiple image inputs, HunyuanCustom enables the creation of virtual human advertisements and virtual try-on experiences with consistent character appearance.
Singing avatar generation: With combined image and audio inputs, it supports the generation of realistic singing avatars for entertainment and digital performer use cases.
Video editing and subject replacement: By using an image and a video as inputs, HunyuanCustom can replace subjects in the video with those from the image, supporting advanced creative editing scenarios.

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/v2/wavespeed-ai/hunyuan-custom-ref2v-720p" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "image": "https://d2g64w682n9w0w.cloudfront.net/media/ec44bbf6abac4c25998dd2c4af1a46a7/images/1746956054461504207_FMWhea6G.png",
    "prompt": "A man is writing a letter at his desk.",
    "negative_prompt": "",
    "size": "1280*720",
    "guidance_scale": 7.5,
    "flow_shift": 13,
    "seed": -1,
    "enable_safety_checker": true
}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v2/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"

Parameters

Task Submission Parameters

Request Parameters

Parameter	Type	Required	Default	Range	Description
image	string	Yes	https://d2g64w682n9w0w.cloudfront.net/media/ec44bbf6abac4c25998dd2c4af1a46a7/images/1746956054461504207_FMWhea6G.png	-	The image for generating the output.
prompt	string	Yes	A man is writing a letter at his desk.	-
negative_prompt	string	No	-	-	The negative prompt for generating the output.
size	string	No	1280*720	1280720, 7201280	The size of the output.
guidance_scale	number	No	7.5	1.0 ~ 10.0	The guidance scale for generation.
flow_shift	number	No	13	1.0 ~ 20.0	The shift value for the timestep schedule for flow matching.
seed	integer	No	-1	-1 ~ 9999999999	The seed for random number generation.
enable_safety_checker	boolean	No	true	-	Whether to enable the safety checker.

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

Hunyuan Custom Ref2V 480p Hunyuan 3D