Hunyuan Video

Hunyuan Video is Tencent’s open video family: text-to-video and image-to-video from the HunyuanVideo weights, not a talking-avatar desk. HunyuanVideo 1.5’s public docs list 5–10 seconds at 480p or 720p, 24 fps, with a super-resolution pass up to 1080p. The Tencent Cloud Hy-Video-1.5 API currently fixes 5 seconds and 720p. This unversioned page is the family name, not a Hunyuan 1.5 generate row. ImgToVid does not run Hunyuan; the generator on this page drafts on Seedance 2.5.

01 — Capabilities

An open Tencent video family, not an 8-second Veo picker

Public Hunyuan pages sell T2V and I2V weights. They do not sell a HeyGen-style speaking twin, and this site does not attach Hunyuan 1.5.

01
Open T2V and I2V, not a talking head
HunyuanVideo (GitHub: Tencent-Hunyuan/HunyuanVideo) is a text-to-video and image-to-video model. Original weights list 720p as recommended, with ~129-frame exports. That is a cinematic one-shot family, not an avatar plus audio track.
02
1.5 numbers belong to 1.5, not this page
HunyuanVideo 1.5 (8.3B) docs: 480p or 720p native, 5–10 seconds at 24 fps, optional super-res to 1080p. Tencent Cloud’s Hy-Video-1.5 API currently generates a fixed 5 seconds at 720p. Those are 1.5 pickers, not a generate table for this unversioned page.
03
Hunyuan Image is stills
Hunyuan Image (including Image 3.0 / V3 in Tencent’s image line) is a still product. It does not run from this video page. Opening this page does not attach an image model.
04
Drafts run Seedance 2.5
ImgToVid does not host Hunyuan. The generator on this page is a draft into Create. Seedance 2.5 carries the prompt. Membership and credits are checked there.

02 — Prompt to output

Prompts that match the clips above

Each prompt describes the picture on its card. “Use this prompt” sends that text to Create. The generator on this page runs Seedance 2.5, not Hunyuan.

01 · Portrait
PromptClose-up of a young man with curly hair in a grey knit sweater, soft window light. He glances away, then smiles. Slow push-in, shallow depth of field.
02 · Product
PromptA white leather sneaker on a pale grey studio backdrop, soft diffused light. The camera orbits slowly. Stitching stays sharp, the look stays minimal.
03 · Street
PromptA slow dolly down a cobblestone lane in an old European village. Climbing roses on stone walls, café tables in morning sun, a few people walking in the distance.
04 · Character
PromptA young woman with shoulder-length brown hair in an olive t-shirt, late-afternoon gold light. She turns her head and looks off. Breeze in her hair, a handheld feel.

03 — Where it fits

Jobs the Hunyuan family is selling

Public docs point at a 5-second 720p T2V, a 10-second 1.5 take, or an I2V from a still. They do not sell a Hunyuan generate on this site.

A 5–10 second T2V or I2V on Hunyuan 1.5
480p or 720p native, 1080p via super-res. This page does not open it.
An original HunyuanVideo 720p export
Open weights, ~129 frames. That run stays in Tencent’s OSS stack.
A Hunyuan Image still
That is a different product. This video page will not call it.
A draft shot on ImgToVid
Write the shot here. Seedance 2.5 carries the prompt into Create. Membership and credits are checked there.

04 — Verdict

What Hunyuan actually is

Strengths

Tencent open video family: T2V and I2V
1.5 docs: 5–10s, 480p / 720p, 1080p super-res
Clear split from Hunyuan Image stills
Honest that this unversioned page is not a live Hunyuan row

Trade-offs

No Hunyuan generate on ImgToVid
This page is not Hunyuan 1.5 and not Hunyuan Image
Cloud API 1.5 currently fixes 5s and 720p — that is not this page
Marked coming soon on this site

05 — Side by side

Hunyuan, Veo 3.1 and Kling 4.0

The Hunyuan column is Tencent’s video family. Veo 3.1 and Kling 4.0 numbers below are from those vendors’ public docs. Hunyuan 1.5’s 5–10s row is a later SKU, not a generate on this site.

	Hunyuan	Veo 3.1	Kling 4.0
Developer	Tencent	Google DeepMind	Kuaishou
Single clip	1.5 docs: 5–10s; Cloud API 1.5: 5s	4, 6 or 8 seconds	3–30 seconds
Picture	1.5: 480p / 720p native; 1080p via SR	720p, 1080p, 4K at 24 fps	720p, 1080p and 4K listed
Sound	Not a first-party talking-head soundtrack table	Native, with the picture	Stereo, with lip sync
Start from	Prompt or a still (T2V / I2V)	Prompt, still, first and last frame	Keyframes or 15 references
On ImgToVid	Coming soon	Coming soon	Coming soon

06 — How it works

Start a clip on ImgToVid

Step 1
Describe one shot
Subject, action, camera. Hunyuan will not be the model that runs it.
Step 2
Use the generator on this page
It runs Seedance 2.5, because Hunyuan is not offered here. The prompt and the settings carry into Create.
Step 3
Generate in Create
Membership and credits are checked there. Coming back to this page does not switch the model over to Hunyuan.

07 — FAQ

Hunyuan, in plain terms

What is Hunyuan?

Hunyuan Video is Tencent’s open T2V/I2V family. HunyuanVideo 1.5 is a later SKU with published 5–10 second, 480p/720p docs. Hunyuan Image is a still product. This unversioned page is the family name. ImgToVid does not host Hunyuan.

How long is a Hunyuan clip?

HunyuanVideo 1.5 docs list 5–10 seconds at 24 fps. Tencent Cloud’s Hy-Video-1.5 API currently fixes 5 seconds. Original HunyuanVideo exports around 129 frames. Those are Tencent pickers, not every take on this site.

Is this Hunyuan 1.5 or Hunyuan Image?

No. This page is the unversioned video family. 1.5 is a later SKU. Hunyuan Image is stills. None of them run on ImgToVid from this page.

Does Hunyuan generate audio?

Public HunyuanVideo pages are picture-first T2V/I2V. They do not publish a HeyGen-style talking-head soundtrack table. That is not a Hunyuan one-shot soundtrack on ImgToVid.

Can I generate Hunyuan videos on ImgToVid?

No. The generator on this page runs Seedance 2.5 so you can draft a shot. Hunyuan is marked coming soon.

Can I use the results commercially?

Commercial use of anything you generate on ImgToVid depends on your plan. Check Pricing and our Terms before you publish, and make sure prompts and uploads do not infringe someone else’s rights.