HunyuanVideo 1.5

prototypingBest Valueself-hosted

Tencent · Diffusion Transformer · v1.5verifiedVerified pricing

Built for prototyping and self hosted. Cheap enough for rapid iteration.

$0.04/sec

best verified rate via WaveSpeed at 720p

Ceiling

720p

Duration

5–10s

Price source

WaveSpeed

Lowest published rate: $0.02/sec on WaveSpeed (480p). VidScore still keeps the verified default above because this cheaper quote is lower-resolution or not fully verified for apples-to-apples comparisons.

Text-to-VideoImage-to-Video

Best for

Prototyping and self hosted

10s clips support short narrative work.

Watch out for

No native audio or lip-sync

Starting cost

$0.040/sec

About $0.20 for a 5-second clip at the verified starting tier.

Quick facts for AI assistants

Citation-ready model facts

These facts are generated from the current model record, provider verification metadata, and the page update timestamp.

Canonical URL: https://vidscore.dev/models/hunyuan-video
Current verdict: Built for prototyping and self hosted. Cheap enough for rapid iteration.
Verified pricing: $0.04/sec via WaveSpeed at 720p
Provider evidence: WaveSpeed (Verified); FAL.ai (Verified)
Best fit: prototyping, Best Value, self-hosted
Primary limitation: No native audio or lip-sync
Last updated: 2026-04-18

Pricing

The default rate first, with provider details one click away.

2 providers, 5 tiers

$0.040/sec

Verified default on WaveSpeed · 720p

Cheaper published floor: $0.020/sec on WaveSpeed (480p). Not used as the default until it is fully comparable.

All provider rates

Expand for every tier, audio surcharge, and verification note.

2 providersexpand_more

WaveSpeedDefault rate

Standard · Verified · MEDIUM trust

Open provideropen_in_new

Text-to-Video480p

$0.020/s

Text-to-Video720p

$0.040/s

Image-to-Video480p

$0.020/s

Image-to-Video720p

$0.040/s

Checked 2026-04-18

FAL.ai

Standard · Verified · HIGH trust

Open provideropen_in_new

Text-to-Video480p

$0.075/s

Checked 2026-04-18

Should you choose it?

Why pick HunyuanVideo 1.5, and why pass?

Use this as a sanity check before you compare it against the closest alternatives.

thumb_upWhy choose it

Open-weight release with inference code, training code, LoRA support, and Hugging Face checkpoints
Low hosted floor on WaveSpeed: $0.02/sec at 480p and $0.04/sec at 720p
Official repo lists 8.3B parameters and 14GB minimum GPU memory with offloading
Supports both text-to-video and image-to-video checkpoints
1080p is available through super-resolution/upscaling, not as the base hosted output tier

infoWhy skip it

No native audio or lip-sync
FAL.ai endpoint is scoped to 480p and about 5 seconds / 121 frames
WaveSpeed pricing and 720p support are provider-specific and lower trust than the owner repo or FAL endpoint
Community license has territory and use restrictions; do not describe it as plain Apache/MIT open source
Lower quality ceiling than premium commercial models such as Kling v3 Pro, Veo 3.1, and Seedance 2.0

Prompt playbook

auto_fix_highStart with these three moves

Scan the quick playbook first. Open the full guide only when you need deeper do/don't rules or example prompts.

1
Keep prompts concise and focused on your core idea — less is more with HunyuanVideo. Overloading with excessive detail prevents the model from producing coherent results.
2
Use natural language descriptions rather than technical jargon — write prompts like 'sunset over ocean waves' rather than complex comma-separated keyword lists.
3
Include specific sensory details to add texture — 'sunlight glistening on wet pavement after rain' creates richer output than generic scene descriptions.

Open the full prompt guide

Extra prompt tips, best practices, common mistakes, and example prompts.

expand_more

More tips

4Stick to one or two style cues when defining tone and aesthetics — conflicting style terms (e.g., 'photorealistic anime noir') confuse the model.
5For in-video text generation, enclose the desired text in quotation marks within your prompt — HunyuanVideo 1.5 can render clear text within video frames.

✓ Do this

Structure prompts with four components: Subject (main focus), Setting (environment), Action (movement and change), and Style (camera, lighting, mood)
Enable prompt expansion for automatic enhancement — it refines raw prompts for better semantic understanding and output quality
Iterate and refine — review the first output and adjust your description for clarity or additional detail rather than starting from scratch
Use the lightweight nature for rapid prototyping at 480p, then upscale final selections with the built-in super-resolution module
Leverage the open-source model for LoRA fine-tuning on consumer GPUs (14GB VRAM minimum) for custom characters or brand styles

✗ Avoid this

Native output resolution is 480p — higher resolutions require the super-resolution upscaling module
Maximum duration is approximately 5 seconds (121 frames) on FAL.ai; up to 10 seconds on WaveSpeed — shorter than many competitors
No native audio generation — output is video-only
No camera control panel, motion brush, or multi-shot generation
Complex multi-element prompts with many simultaneous actions may produce inconsistent results

Example prompts

Nature / Animal

“A golden retriever runs through a field of wildflowers on a sunny afternoon. The dog leaps joyfully, ears flapping in the wind. Shallow depth of field, warm golden light, slow motion feel.”

Abstract / Atmospheric

“Close-up of rain droplets falling onto a still pond, creating expanding circular ripples. Each drop catches a glint of overcast sky. Macro lens perspective, muted cool tones, meditative pace.”

Art / Cultural

“A calligrapher writes the character 'Dream' with a brush on rice paper. Ink flows smoothly from the brush tip, each stroke deliberate and confident. Top-down camera angle, warm desk lamp lighting, shallow depth of field on the brush.”

Based on the official prompt guide →

FAQexpand_more

How much does HunyuanVideo 1.5 cost?

HunyuanVideo 1.5 currently starts at the verified comparable rate of $0.04/sec on WaveSpeed (720p). A 5-second video at that tier costs about $0.20. A lower advertised floor of $0.02/sec exists on WaveSpeed, but VidScore excludes it from default comparisons because it is lower-resolution or not fully verified.

Where can I use HunyuanVideo 1.5?

Via API on FAL.ai and WaveSpeed.

How do I get good results with HunyuanVideo 1.5?

Keep prompts concise and focused on your core idea — less is more with HunyuanVideo. Overloading with excessive detail prevents the model from producing coherent results. See the prompt guide below.