Tencent's HunyuanVideo, a 13B open-weights text-to-video diffusion transformer. Produces high-motion, photorealistic clips with smooth temporal consistency and was one of the first open models to rival closed systems on motion quality.
При стартиране се резервират 9,18 щ.д. (918 кредита); фактурира се действителното GPU време.
За акаунти без покупка: запусци над 2 кредита изискват допълнително зареждане.
Нов си тук?
10 безплатни кредита (0,10 щ.д.) при регистрация с Google
Използваемо 24 часа след регистрация, до 5 запуска на ден и максимум 2 кредита на запуск. Други методи за вход стартират без кредита.
02
Examples
Real outputs from the public examples of this model on Replicate, with the prompt and settings that produced them. They were not generated live on this page.
Prompt
A cat walks on the grass, realistic style
Продължителност: 0:05
Settings
width
864
height
480
fps
24
Prompt
Close-up, A little girl wearing a red hoodie in winter strikes a match. The sky is dark, there is a layer of snow on the ground, and it is still snowing lightly. The flame of the match flickers, illuminating the girl's face intermittently.
Продължителност: 0:05
Settings
width
864
height
480
fps
24
Prompt
a stylish woman walks down a Tokyo street filled with warm glowing neon and animated city signage. She wears a black leather jacket, a long red dress, and black boots, and carries a black purse. She wears
sunglasses and red lipstick. She walks confidently and casually. The street is damp and reflective, creating a mirror effect of the colorful lights. Many pedestrians walk about.
Продължителност: 0:05
Settings
width
864
height
480
fps
24
Примерни подкани
Примери от каталога на Railwail. Те не бяха генерирани живо на тази страница.
Underwater Scene
Продължителност: 0:08
Camera gliding through a vibrant coral reef teeming with tropical fish, sunlight filtering through the crystal-clear water creating dancing light patterns on the ocean floor, documentary style
Fantasy Animation
Продължителност: 0:06
A tiny glowing fairy emerging from an opening flower bud in an enchanted forest, sparkles trailing behind her wings as she takes flight, magical atmosphere with bioluminescent plants
03
За HunyuanVideo
НакраткоКъм 23 септември 2026 г.
HunyuanVideo е модел на Tencent от категория Генериране на видеа. На Railwail HunyuanVideo струва ≈ 3,06 щ.д. за стартиране.
HunyuanVideo from Tencent is a large open-source text-to-video model built on a DiT architecture with a unified full-attention design. It is known for realistic physics, large-scale motion and good text alignment, and ships its own weights, making it a popular base for fine-tuning and LoRA training.
Фон
За Tencent
Основана 1998 · Shenzhen, China
Tencent Holdings is one of the largest technology and entertainment conglomerates in the world, founded in 1998 by Ma Huateng (Pony Ma) and four co-founders in Shenzhen. Tencent's AI Lab, founded in 2016, and the Hunyuan team (the company's foundation-model group) developed the Hunyuan family of text, image, 3D and video models. HunyuanVideo (released December 2024 with the 13B foundation model open-sourced) was the largest publicly released open-weight video diffusion model at the time, and rapidly became a popular base for community fine-tunes (LoRAs, control nets, audio-driven extensions). The model is hosted on Hugging Face and GitHub under a custom licence that allows research and limited commercial use.
Diffusion Transformer with dual-stream design (separate text/video streams)
HunyuanVideo is a 13B-parameter Diffusion Transformer (DiT) operating on a 3D causal VAE latent. Its denoiser uses a dual-stream / single-stream design inspired by FLUX-1: dedicated text and video streams first process their modalities separately and then concatenate for joint self-attention. Text conditioning combines a CLIP-like vision-language encoder and a multilingual large-language-model text encoder (MLLM) for stronger prompt understanding, especially on long captions. The model is trained with Flow Matching and 3D Rotary Position Embeddings, and uses a progressive curriculum from images to short videos to long videos at 720p / 24 fps. The accompanying paper details a meticulously curated multi-billion-clip dataset with hierarchical filtering and dense bilingual captions. HunyuanVideo supports text-to-video natively and the open release includes a high-quality 5-second / 720p model; community follow-ups added image-to-video, audio-driven and longer-duration variants.
Параметри
13 billion
Възможности
13B open-weight text-to-video model (one of the largest released openly)
Generates ~5-second clips at 720p / 24 fps natively
Bilingual Chinese/English prompt handling via MLLM text encoder
Dual-stream DiT architecture inspired by FLUX-1
Strong prompt adherence on long, dense captions
Active community ecosystem (image-to-video, LoRAs, audio-sync)
Runs on 60-80 GB GPU memory (FP16), 40 GB with optimisations
Permissive licence for non-commercial research and limited commercial use
Best for: open-source video pipelines, research, on-prem creative tooling.
Обучение и лиценз
Multi-billion-clip curated video corpus with hierarchical aesthetic, motion and caption-quality filtering, plus dense bilingual captions produced by an in-house MLLM captioner.
Лиценз: Tencent Hunyuan Community Licence: weights free for research and limited commercial use with attribution; restrictions apply above thresholds and for certain jurisdictions.
Тестване на безопасност: Released with safety filtering during training and a recommended NSFW classifier for deployment; subject to Chinese CAC algorithmic-content rules on Tencent-hosted surfaces.
Известни ограничения
Native duration ~5 seconds
720p only (extensions require upscalers)
High VRAM requirements vs smaller open models
No native audio
Licence has thresholds for very large commercial deployers
Цените са в US долари. Използването се начислява от предплатени кредити.
Типично стартиране (≈ 418 s на 4x H100)
3,06 щ.д. за стартиране
GPU време (4x H100)
0,00732 щ.д. за GPU секунда
Таксува се по GPU времето, което стартирането действително отнема. При начало на стартирането 3× типичната цена се резервира от баланса ти и се уреждат впоследствие.
1 кредит = 0,01 щ.д.
Калкулатор на разходите
Калкулатор за цени
s
Типично според доставчика: около 418 s
Общо
306,00 щ.д.
30 600 кредита
На изпълнение
3,06 щ.д. · 306 кредита
Начислява се действителното GPU време; това е оценка.
05
API
Извикайте HunyuanVideo с вашия Railwail API ключ. Използвайте този ID на модела в заявката:
curl https://railwail.com/api/v1/videos/generations \
-H "Authorization: Bearer $RAILWAIL_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "hunyuan-video",
"prompt": "A slow drone shot over a misty pine forest at sunrise"
}'
# Response: {"job_id": "...", "status": "queued", ...}
# Poll until status is completed, failed or cancelled:
curl https://railwail.com/api/v1/jobs/JOB_ID \
-H "Authorization: Bearer $RAILWAIL_API_KEY"
import os
import time
import requests
API = "https://railwail.com/api/v1"
headers = {"Authorization": f"Bearer {os.environ['RAILWAIL_API_KEY']}"}
job = requests.post(
f"{API}/videos/generations",
headers=headers,
json={
"model": "hunyuan-video",
"prompt": "A slow drone shot over a misty pine forest at sunrise",
},
).json()
while True:
status = requests.get(f"{API}/jobs/{job['job_id']}", headers=headers).json()
if status["status"] in ("completed", "failed", "cancelled"):
break
time.sleep(5)
print(status["status"], status.get("output_url"))
const API = "https://railwail.com/api/v1";
const headers = {
Authorization: `Bearer ${process.env.RAILWAIL_API_KEY}`,
"Content-Type": "application/json",
};
const job = await fetch(`${API}/videos/generations`, {
method: "POST",
headers,
body: JSON.stringify({
model: "hunyuan-video",
prompt: "A slow drone shot over a misty pine forest at sunrise"
}),
}).then((r) => r.json());
let status;
do {
await new Promise((r) => setTimeout(r, 5000));
status = await fetch(`${API}/jobs/${job.job_id}`, { headers }).then((r) => r.json());
} while (!["completed", "failed", "cancelled"].includes(status.status));
console.log(status.status, status.output_url);
Tencent Hunyuan Community Licence: weights free for research and limited commercial use with attribution; restrictions apply above thresholds and for certain jurisdictions.
Каталогът е актуализиран
23 септември 2026 г.
Входни параметри
Входове и настройки от входната схема на модела. Примерът в раздела API показва кои от тях приема API.
HunyuanVideo е модел от Tencent в категория Генериране на видеа. На Railwail можеш да го извикаш с API ключ чрез Railwail API.
Колко струва HunyuanVideo на Railwail?
На Railwail HunyuanVideo струва ≈ 3,06 щ.д. за стартиране. Таксуват се само ресурсите, които всяка заявка действително използва. Използването се плаща с предварително закупени кредити; 1 кредит е равен на 0,01 щ.д..
Какви настройки поддържа HunyuanVideo?
Според схемата на входа, HunyuanVideo познава тези параметри: prompt (до 2000 символа) и seed.
Колко бърз е HunyuanVideo?
Все още няма достатъчно измерени задачи на HunyuanVideo на Railwail, за да се посочи време на изпълнение. Зависи от входа, настройките и натоварването на доставчика.
Е ли HunyuanVideo по-добър от Google Veo 3.1?
Зависи от задачата. HunyuanVideo (Tencent) и Google Veo 3.1 (Google DeepMind) са и двата модела в категория Генериране на видеа. Страницата за сравнение показва техните цени и спецификации един до друг.
Създай Railwail API ключ и изпрати твоята заявка с ID на модела hunyuan-video. Примери на код за curl, Python и JavaScript са в раздела API на тази страница.
