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.
US$Â 9,18 (918 credits) worden gereserveerd bij het starten; de werkelijke GPU-tijd wordt gefactureerd.
Voor accounts zonder aankoop: uitvoeringen boven 2 credits hebben een opwaardering nodig.
Nieuw hier?
10 gratis credits (US$Â 0,10) wanneer je je aanmeldt met Google
Bruikbaar 24 uur na aanmelding, tot 5 uitvoeringen per dag en maximaal 2 credits per uitvoering. Andere aanmeldmethoden starten zonder credits.
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
Lengte: 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.
Lengte: 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.
Lengte: 0:05
Settings
width
864
height
480
fps
24
Voorbeeldprompts
Voorbeelden uit de Railwail-catalogus. Ze zijn niet live op deze pagina gegenereerd.
Underwater Scene
Lengte: 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
Lengte: 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
Over HunyuanVideo
SamengevatPer 23 september 2026
HunyuanVideo is een model van Tencent in de categorie Videogenerering. Op Railwail kost HunyuanVideo ≈ US$ 3,06 per uitvoering.
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.
Achtergrond
Over Tencent
Opgericht 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.
Parameters
13 billion
Mogelijkheden
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.
Training & licentie
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.
Licentie: Tencent Hunyuan Community Licence: weights free for research and limited commercial use with attribution; restrictions apply above thresholds and for certain jurisdictions.
Veiligheidstests: Released with safety filtering during training and a recommended NSFW classifier for deployment; subject to Chinese CAC algorithmic-content rules on Tencent-hosted surfaces.
Bekende beperkingen
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
Prijzen in US-dollars. Het gebruik wordt in rekening gebracht via vooraf gekochte credits.
Typische uitvoering (≈ 418 s op 4x H100)
US$Â 3,06 per uitvoering
GPU-tijd (4x H100)
US$Â 0,00732 per GPU-seconde
Afgerekend wordt de GPU-tijd die de run werkelijk gebruikt. Wanneer de run start, wordt het 3-voudige van de typische prijs van uw saldo gereserveerd en later verrekend.
1 credit = US$Â 0,01
Kostencalculator
Prijscalculator
s
Typisch volgens de provider: ongeveer 418 s
Totaal
US$Â 306,00
30.600 credits
Per run
US$ 3,06 · 306 credits
Afgerekend wordt de werkelijke GPU-tijd; dit is een schatting.
05
API
Roep HunyuanVideo aan met je Railwail API-sleutel. Gebruik deze model-ID in het verzoek:
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.
Catalogusitem bijgewerkt
23 september 2026
Invoerparameters
Invoeren en instellingen uit het invoerschema van het model. Het voorbeeld in de API-sectie toont welke daarvan de API accepteert.
HunyuanVideo is een model van Tencent in de categorie Videogenerering. Op Railwail kunt u het aanroepen met een API-sleutel via de Railwail-API.
Hoeveel kost HunyuanVideo op Railwail?
Op Railwail kost HunyuanVideo ≈ US$ 3,06 per uitvoering. U betaalt voor wat elke aanvraag daadwerkelijk verbruikt. Gebruik wordt betaald met vooraf gekochte credits; 1 credit is gelijk aan US$ 0,01.
Welke instellingen ondersteunt HunyuanVideo?
Volgens het invoerschema kent HunyuanVideo deze parameters: prompt (tot 2.000 tekens) en seed.
Hoe snel is HunyuanVideo?
Er zijn nog niet genoeg gemeten runs van HunyuanVideo op Railwail om een uitvoeringstijd op te geven. Dit hangt af van de invoer, de instellingen en de belasting bij de provider.
Is HunyuanVideo beter dan Google Veo 3.1?
Dat hangt van de taak af. HunyuanVideo (Tencent) en Google Veo 3.1 (Google DeepMind) zijn beide modellen in de categorie Videogenerering. De vergelijkingspagina toont hun prijzen en specificaties naast elkaar.
Maak een Railwail-API-sleutel aan en stuur uw aanvraag met de model-ID hunyuan-video. Codevoorbeelden voor curl, Python en JavaScript staan in het API-gedeelte van deze pagina.
