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 tiktok dancer is dancing on a small drone, doing flips and tricks
slow handheld camera movement: Two firebenders face off in a dark alley as heavy rain pours. One exhales steam. Sparks ignite from soaked fists. They launch into motion kicks, spins, flaming strikes that hiss on contact with water. Explosions reflect in puddles. Fire clashes mid-air, casting harsh orange light. A final blast sends water and embers flying toward camera. Stylized urban fantasy with dramatic lighting and intense motion.
From a soaring aerial, the rider rockets across a collapsing skyline, rooftops narrowing into jagged ledges. Camera hovers tight above as he angles through curved glass and steel, void yawning between buildings. Each rooftop leap sparks drama, until he threads impossibly across the final span, city blurring below.
MiniMax (Shanghai Xiyu Technology) was founded in December 2021 by Yan Junjie (former SenseTime general manager) along with co-founders from SenseTime and Microsoft Research Asia. It is one of China's four AI tigers alongside Zhipu, Moonshot and Baichuan. MiniMax developed the abab LLM family, the Hailuo AI consumer chat app and the Hailuo video generator (launched September 2024). The company has raised over $1B from investors including Tencent, Alibaba, HongShan (Sequoia China) and Mihoyo, valuing it at $2.5B+ in 2024. Hailuo Video gained early international traction as one of the first Chinese consumer video AIs available outside China.
Latent video diffusion model (Diffusion Transformer)
Hailuo 2.3 is MiniMax's third-generation video model, building on Hailuo Video-01 and 02. It is a closed-source diffusion-transformer (DiT) operating on a learned spatio-temporal latent space, conditioned on bilingual (Chinese/English) text embeddings and optional image embeddings. Version 2.3 advertises substantial improvements over earlier versions in motion coherence, prompt adherence on complex actions and 'cinematic' control. MiniMax publish no architectural details beyond marketing material, but the product behaviour and reported throughput suggest a multi-billion-parameter DiT trained on a large curated video corpus with synthetic dense captions and reward-model post-training for aesthetics. Hailuo 2.3 supports 6-10 second clips at up to 1080p and a director-style control vocabulary (camera moves, shot scale).
curl https://railwail.com/api/v1/videos/generations \
-H "Authorization: Bearer $RAILWAIL_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "hailuo-23",
"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": "hailuo-23",
"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: "hailuo-23",
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);
MiniMax Hailuo 02 on Replicate. Text-to-video and image-to-video producing 6s or 10s clips at 768p standard or 1080p pro. Known for accurate real-world physics and stable motion.
