LingBot Video MoE

uv pip install "sglang[diffusion]" --prerelease=allow

sglang serve \
  --model-path robbyant/lingbot-video-moe-30b-a3b \
  --port 30010

import json
import time
from pathlib import Path

import requests

base_url = "http://127.0.0.1:30010"
prompt = json.dumps(
    {
        "comprehensive_description": {
            "scene_content_description": (
                "A small silver robot arm on a white table slowly reaches "
                "toward a red cube. The background is a softly lit laboratory wall."
            ),
            "camera_movement_description": (
                "The camera is static at eye level in a medium shot."
            ),
        },
        "camera_info": {
            "color": "Neutral",
            "frame_size": "Medium",
            "shot_type_angle": "Eye level",
            "lens_size": "Medium",
            "composition": "Center",
            "lighting": "Soft light",
            "lighting_type": "Artificial light",
        },
        "world_knowledge": [],
        "prominent_elements": [
            {
                "name": "robot arm",
                "description": "A small silver robot arm with a two-finger gripper.",
                "actions": [
                    {
                        "timestamp": "[0.0s - 1.0s]",
                        "action": "reaches toward the red cube",
                    }
                ],
                "location": "center of the frame",
                "relative_size": "dominant",
                "shape_and_color": "articulated silver metal arm",
                "texture": "brushed metal",
                "appearance_details": "two-finger gripper and visible joints",
                "relationship": "reaching toward the red cube on the table",
                "orientation": "upright, base on the table",
                "pose": "reaching",
            }
        ],
    },
    separators=(",", ":"),
)

response = requests.post(
    f"{base_url}/v1/videos",
    json={
        "model": "robbyant/lingbot-video-moe-30b-a3b",
        "prompt": prompt,
        "size": "640x384",
        "num_frames": 17,
        "fps": 16,
        "num_inference_steps": 12,
        "guidance_scale": 6.0,
        "flow_shift": 3.0,
        "seed": 0,
    },
    timeout=60,
)
response.raise_for_status()
video_id = response.json()["id"]

while True:
    job = requests.get(f"{base_url}/v1/videos/{video_id}", timeout=30).json()
    if job["status"] == "completed":
        break
    if job["status"] == "failed":
        raise RuntimeError(job.get("error") or "Video generation failed")
    time.sleep(1)

video = requests.get(
    f"{base_url}/v1/videos/{video_id}/content",
    timeout=300,
)
video.raise_for_status()
Path("lingbot_video_moe.mp4").write_bytes(video.content)