
Rodin Gen-2 engine that turns a text prompt or up to five reference images into production 3D assets with PBR materials and quad or raw meshes.
Rodin Gen-2 engine that turns a text prompt or up to five reference images into production 3D assets with PBR materials and quad or raw meshes.
也称为 Deemos Hyper3D Gen2
hyper3d-gen2/v1/3d/generationsdeemos/hyper3d-gen2hyper3d-gen2-260112rodin-gen2来自 EmpirioLabs 目录的实时按量计费价格。只为实际用量付费,没有月度最低消费。
Hyper3D Gen2 通过 POST /v1/3d/generations 运行。请求会立即返回 job_id;轮询 GET /v1/jobs/{job_id} 直到任务完成,再从结果中读取输出 URL。 在EmpirioLabs 控制台获取 API 密钥。
curl https://api.empiriolabs.ai/v1/3d/generations \
-H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "hyper3d-gen2",
"prompt": "Describe what you want Hyper3D Gen2 to generate."
}'curl https://api.empiriolabs.ai/v1/jobs/JOB_ID \
-H "Authorization: Bearer $EMPIRIOLABS_API_KEY"import requests
response = requests.post(
"https://api.empiriolabs.ai/v1/3d/generations",
headers={"Authorization": "Bearer YOUR_EMPIRIOLABS_API_KEY"},
json={
"model": "hyper3d-gen2",
"prompt": "Describe what you want Hyper3D Gen2 to generate.",
},
)
job = response.json()
# Generation runs as an async job. Poll until it completes.
import time
while True:
status = requests.get(
f"https://api.empiriolabs.ai/v1/jobs/{job['job_id']}",
headers={"Authorization": "Bearer YOUR_EMPIRIOLABS_API_KEY"},
).json()
if status.get("status") in ("completed", "failed"):
print(status)
break
time.sleep(5)EmpirioLabs 上 Hyper3D Gen2 API 支持的请求参数。省略字段时使用默认值。
| 参数 | 类型 | 默认值 | 范围 / 值 | 描述 |
|---|---|---|---|---|
| prompt | string | - | - | Text description of the object, in English, up to 400 characters. Optional when input images are provided. |
| image | array | - | - | Up to five input images of the object. Multiple images act as multi-view references. |
| material | enum | PBR | PBR, Shaded, All, None | Texture output: PBR maps, Shaded baked lighting, All for both, or None for an untextured white mesh. |
| mesh_mode | enum | Quad | Quad, Raw | Quad outputs a quad mesh; Raw outputs a triangle mesh with higher face-count ceilings. |
| subdivision_level | enum | - | high, medium, low | Preset face-count level for the chosen mesh mode. Ignored when quality_override is set. |
| quality_override | integer | - | 500 到 1000000 | Custom face count. Raw meshes accept 500 to 1,000,000; Quad meshes 1,000 to 200,000. |
| hd_texture | boolean | false | - | Generate HD textures. |
| high_pack | boolean | false | - | Upgrade texture maps to 4K (2K without it). |
| use_original_alpha | boolean | false | - | Preserve transparent regions of the input image. |
| ta_pose | boolean | false | - | Force humanoid subjects into a standard T or A binding pose. |
| seed | integer | - | 0 到 65535 | Seed in [0, 65535]. Same seed gives similar, not identical, results. |
Generates one 3D asset per request from a text prompt (English, up to 400 characters), one to five reference images, or both. Billing is a flat rate per generated model.
在 EmpirioLabs,Hyper3D Gen2 按量计费:Per generation $0.80 per request。本页的实时价格表始终与 API 的实际计费一致。
Hyper3D Gen2 通过 api.empiriolabs.ai 上的 POST /v1/3d/generations 提供,使用标准的 Bearer 令牌认证。
可以。EmpirioLabs Playground在浏览器中以与 API 相同的参数运行 Hyper3D Gen2,你可以在写代码之前先测试提示词。
创建 EmpirioLabs 账户,然后在控制台的 API Keys生成密钥。计费使用按量付费的额度,只为实际发出的请求付费。