Text-to-image plus multi-reference editing with up to three source images, selectable quality tiers, and 1K or 2K output resolution.
xAI图像生成发布日期 2026年8月7日专有端点新Text-to-image plus multi-reference editing with up to three source images, selectable quality tiers, and 1K or 2K output resolution.
也称为 Grok Imagine Image, xAI Grok Imagine Image 2.0
grok-imagine-image-2-0/v1/images/generationsPOST/v1/images/editsgrok-imagine-image-2grok-imagine-image-2.0xai/grok-imagine-image-2-0xai/grok-imagine-image-2xai/grok-imagine-image-2.0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。
Grok Imagine Image 2.0 通过 POST /v1/images/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。 也可以加上 "sync": true 跳过轮询：请求保持打开并直接返回 OpenAI 风格的完整图像响应，OpenAI SDK 可以原样使用。 在EmpirioLabs 控制台获取 API 密钥。
curl https://api.empiriolabs.ai/v1/images/generations \
-H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "grok-imagine-image-2-0",
"prompt": "Describe what you want Grok Imagine Image 2.0 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/images/generations",
headers={"Authorization": "Bearer YOUR_EMPIRIOLABS_API_KEY"},
json={
"model": "grok-imagine-image-2-0",
"prompt": "Describe what you want Grok Imagine Image 2.0 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 Grok Imagine Image 2.0 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 | - | - | Describe the image to create. With source images attached, this becomes the editing instruction. Refer to multiple images as <IMAGE_0>, <IMAGE_1>, and so on. Up to... |
| image | array | - | - | One to three source images to edit, as URLs, data URIs, or uploaded image objects. Leave empty to generate from the prompt alone. |
| images | array | - | - | Plural alias for multiple uploaded image references. |
| quality | enum | medium | low, medium | Rendering quality. Low returns in a few seconds and costs less per image. Medium takes longer and resolves finer detail. |
| resolution | enum | 1k | 1k, 2k | Output resolution tier. 2k renders more pixels and costs more per image than 1k. |
| aspect_ratio | enum | auto | auto, 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 2:1, 1:2, 19.5:9, ... | Output aspect ratio. Auto lets the model pick the best fit for the prompt. For an edit, auto follows the first source image. |
| num_images | number | 1 | 1 到 10 | Number of output images. Each output image is billed separately. |
| response_format | enum | url | url, b64_json | Return signed image URLs by default, or include base64 image data when b64_json is requested. |
Generates images from a text prompt, or edits up to three source images from a natural-language instruction.
Place the product from <IMAGE_0> onto the marble surface in <IMAGE_1>.Quality selects how much work goes into the render: low returns in a few seconds, medium takes longer and resolves finer detail. Resolution selects the 1K or 2K output tier. The two combine into four price points, so a low 1K image is the cheapest option and a medium 2K image the most detailed.
Supports prompt, source images (URL or upload), quality, resolution, aspect ratio across fourteen ratios including auto, number of images, and response format.
Generated images pass an automated content-safety check. An image flagged as explicit is not returned. Because the image is generated before the check runs, a flagged generation is still billed.
在 EmpirioLabs，Grok Imagine Image 2.0 按量计费：Low quality, 1K $0.048 per image; Low quality, 2K $0.072 per image; Medium quality, 1K $0.072 per image。本页的实时价格表始终与 API 的实际计费一致。
Grok Imagine Image 2.0 通过 api.empiriolabs.ai 上的 POST /v1/images/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 Grok Imagine Image 2.0，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。
