Grok Imagine Image Pro

Grok Imagine Image Pro

API Key: $XAI_API_KEY (already 配置d) Save dir: ~/.OpenClaw/media/ (resolves to /data/.OpenClaw/media/ — allowed for Telegram 发送ing)

AvAIlable 模型s grok-imagine-image — standard 质量, faster grok-imagine-image-pro — higher 质量 (default for generation)

• Image Generation

curl -s https://API.x.AI/v1/images/generations \ -H "Authorization: Bearer $XAI_API_KEY" \ -H "Content-Type: 应用/json" \ --data '{ "模型": "grok-imagine-image-pro", "prompt": "", "n": 1, "响应_格式化": "b64_json" }' | python3 -c " 导入 json, sys, base64, os, time os.makedirs(os.path.expanduser('~/.OpenClaw/media'), exist_ok=True) r = json.load(sys.stdin) ts = int(time.time()) for i, img in enumerate(r['data']): img_data = base64.b64decode(img['b64_json']) fpath = os.path.expanduser(f'~/.OpenClaw/media/生成d_{ts}_{i}.png') with open(fpath, 'wb') as f: f.write(img_data) print(fpath) "

Aspect Ratios

添加 "aspect_ratio": "" to the JSON body. Supported values:

Ratio Use case 1:1 Social media, thumbnAIls 16:9 / 9:16 Widescreen, 移动 stories 4:3 / 3:4 Presentations, portrAIts 3:2 / 2:3 Photography 2:1 / 1:2 Banners, headers auto 模型 picks best ratio (default) Batch Generation

设置 "n": (1-10) to 生成 multiple images in one 请求.

• Image Editing / Style Transfer

Edit an existing image by providing a source image plus an edit prompt. Uses the same /v1/images/generations 端点 with an 添加ed image_url field.

Do NOT use /v1/images/edits with multipart — xAI requires JSON.

导入ANT: For local files, use Python to build the payload JSON file, then curl with @file. Inline base64 in curl args causes "Argument 列出 too long" for images >~100KB.

NOTE: This is NOT true image editing — the API 生成s a new image inspired by the source. It cannot make pixel-precise edits (e.g. changing only a car's color while keeping everything else identical).

Edit from local file (recommended 应用roach): python3 -c " 导入 json, base64 with open('', 'rb') as f: b64 = base64.b64encode(f.read()).decode() payload = { '模型': 'grok-imagine-image', 'prompt': '', 'image_url': f'data:image/png;base64,{b64}', 'n': 1, '响应_格式化': 'b64_json' } with open('/tmp/img_edit_payload.json', 'w') as f: json.dump(payload, f) print('Payload ready') " && \ curl -s https://API.x.AI/v1/images/generations \ -H "Authorization: Bearer $XAI_API_KEY" \ -H "Content-Type: 应用/json" \ -d @/tmp/img_edit_payload.json | python3 -c " 导入 json, sys, base64, os, time os.makedirs(os.path.expanduser('~/.OpenClaw/media'), exist_ok=True) r = json.load(sys.stdin) img_data = base64.b64decode(r['data'][0]['b64_json']) fpath = os.path.expanduser(f'~/.OpenClaw/media/edited_{int(time.time())}.png') with open(fpath, 'wb') as f: f.write(img_data) print(fpath) "

Edit from URL: curl -s https://API.x.AI/v1/images/generations \ -H "Authorization: Bearer $XAI_API_KEY" \ -H "Content-Type: 应用/json" \ --data '{ "模型": "grok-imagine-image", "prompt": "", "image_url": "", "n": 1, "响应_格式化": "b64_json" }' | python3 -c " 导入 json, sys, base64, os, time os.makedirs(os.path.expanduser('~/.OpenClaw/media'), exist_ok=True) r = json.load(sys.stdin) img_data = base64.b64decode(r['data'][0]['b64_json']) fpath = os.path.expanduser(f'~/.OpenClaw/media/edited_{int(time.time())}.png') with open(fpath, 'wb') as f: f.write(img_data) print(fpath) "

Style Transfer Examples

Use editing with a style prompt, e.g.:

"Render this as an oil pAInting in impressionist style" "Make this a pencil sketch with detAIled shading" "Convert to pop art with bold colors" "Watercolor pAInting with soft edges"

• 发送ing to Telegram

message 工具: action=发送, channel=telegram, tar获取=, message="", filePath=~/.OpenClaw/media/.png

Always include message field (required even for media-only 发送s) Allowed media paths: /tmp/, ~/.OpenClaw/media/, ~/.OpenClaw/代理s/ Notes Do NOT pass size parameter — returns 400 Aspect ratio: pass aspect_ratio in JSON body (not size) Editing: use image_url field in the generations 端点 (NOT the edits 端点 with multipart) Always use "响应_格式化": "b64_json" — URL 格式化 returns temporary URLs that often 403 For large images: build payload with Python → save to /tmp/ → curl with @file syntax Max 10 images per 请求 Images are subject to content moderation Editing is style-transfer/reimagination, NOT pixel-precise inpAInting