# Qwen | Image Edit 2511 | Multiple Angles Generates the same scene from different perspectives by adjusting azimuth and elevation, leveraging Qwen Image Edit 2511 with LoRA Multiple Angles for consistent and detailed results. ## API Information - **Model Slug:** qwen-image-edit-2511-multiple-angles - **Branded URL:** https://www.eachlabs.ai/alibaba/qwen/qwen-image-edit-2511-multiple-angles - **Provider:** Alibaba - **Category:** Image to Image - **Output Type:** image - **Status:** active - **Version:** 0.0.1 - **Base Cost:** Per-megapixel pricing (round rounding) - **Estimated Processing Time:** 15 seconds - **Last Updated:** 2026-04-29 - **Interactive Demo:** https://www.eachlabs.ai/ai-models/qwen-image-edit-2511-multiple-angles ## Pricing - **Charge Type:** dynamic - **Pricing Details:** Per-megapixel pricing (round rounding) ### Pricing Rules | Condition | Pricing | | --- | --- | | output.width < "708" AND output.height < "708" | Minimum 1 MP for small images (< 708x708, round rounding) | | Rule 2 | Per-megapixel pricing (round rounding) | ## Input Schema | Parameter | Type | Required | Default | Constraints | Description | |-----------|------|----------|---------|-------------|-------------| | image_urls | array | Yes | - | 1–15 | The URL of the image to adjust camera angle for. | | horizontal_angle | number | No | 0 | 0–360 | Horizontal rotation angle around the object in degrees. 0°=front view, 90°=right side, 180°=back view, 270°=left side, 360°=front view again. | | vertical_angle | number | No | 0 | -30–90 | Vertical camera angle in degrees. -30°=low-angle shot (looking up), 0°=eye-level, 30°=elevated, 60°=high-angle, 90°=bird's-eye view (looking down). | | zoom | number | No | 5 | 0–10 | Camera zoom/distance. 0=wide shot (far away), 5=medium shot (normal), 10=close-up (very close). | | lora_scale | number | No | 1 | 0–4 | The scale factor for the LoRA model. Controls the strength of the camera control effect. | | image_size | string | No | square_hd | square_hd,square,portrait_4_3,portrait_16_9,landscape_4_3,landscape_16_9 | The size of the generated image. If not provided, the size of the input image will be used. | | guidance_scale | number | No | 4.5 | 1–20 | The CFG (Classifier Free Guidance) scale. | | num_inference_steps | integer | No | 28 | 1–50 | The number of inference steps to perform. | | acceleration | string | No | regular | none,regular | Acceleration level for image generation. | | negative_prompt | string | No | - | - | The negative prompt for the generation | | seed | string | No | - | - | Random seed for reproducibility. | | enable_safety_checker | boolean | No | true | - | Whether to enable the safety checker. | | output_format | string | No | png | png,jpeg,webp | The format of the output image | | num_images | integer | No | 1 | 1–4 | Number of images to generate | ## Example Request ```bash curl -X POST https://api.eachlabs.ai/v1/prediction/ \ -H "X-API-Key: YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "qwen-image-edit-2511-multiple-angles", "input": { "image_urls": [ "https://storage.googleapis.com/magicpoint/inputs/qwen-image-edit-2511-multiple-angles-input.png" ] } }' ``` ## Output Schema Response returned by `GET /v1/prediction/{id}` when the job completes: ```json { "status": "success", "predictionID": "string", "output": "string (URL of generated image)", "metrics": { "predict_time": "number (seconds)" } } ``` ## Polling ```bash curl https://api.eachlabs.ai/v1/prediction/{PREDICTION_ID} \ -H "X-API-Key: YOUR_API_KEY" ``` | Status | Meaning | |--------|---------| | `processing` | Still running — poll again | | `success` | Done — read `output` | | `error` | Failed — read `message` / `details` | ## Webhook (alternative to polling) Pass `"webhook_url": "https://your.host/path"` in the create request. Eachlabs POSTs this payload when the job ends: ```json { "exec_id": "prediction-uuid", "status": "succeeded", "output": "https://...", "error": "" } ``` `status` is `"succeeded"` or `"failed"`. `exec_id` equals the `predictionID` from create. Return 2xx within 30 seconds. ## Errors Error body: `{ "status": "error", "message": "...", "details": "..." }` | Code | Meaning | |------|---------| | `400` | Invalid input | | `401` | Missing / invalid `X-API-Key` | | `404` | Unknown model or prediction id | | `429` | Rate limit — 100 creates / min, 10 concurrent per key | | `5xx` | Retry with backoff | ## Overview **qwen-image-edit-2511-multiple-angles — Image Editing AI Model** qwen-image-edit-2511-multiple-angles, developed by Alibaba as part of the Qwen family, revolutionizes **image-to-image AI model** workflows by generating consistent scenes from multiple angles using a single input image and text prompt. This LoRA-fine-tuned version of Qwen Image Edit 2511 enables precise control over azimuth and elevation adjustments, delivering detailed, coherent outputs without common distortions seen in multi-view generation. Ideal for developers seeking an **Alibaba image-to-image** solution, it leverages synthetic data training for superior angle consistency, solving the challenge of creating 360-degree product views or architectural renders efficiently. Powered by Alibaba's advanced unified model architecture, qwen-image-edit-2511-multiple-angles supports intelligent image editing with enhanced detail adherence to prompts, making it a top choice for **AI image editor API** integrations in e-commerce and design applications. ## Usage Notes - API Base URL: `https://api.eachlabs.ai/v1` - Authentication: send `X-API-Key: YOUR_API_KEY`. Generate a key from the Eachlabs dashboard at https://www.eachlabs.ai/dashboard/api-keys. - File-typed parameters (`*_url`, `image_url`, `video_url`, `audio_url`, etc.) accept publicly-reachable HTTPS URLs only. Upload your asset first (GCS / S3 / your CDN) and pass the resulting URL. Data-URIs and localhost URLs are rejected. - For structured parameters (arrays / objects) send real JSON values, not stringified payloads. - Monetary values are reported in USD; per-token / per-megapixel rates may be billed in micro-cents internally. - Prefer `webhook_url` over polling for long-running predictions — see the Webhook Callback section.