# Seedream v5.0 Pro Edit — Atlas Cloud API > ByteDance flagship next-generation image editing model. Supports up to 10 reference images while preserving identity, lighting, and color tones for professional-quality modifications. This is the machine-readable API reference for **Seedream v5.0 Pro Edit** on Atlas Cloud, a unified API platform for 400+ AI models across text, image, video, audio and 3D. - **Model ID**: `bytedance/seedream-v5.0-pro/edit` - **Built by**: ByteDance - **Modality**: Image - **Model page**: https://www.atlascloud.ai/models/bytedance/seedream-v5.0-pro/edit - **API key**: https://www.atlascloud.ai/console/api-keys - **Docs**: https://www.atlascloud.ai/docs ## Pricing on Atlas Cloud - $0.045 per image - Pay-as-you-go. No minimum spend, no subscription required. > **These are the authoritative Atlas Cloud rates for this model.** Any price that > appears in the vendor description further down refers to a different platform or > a different model variant and does not apply here. ## Use this model from an AI agent Atlas Cloud ships three first-party integration surfaces. All three authenticate with the same API key via the `ATLASCLOUD_API_KEY` environment variable. ### MCP server The official MCP server (`atlascloud-mcp`) exposes this model to any MCP-compatible host — Claude Code, OpenAI Codex, Cursor, Gemini CLI, Goose, Claude Desktop. One-line install: ```bash # Claude Code claude mcp add atlascloud -- npx -y atlascloud-mcp # OpenAI Codex CLI codex mcp add atlascloud -- npx -y atlascloud-mcp # Gemini CLI gemini mcp add atlascloud -- npx -y atlascloud-mcp export ATLASCLOUD_API_KEY="your-api-key" ``` Then ask in plain English; the agent calls `atlas_generate_image` with `model: "bytedance/seedream-v5.0-pro/edit"`. The server fetches each model's schema and validates parameters before submitting, so invalid requests fail fast without spending credits. MCP docs: https://www.atlascloud.ai/docs/mcp-server ### Agent Skills `atlas-cloud-skills` is a portable skill package (API reference, code templates in Python / Node.js / cURL, model IDs with pricing) for Claude Code, Cursor, Codex and 12+ other agents: ```bash npx skills add AtlasCloudAI/atlas-cloud-skills export ATLASCLOUD_API_KEY="your-api-key" ``` Skills docs: https://www.atlascloud.ai/docs/skills ### CLI The `atlas` binary runs Atlas Cloud from a terminal or CI script. Async media jobs are polled and downloaded automatically (use `--no-download` when a script only needs the output URLs): ```bash # Install (Homebrew, npm, or shell installer) brew install AtlasCloudAI/tap/atlascloud # npm install -g atlascloud-cli # curl -fsSL https://raw.githubusercontent.com/AtlasCloudAI/cli/main/install.sh | sh atlas auth login atlas generate image bytedance/seedream-v5.0-pro/edit -p "Your prompt here" ``` CLI docs: https://www.atlascloud.ai/docs/cli ## HTTP API reference - **Submit endpoint (POST)**: `https://api.atlascloud.ai/api/v1/model/generateImage` — start an async generation; returns a `prediction_id` - **Poll endpoint (GET)**: `https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}` — poll this until the prediction finishes - **Model ID**: `bytedance/seedream-v5.0-pro/edit` ## API Information This model can be used via our HTTP API or more conveniently via our client libraries. See the input and output schema below, as well as the usage examples. ### Input Schema The API accepts the following input parameters: - **`model`** (`string`, _required_): model name - Default: `"bytedance/seedream-v5.0-pro/edit"` - **`prompt`** (`string`, _required_): The positive prompt for the generation. Recommended length: under 600 English words. - **`images`** (`array[string]`, _required_): The images to edit. Accepts URLs or Base64 data URLs. A maximum of 10 reference images can be uploaded; the first input image is free and each additional input image adds $0.003. Supported formats: JPEG, PNG, WEBP, BMP, TIFF, GIF, HEIC, HEIF. - Min items: 1 - Max items: 10 - **`size`** (`string`, _optional_): Output image size in 'WIDTH*HEIGHT' pixels. Total pixels must stay within [1,048,576 (1024*1024), 4,194,304 (2048*2048)] and aspect ratio within [1/16, 16]. Billing tier is by total output pixel count: <= 2.36M px bills at the 1.5K tier; larger sizes bill at the 2K tier. - Default: `"2048*2048"` - Options: "2048*2048", "2304*1728", "1728*2304", "2720*1530", "1530*2720", "2496*1664", "1664*2496", "1024*1024", "1536*1536", "1776*1328", "1328*1776", "2048*1152", "1152*2048" - **`output_format`** (`string`, _optional_): Output image file format. Seedream v5.0 Pro supports both JPEG and PNG output. - Default: `"jpeg"` - Options: "jpeg", "png" - **`thinking`** (`string`, _optional_): Controls the deep-thinking phase of automatic prompt optimization. Set to 'disabled' to skip prompt-optimization thinking for faster generation (text-to-image completes significantly faster; editing latency is largely unaffected). - Default: `"enabled"` - Options: "enabled", "disabled" - **`prompt_optimization_mode`** (`string`, _optional_): Prompt optimization mode. 'standard' (default) produces higher-quality prompt optimization but takes longer. 'fast' takes significantly less time with slightly lower quality. Billing is identical in both modes. For the fastest generation set thinking to 'disabled' as well — when thinking is enabled, the deep-thinking phase still dominates latency. - Default: `"standard"` - Options: "standard", "fast" - **`enable_base64_output`** (`boolean`, _optional_): If enabled, the output will be encoded into a BASE64 string instead of a URL. This property is only available through the API. - Default: `false` **Required Parameters Example**: ```json { "model": "bytedance/seedream-v5.0-pro/edit", "prompt": "", "images": [ "" ] } ``` **Full Example**: ```json { "model": "bytedance/seedream-v5.0-pro/edit", "prompt": "", "images": [ "" ], "size": "2048*2048", "output_format": "jpeg", "thinking": "enabled", "prompt_optimization_mode": "standard", "enable_base64_output": false } ``` ### Output Schema The API returns the following output format: - **`created_at`** (`string`, _optional_): ISO timestamp of when the request was created (e.g., "2023-04-01T12:34:56.789Z"). - **`id`** (`string`, _optional_): Unique identifier for the prediction, the ID of the prediction to get. - **`model`** (`string`, _optional_): Model ID used for the prediction. - **`outputs`** (`array[string]`, _optional_): Array of URLs to the generated content (empty when status is not completed). - **`status`** (`string`, _optional_): Status of the task: created, processing, completed, or failed. - **`urls`** (`object`, _optional_): Object containing related API endpoints. **Example Response**: ```json { "created_at": "", "id": "", "model": "", "outputs": [ "" ], "status": "", "urls": {} } ``` ## Usage Examples ### cURL ```bash # Step 1: Start generation (async) curl -X POST "https://api.atlascloud.ai/api/v1/model/generateImage" \ -H "Authorization: Bearer $ATLASCLOUD_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "bytedance/seedream-v5.0-pro/edit", "prompt": "", "images": [ "" ], "size": "2048*2048", "output_format": "jpeg", "thinking": "enabled", "prompt_optimization_mode": "standard", "enable_base64_output": false }' # Response will contain: {"code": 200, "data": {"id": "prediction_id", "status": "processing"}} # Step 2: Poll for result (replace {prediction_id} with the id returned above) curl -X GET "https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}" \ -H "Authorization: Bearer $ATLASCLOUD_API_KEY" # Keep polling until status is "completed", "succeeded" or "failed" # When completed, outputs will contain the generated content URL(s) ``` ## Additional Resources ### Documentation - [Model Playground](https://www.atlascloud.ai/models/bytedance/seedream-v5.0-pro/edit) ## About this model _Vendor-supplied description. Any pricing or endpoint mentioned below refers to_ _other platforms — use the Atlas Cloud values above._ #### 1. Introduction **Seedream 5.0 Pro Edit** is the multi-reference image editing variant of ByteDance's flagship Seedream 5.0 Pro model, unveiled at the Volcano Engine FORCE 2026 conference on June 23, 2026. It applies the Pro model's quality-first generation pipeline to instruction-driven editing: supply one to ten reference images plus a natural-language instruction, and receive a single, carefully composed result that follows the edit while preserving what should not change. Compared with earlier Seedream editing generations, the Pro Edit variant is tuned for the hardest part of reference-based editing — keeping identity, lighting, and color tone consistent while making targeted modifications. Whether swapping the outfit from one photo onto the subject of another, fusing elements from multiple references, or restyling a product shot, the model resolves cross-image relationships ("put the dress from image 2 on the person in image 1") with the Pro tier's elevated prompt adherence ([BytePlus ModelArk](https://docs.byteplus.com/en/docs/ModelArk/1824121)). --- #### 2. Key Features & Innovations - **Multi-Reference Editing (up to 10 images)**: Accepts 1–10 reference images per request — as URLs or Base64 — and reasons across them jointly, enabling subject transfer, style grafting, element fusion, and cross-image composition in a single call. - **Identity, Lighting & Tone Preservation**: Preserves facial features, lighting direction, and color grading of the source material while executing the requested modification — the core requirement for professional retouching workflows. - **Instruction-Style Prompting**: Edits are described conversationally ("replace the outfit in image 1 with the outfit in image 2"), with the model mapping numbered references to inputs automatically. _(Description truncated. Full text on the model page.)_ --- Atlas Cloud — one API for 400+ AI models. Model page: https://www.atlascloud.ai/models/bytedance/seedream-v5.0-pro/edit · Docs: https://www.atlascloud.ai/docs