shield_lock
金大哥
← 返回 Skill 列表
extension
分类: 内容与媒体无需 API Key

sophnet-image-edit

当用户请求SophNet图像编辑（图像到图像）时使用，包括多图像编辑任务（合成、风格转换、区域交换），所有上传的图像路径必须从媒体理解日志中解析（通常是media/inbound/images/*），并按顺序传递给模型Qwen-Image-Edit-2509。

person作者: jakexiaohubgithub
open_in_new仓库download下载资源包

SophNet Image Edit

Overview

Edit existing images with Python scripts that handle task polling and structured output.

Script responsibilities:

  • edit_image.py: core API caller and polling loop, outputs INPUT_IMAGE_COUNT, TASK_ID, STATUS, and IMAGE_URL.
  • edit_and_preview.sh: wrapper for local use, calls edit_image.py, downloads first result, adds PREVIEW_PATH.

When to Use

  • User asks to edit or transform existing images with Sophnet.
  • Task uses one or more source images (URL or uploaded local files).
  • Task depends on image order/role, such as:
    • put part of image-2 into image-1
    • render image-2 with image-1 style
    • blend/composite many images into one result
  • Do not use when the task is pure text-to-image generation; use sophnet-image-generate.

Image Path Resolution

When users upload images in chat channels, files are usually saved under media/inbound/images/ in the workspace. Use Media Understanding logs to get exact resolved paths.

Typical log pattern:

[Media Understanding] Resolved relative path: "media/inbound/images/xxx.jpg" -> "/absolute/path/to/workspace/media/inbound/images/xxx.jpg"

Path rules:

  • --image accepts URL, data URI, or local file path.
  • Local file paths are auto-converted to data URI by the script.
  • For multi-image tasks, pass every image explicitly and in required order.

Multi-Image Rules

  1. Keep source image order stable and explicit.
  2. Bind prompt language to order (image-1, image-2, image-3...).
  3. Do not drop "reference" images; pass all images used by the prompt.
  4. Verify script output INPUT_IMAGE_COUNT equals expected image count before trusting results.

Recommended prompt pattern for multi-image tasks:

  • 图1作为底图，图2提供主体元素，图3提供风格参考；将图2主体抠出放到图1右上角，并按图3风格整体渲染。

Quick Reference

| Goal | Command | | --- | --- | | Edit with one source | bash {baseDir}/scripts/edit_and_preview.sh --prompt "..." --image "https://example.com/source.jpg" | | Edit with two sources (ordered) | bash {baseDir}/scripts/edit_and_preview.sh --prompt "图1作为底图，将图2主体放入图1左下角" --image "media/inbound/images/img1.jpg" --image "media/inbound/images/img2.jpg" | | Style transfer across two images | uv run --project {baseDir} python {baseDir}/scripts/edit_image.py --prompt "使用图1的画风渲染图2内容" --image "/abs/path/style.jpg" --image "/abs/path/content.jpg" | | Many images via CSV | uv run --project {baseDir} python {baseDir}/scripts/edit_image.py --prompt "..." --images "media/inbound/images/a.jpg,media/inbound/images/b.jpg,https://example.com/c.jpg" | | Many images via list file | uv run --project {baseDir} python {baseDir}/scripts/edit_image.py --prompt "..." --images-file "/tmp/image-list.txt" | | Validate image count only | uv run --project {baseDir} python {baseDir}/scripts/edit_image.py --prompt "..." --images-file "/tmp/image-list.txt" --dry-run | | Show options | uv run --project {baseDir} python {baseDir}/scripts/edit_image.py --help |

Notes:

  • --dry-run does not require API key and is for input-count verification only.
  • Prefer --images-file when handling many images or values that may contain commas.

/tmp/image-list.txt format example:

# One image reference per line
media/inbound/images/base.jpg
media/inbound/images/object.png
https://example.com/style.jpg

Script Output Fields

The script outputs structured key=value lines. Parse all of them:

| Field | Description | | --- | --- | | INPUT_IMAGE_COUNT | Number of source images passed to the API | | TASK_ID | API task identifier | | STATUS | succeeded or failed | | OUTPUT_COUNT | Number of result images | | IMAGE_URL | Publicly accessible signed URL for each result image | | PREVIEW_PATH | Local file path (only when OSS re-upload failed as fallback) |

Presenting Results to Users

After a successful edit, present the results with context -- not just a bare URL. Include:

  1. What was done: mention the edit instruction / style applied.
  2. Input/output image counts.
  3. The result image URL(s): provide the IMAGE_URL so the user can view/download.
  4. If PREVIEW_PATH is present, mention the local file path.

Example response pattern:

图片编辑完成！

- 编辑指令：把图片变成水彩画风格
- 输入图片数：1
- 结果图片：<IMAGE_URL>

Implementation

  1. Resolve all uploaded image paths from Media Understanding logs.
  2. If this edit step follows sophnet-image-generate, prefer upstream IMAGE_URL for handoff; use PREVIEW_PATH only when local-file input is explicitly intended.
  3. Build prompt with explicit image order semantics.
  4. Run script with one --image per image, or --images, or --images-file.
  5. For multi-image tasks, run once with --dry-run and confirm INPUT_IMAGE_COUNT matches intended image count.
  6. Parse ALL output fields (see table above) and present them to the user.
  7. Use PREVIEW_PATH when present.

API payload shape:

  • model: Qwen-Image-Edit-2509
  • input.prompt: edit instruction with image-role semantics
  • input.images[]: all source image refs in strict order
  • parameters: size, n, watermark

Common Mistakes

  • Passing only one image for a multi-image prompt.
  • Mentioning image-2/image-3 in prompt but not passing those images.
  • Reordering --image arguments unintentionally.
  • Ignoring INPUT_IMAGE_COUNT mismatch.
  • Using non-existent local paths.
  • In generate→edit workflows, defaulting to PREVIEW_PATH instead of IMAGE_URL without reason.
  • Only showing a bare URL without context -- always present a summary with edit details.