Skip to content
dreamina-super-resolution logo

图片智能超清工具

dreamina-super-resolution

使用智能超清工具对图片进行高清放大 (pro_hd)

NeverSight/skills_feed0installs215starsOther

SKILL.md

Full skill instructions

图片智能超清工具

API 端点

POST https://jimeng.jianying.com/​mweb/​v1/​aigc_draft/​generate

Python 示例

import requests
import hashlib
import time
import uuid
import json

def generate_sign(uri_path):
    device_time = int(time.time())
    sign_str = f"9e2c|{uri_path[-7:]}|7|5.8.0|{device_time}||11ac"
    sign = hashlib.md5(sign_str.encode()).hexdigest()
    return sign, device_time

def super_resolution(sessionid, image_uri, resolution_type="4k", detail_strength=0.5):
    """
    智能超清 - 将图片放大到 4K 分辨率
    
    Args:
        sessionid: 登录 sessionid
        image_uri: 输入图片 URI (通过 upload_image 获取)
        resolution_type: "2k" 或 "4k",默认 "4k"
        detail_strength: 细节生成程度 0-1,默认 0.5
    """
    uri = "/​mweb/​v1/​aigc_draft/​generate"
    sign, device_time = generate_sign(uri)
    
    component_id = str(uuid.uuid4())
    submit_id = str(uuid.uuid4())
    
    draft_content = {
        "type": "draft",
        "id": str(uuid.uuid4()),
        "min_version": "3.2.8",
        "min_features": ["AIGC_GenerateType_ProHD"],
        "is_from_tsn": True,
        "version": "3.3.8",
        "main_component_id": component_id,
        "component_list": [{
            "type": "image_base_component",
            "id": component_id,
            "min_version": "3.0.2",
            "aigc_mode": "workbench",
            "metadata": {
                "type": "",
                "id": str(uuid.uuid4()),
                "created_platform": 3,
                "created_time_in_ms": str(int(time.time() * 1000))
            },
            "generate_type": "pro_hd",
            "abilities": {
                "type": "",
                "id": str(uuid.uuid4()),
                "pro_hd": {
                    "type": "",
                    "id": str(uuid.uuid4()),
                    "resolution_type": resolution_type,
                    "hd_scene_type": "auto",
                    "original_image_strength": 0.65,
                    "detail_strength": detail_strength,
                    "postedit_param": {
                        "type": "",
                        "id": str(uuid.uuid4()),
                        "generate_type": 35,
                        "origin_image": {
                            "type": "image",
                            "id": str(uuid.uuid4()),
                            "source_from": "upload",
                            "platform_type": 1,
                            "image_uri": image_uri,
                            "uri": image_uri
                        }
                    }
                }
            }
        }]
    }
    
    headers = {
        "Content-Type": "application/​json",
        "Appid": "513695",
        "Appvr": "5.8.0",
        "Pf": "7",
        "Origin": "https://jimeng.jianying.com",
        "Referer": "https://jimeng.jianying.com",
        "Cookie": f"sessionid={sessionid}",
        "Device-Time": str(device_time),
        "Sign": sign,
        "Sign-Ver": "1"
    }
    
    data = {
        "extend": {},
        "submit_id": submit_id,
        "draft_content": json.dumps(draft_content),
        "http_common_info": {"aid": 513695}
    }
    
    resp = requests.post(
        f"https://jimeng.jianying.com{uri}",
        params={
            "aid": 513695, 
            "device_platform": "web", 
            "region": "cn",
            "da_version": "3.3.8",
            "web_version": "7.5.0"
        },
        headers=headers,
        json=data
    )
    return resp.json()

参数说明

字段类型必填说明
image_uristring是输入图片 URI (通过 upload_image 获取)
resolution_typestring否2k 或 4k,默认 4k
detail_strengthfloat否细节生成程度 0-1,默认 0.5

关键参数

  • generate_type: pro_hd
  • gen_type: 35
  • hd_scene_type: auto (自动选择场景)

使用流程

  1. 上传图片获取 image_uri (见 dreamina-upload-image)
  2. 调用智能超清 API
  3. 轮询查询结果 (见 dreamina-query-result)
  4. 下载高清图片

More Other skills

Delegate independent tasks to specialized agents working concurrently with isolated context.

295.4K 206.3K
View

Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.

179.7K 100.1K
View

Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.

179.7K 89.5K
View

A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).

179.7K 76.1K
View

Fundamental design principles for writing maintainable, testable Python code.

40.2K 21.9K
View

Modern responsive layouts using container queries, fluid typography, CSS Grid, and mobile-first strategies.

40.2K 20K
View

Generate Playwright tests from scenarios using interactive browser exploration and validation.

39.7K 18.2K
View

Modern React state management with Redux Toolkit, Zustand, Jotai, and React Query for every state category.

40.2K 14.7K
View

GDPR-compliant data handling with consent management, data subject rights, and privacy controls.

40.2K 14.3K
View

Python error handling patterns including input validation, exception hierarchies, and partial failure handling. Use when implementing validation logic, designing exception strategies, handling batch processing failures, or building robust APIs.

40.2K 13.5K
View

Detailed multi-file refactor planning with safety checks and rollback guidance.

39.7K 13K
View