PROMPT 详情

Transform photo to watercolor painting

Transform this photograph into a loose, expressive watercolor painting. Maintain the overall composition and subject placement but introduce visible brushstrokes, soft color bleeds where wet pigment meets wet paper, and areas of unpainted white paper showing through at the edges. Colors should be slightly more saturated than the original. Fine details like text or sharp edges should become soft and painterly. The result should look like a skilled plein air watercolor artist painted this scene on location in a single sitting.
ideogram-v3-remix /api/v1/ideogram_v3/text_to_image
运行信息
模型
ideogram-v3-remix
提供方
Ideogram
服务
Ideogram V3
Endpoint
Text To Image
1. claude mcp add runapi -s user -- npx -y @runapi.ai/mcp
2. 重启 Claude Code
3. 粘贴这个 prompt:生成一张图像:"Transform this photograph into a loose, expressive watercolor painting. Maintain the overall composition and subject placement but introduce visible brushstrokes, soft color bleeds where wet pigment meets wet paper, and areas of unpainted white paper showing through at the edges. Colors should be slightly more saturated than the original. Fine details like text or sharp edges should become soft and painterly. The result should look like a skilled plein air watercolor artist painted this scene on location in a single sitting."
1. codex plugin install runapi-mcp@agents
2. 重启 Codex
3. 粘贴这个 prompt:生成一张图像:"Transform this photograph into a loose, expressive watercolor painting. Maintain the overall composition and subject placement but introduce visible brushstrokes, soft color bleeds where wet pigment meets wet paper, and areas of unpainted white paper showing through at the edges. Colors should be slightly more saturated than the original. Fine details like text or sharp edges should become soft and painterly. The result should look like a skilled plein air watercolor artist painted this scene on location in a single sitting."
1. npx @runapi.ai/mcp init cursor
2. 重启 Cursor
3. 粘贴这个 prompt:生成一张图像:"Transform this photograph into a loose, expressive watercolor painting. Maintain the overall composition and subject placement but introduce visible brushstrokes, soft color bleeds where wet pigment meets wet paper, and areas of unpainted white paper showing through at the edges. Colors should be slightly more saturated than the original. Fine details like text or sharp edges should become soft and painterly. The result should look like a skilled plein air watercolor artist painted this scene on location in a single sitting."
1. npx @runapi.ai/mcp init windsurf
2. 重启 Windsurf
3. 粘贴这个 prompt:生成一张图像:"Transform this photograph into a loose, expressive watercolor painting. Maintain the overall composition and subject placement but introduce visible brushstrokes, soft color bleeds where wet pigment meets wet paper, and areas of unpainted white paper showing through at the edges. Colors should be slightly more saturated than the original. Fine details like text or sharp edges should become soft and painterly. The result should look like a skilled plein air watercolor artist painted this scene on location in a single sitting."
curl -X POST https://runapi.ai/api/v1/ideogram_v3/text_to_image \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'JSON'
{
  "model": "ideogram-v3-remix",
  "prompt": "Transform this photograph into a loose, expressive watercolor painting. Maintain the overall composition and subject placement but introduce visible brushstrokes, soft color bleeds where wet pigment meets wet paper, and areas of unpainted white paper showing through at the edges. Colors should be slightly more saturated than the original. Fine details like text or sharp edges should become soft and painterly. The result should look like a skilled plein air watercolor artist painted this scene on location in a single sitting."
}
JSON
import { IdeogramV3Client } from "@runapi.ai/ideogram-v3";

const client = new IdeogramV3Client({
  apiKey: process.env.RUNAPI_API_KEY,
});

const result = await client.textToImage.run({
  "model": "ideogram-v3-remix",
  "prompt": "Transform this photograph into a loose, expressive watercolor painting. Maintain the overall composition and subject placement but introduce visible brushstrokes, soft color bleeds where wet pigment meets wet paper, and areas of unpainted white paper showing through at the edges. Colors should be slightly more saturated than the original. Fine details like text or sharp edges should become soft and painterly. The result should look like a skilled plein air watercolor artist painted this scene on location in a single sitting."
});
console.log(result.id);
require "runapi/ideogram_v3"

client = RunApi::IdeogramV3::Client.new
result = client.text_to_image.run(
  model: "ideogram-v3-remix",
  prompt: "Transform this photograph into a loose, expressive watercolor painting. Maintain the overall composition and subject placement but introduce visible brushstrokes, soft color bleeds where wet pigment meets wet paper, and areas of unpainted white paper showing through at the edges. Colors should be slightly more saturated than the original. Fine details like text or sharp edges should become soft and painterly. The result should look like a skilled plein air watercolor artist painted this scene on location in a single sitting."
)
puts result.id
package main

import (
  "context"
  "fmt"
  "log"
  "net/http"
  "os"
  "strings"
)

func main() {
  body := strings.NewReader("{\"model\":\"ideogram-v3-remix\",\"prompt\":\"Transform this photograph into a loose, expressive watercolor painting. Maintain the overall composition and subject placement but introduce visible brushstrokes, soft color bleeds where wet pigment meets wet paper, and areas of unpainted white paper showing through at the edges. Colors should be slightly more saturated than the original. Fine details like text or sharp edges should become soft and painterly. The result should look like a skilled plein air watercolor artist painted this scene on location in a single sitting.\"}")
  req, err := http.NewRequestWithContext(context.Background(), http.MethodPost, "https://runapi.ai/api/v1/ideogram_v3/text_to_image", body)
  if err != nil {
    log.Fatal(err)
  }

  req.Header.Set("Authorization", "Bearer "+os.Getenv("RUNAPI_API_KEY"))
  req.Header.Set("Content-Type", "application/json")

  resp, err := http.DefaultClient.Do(req)
  if err != nil {
    log.Fatal(err)
  }
  defer resp.Body.Close()

  fmt.Println(resp.Status)
}
ideogram-v3-remix /api/v1/ideogram_v3/text_to_image 获取 API Key
常见问题

使用这个 ideogram-v3-remix prompt

如何安全复制这个 prompt?

使用完整 prompt 区块旁边的复制按钮。它只复制 prompt 文本,不包含页面标签,所以可以直接粘贴到 agent 指令、JSON 请求体或你自己的 prompt 库。

为什么详情页会显示参数?

有些 prompt 采集时带有画幅、时长或声音控制等生成设置。存在参数时,页面会单独列出,方便你同时复用 prompt 文本和结构化设置。

应该调用哪个 endpoint?

使用 API 代码块里显示的 endpoint 路径。这个路径由 prompt 的 RunAPI 服务和 endpoint 名称生成,并渲染成 curl 与 SDK 示例使用的公开 API URL。

可以不用代码,直接在 agent 里用吗?

可以。在标签切换器里选择 Claude Code、Codex、Cursor 或 Windsurf,安装 RunAPI MCP Server,然后粘贴生成好的指令。指令会包含完整 prompt 文本。