A [person type] standing full-body near the edge of the frame, slightly to the left, in [real-world incomplete / empty / damaged environment]. The camera is positioned behind and slightly to the right of the person, capturing them from a three-quarter rear angle. The person stands calmly and thoughtfully, looking toward the space ahead. The environment is [describe the real space as it exists now: empty, unfinished, decayed, rigid, lifeless]. The atmosphere feels [emotional tone: quiet, dry, historical, minimal, raw]. Natural light illuminates the scene, creating realistic shadows and depth. Floating hand-drawn sketch lines appear over and within the environment, aligned precisely in perspective with the real space. These sketches represent [what is missing / what once existed / what could exist in the future]. The sketch lines are black, clean, and hand-drawn, resembling [architectural / interior / restoration / urban planning] concept sketches made with pencil or ink. The strokes are expressive, slightly imperfect, and organic — not rigid or mechanical. The sketched elements occupy the foreground and midground, appearing closer to the person than expected. Some sketch lines subtly overlap the person’s silhouette and the real surfaces, visually merging imagination with reality. The sketches float naturally within the scene, seamlessly blending with the environment and conveying the idea of [vision / restoration / transformation / potential] coming to life.
gpt-image-2/api/v1/gpt_image_2/text_to_image
运行信息
模型
gpt-image-2
提供方
OpenAI
服务
Gpt Image 2
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："A [person type] standing full-body near the edge of the frame, slightly to the left, in [real-world incomplete / empty / damaged environment]. The camera is positioned behind and slightly to the right of the person, capturing them from a three-quarter rear angle. The person stands calmly and thoughtfully, looking toward the space ahead. The environment is [describe the real space as it exists now: empty, unfinished, decayed, rigid, lifeless]. The atmosphere feels [emotional tone: quiet, dry, historical, minimal, raw]. Natural light illuminates the scene, creating realistic shadows and depth. Floating hand-drawn sketch lines appear over and within the environment, aligned precisely in perspective with the real space. These sketches represent [what is missing / what once existed / what could exist in the future]. The sketch lines are black, clean, and hand-drawn, resembling [architectural / interior / restoration / urban planning] concept sketches made with pencil or ink. The strokes are expressive, slightly imperfect, and organic — not rigid or mechanical. The sketched elements occupy the foreground and midground, appearing closer to the person than expected. Some sketch lines subtly overlap the person’s silhouette and the real surfaces, visually merging imagination with reality. The sketches float naturally within the scene, seamlessly blending with the environment and conveying the idea of [vision / restoration / transformation / potential] coming to life."
1. codex plugin install runapi-mcp@agents
2. 重启 Codex
3. 粘贴这个 prompt：生成一张图像："A [person type] standing full-body near the edge of the frame, slightly to the left, in [real-world incomplete / empty / damaged environment]. The camera is positioned behind and slightly to the right of the person, capturing them from a three-quarter rear angle. The person stands calmly and thoughtfully, looking toward the space ahead. The environment is [describe the real space as it exists now: empty, unfinished, decayed, rigid, lifeless]. The atmosphere feels [emotional tone: quiet, dry, historical, minimal, raw]. Natural light illuminates the scene, creating realistic shadows and depth. Floating hand-drawn sketch lines appear over and within the environment, aligned precisely in perspective with the real space. These sketches represent [what is missing / what once existed / what could exist in the future]. The sketch lines are black, clean, and hand-drawn, resembling [architectural / interior / restoration / urban planning] concept sketches made with pencil or ink. The strokes are expressive, slightly imperfect, and organic — not rigid or mechanical. The sketched elements occupy the foreground and midground, appearing closer to the person than expected. Some sketch lines subtly overlap the person’s silhouette and the real surfaces, visually merging imagination with reality. The sketches float naturally within the scene, seamlessly blending with the environment and conveying the idea of [vision / restoration / transformation / potential] coming to life."
1. npx @runapi.ai/mcp init cursor
2. 重启 Cursor
3. 粘贴这个 prompt：生成一张图像："A [person type] standing full-body near the edge of the frame, slightly to the left, in [real-world incomplete / empty / damaged environment]. The camera is positioned behind and slightly to the right of the person, capturing them from a three-quarter rear angle. The person stands calmly and thoughtfully, looking toward the space ahead. The environment is [describe the real space as it exists now: empty, unfinished, decayed, rigid, lifeless]. The atmosphere feels [emotional tone: quiet, dry, historical, minimal, raw]. Natural light illuminates the scene, creating realistic shadows and depth. Floating hand-drawn sketch lines appear over and within the environment, aligned precisely in perspective with the real space. These sketches represent [what is missing / what once existed / what could exist in the future]. The sketch lines are black, clean, and hand-drawn, resembling [architectural / interior / restoration / urban planning] concept sketches made with pencil or ink. The strokes are expressive, slightly imperfect, and organic — not rigid or mechanical. The sketched elements occupy the foreground and midground, appearing closer to the person than expected. Some sketch lines subtly overlap the person’s silhouette and the real surfaces, visually merging imagination with reality. The sketches float naturally within the scene, seamlessly blending with the environment and conveying the idea of [vision / restoration / transformation / potential] coming to life."
1. npx @runapi.ai/mcp init windsurf
2. 重启 Windsurf
3. 粘贴这个 prompt：生成一张图像："A [person type] standing full-body near the edge of the frame, slightly to the left, in [real-world incomplete / empty / damaged environment]. The camera is positioned behind and slightly to the right of the person, capturing them from a three-quarter rear angle. The person stands calmly and thoughtfully, looking toward the space ahead. The environment is [describe the real space as it exists now: empty, unfinished, decayed, rigid, lifeless]. The atmosphere feels [emotional tone: quiet, dry, historical, minimal, raw]. Natural light illuminates the scene, creating realistic shadows and depth. Floating hand-drawn sketch lines appear over and within the environment, aligned precisely in perspective with the real space. These sketches represent [what is missing / what once existed / what could exist in the future]. The sketch lines are black, clean, and hand-drawn, resembling [architectural / interior / restoration / urban planning] concept sketches made with pencil or ink. The strokes are expressive, slightly imperfect, and organic — not rigid or mechanical. The sketched elements occupy the foreground and midground, appearing closer to the person than expected. Some sketch lines subtly overlap the person’s silhouette and the real surfaces, visually merging imagination with reality. The sketches float naturally within the scene, seamlessly blending with the environment and conveying the idea of [vision / restoration / transformation / potential] coming to life."
curl -X POST https://runapi.ai/api/v1/gpt_image_2/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "gpt-image-2",
"prompt": "A [person type] standing full-body near the edge of the frame, slightly to the left, in [real-world incomplete / empty / damaged environment]. The camera is positioned behind and slightly to the right of the person, capturing them from a three-quarter rear angle. The person stands calmly and thoughtfully, looking toward the space ahead. The environment is [describe the real space as it exists now: empty, unfinished, decayed, rigid, lifeless]. The atmosphere feels [emotional tone: quiet, dry, historical, minimal, raw]. Natural light illuminates the scene, creating realistic shadows and depth. Floating hand-drawn sketch lines appear over and within the environment, aligned precisely in perspective with the real space. These sketches represent [what is missing / what once existed / what could exist in the future]. The sketch lines are black, clean, and hand-drawn, resembling [architectural / interior / restoration / urban planning] concept sketches made with pencil or ink. The strokes are expressive, slightly imperfect, and organic — not rigid or mechanical. The sketched elements occupy the foreground and midground, appearing closer to the person than expected. Some sketch lines subtly overlap the person’s silhouette and the real surfaces, visually merging imagination with reality. The sketches float naturally within the scene, seamlessly blending with the environment and conveying the idea of [vision / restoration / transformation / potential] coming to life."
}
JSON
import { GptImage2Client } from "@runapi.ai/gpt-image-2";
const client = new GptImage2Client({
apiKey: process.env.RUNAPI_API_KEY,
});
const result = await client.textToImage.run({
"model": "gpt-image-2",
"prompt": "A [person type] standing full-body near the edge of the frame, slightly to the left, in [real-world incomplete / empty / damaged environment]. The camera is positioned behind and slightly to the right of the person, capturing them from a three-quarter rear angle. The person stands calmly and thoughtfully, looking toward the space ahead. The environment is [describe the real space as it exists now: empty, unfinished, decayed, rigid, lifeless]. The atmosphere feels [emotional tone: quiet, dry, historical, minimal, raw]. Natural light illuminates the scene, creating realistic shadows and depth. Floating hand-drawn sketch lines appear over and within the environment, aligned precisely in perspective with the real space. These sketches represent [what is missing / what once existed / what could exist in the future]. The sketch lines are black, clean, and hand-drawn, resembling [architectural / interior / restoration / urban planning] concept sketches made with pencil or ink. The strokes are expressive, slightly imperfect, and organic — not rigid or mechanical. The sketched elements occupy the foreground and midground, appearing closer to the person than expected. Some sketch lines subtly overlap the person’s silhouette and the real surfaces, visually merging imagination with reality. The sketches float naturally within the scene, seamlessly blending with the environment and conveying the idea of [vision / restoration / transformation / potential] coming to life."
});
console.log(result.id);
require "runapi/gpt_image_2"
client = RunApi::GptImage2::Client.new
result = client.text_to_image.run(
model: "gpt-image-2",
prompt: "A [person type] standing full-body near the edge of the frame, slightly to the left, in [real-world incomplete / empty / damaged environment]. The camera is positioned behind and slightly to the right of the person, capturing them from a three-quarter rear angle. The person stands calmly and thoughtfully, looking toward the space ahead. The environment is [describe the real space as it exists now: empty, unfinished, decayed, rigid, lifeless]. The atmosphere feels [emotional tone: quiet, dry, historical, minimal, raw]. Natural light illuminates the scene, creating realistic shadows and depth. Floating hand-drawn sketch lines appear over and within the environment, aligned precisely in perspective with the real space. These sketches represent [what is missing / what once existed / what could exist in the future]. The sketch lines are black, clean, and hand-drawn, resembling [architectural / interior / restoration / urban planning] concept sketches made with pencil or ink. The strokes are expressive, slightly imperfect, and organic — not rigid or mechanical. The sketched elements occupy the foreground and midground, appearing closer to the person than expected. Some sketch lines subtly overlap the person’s silhouette and the real surfaces, visually merging imagination with reality. The sketches float naturally within the scene, seamlessly blending with the environment and conveying the idea of [vision / restoration / transformation / potential] coming to life."
)
puts result.id
package main
import (
"context"
"fmt"
"log"
"net/http"
"os"
"strings"
)
func main() {
body := strings.NewReader("{\"model\":\"gpt-image-2\",\"prompt\":\"A [person type] standing full-body near the edge of the frame, slightly to the left, in [real-world incomplete / empty / damaged environment]. The camera is positioned behind and slightly to the right of the person, capturing them from a three-quarter rear angle. The person stands calmly and thoughtfully, looking toward the space ahead. The environment is [describe the real space as it exists now: empty, unfinished, decayed, rigid, lifeless]. The atmosphere feels [emotional tone: quiet, dry, historical, minimal, raw]. Natural light illuminates the scene, creating realistic shadows and depth. Floating hand-drawn sketch lines appear over and within the environment, aligned precisely in perspective with the real space. These sketches represent [what is missing / what once existed / what could exist in the future]. The sketch lines are black, clean, and hand-drawn, resembling [architectural / interior / restoration / urban planning] concept sketches made with pencil or ink. The strokes are expressive, slightly imperfect, and organic — not rigid or mechanical. The sketched elements occupy the foreground and midground, appearing closer to the person than expected. Some sketch lines subtly overlap the person’s silhouette and the real surfaces, visually merging imagination with reality. The sketches float naturally within the scene, seamlessly blending with the environment and conveying the idea of [vision / restoration / transformation / potential] coming to life.\"}")
req, err := http.NewRequestWithContext(context.Background(), http.MethodPost, "https://runapi.ai/api/v1/gpt_image_2/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)
}
gpt-image-2/api/v1/gpt_image_2/text_to_image获取 API Key
Low-angle fashion campaign photograph of a confident model holding a large [product name] very close to the camera, exaggerated perspective with the hand and product dominating the foreground, full-body pose visible in the background, wide stance, dynamic posture, clean pure white studio background, high-key lighting, sharp focus on product, slight depth of field on the model, bold colorful outfit with strong contrast tones, modern beauty advertising aesthetic, ultra-clean composition, commercial studio photography, glossy packaging detail visible, crisp shadows
curl -X POST https://runapi.ai/api/v1/gpt_image_2/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "gpt-image-2",
"prompt": "Low-angle fashion campaign photograph of a confident model holding a large [product name] very close to the camera, exaggerated perspective with the hand and product dominating the foreground, full-body pose visible in the background, wide stance, dynamic posture, clean pure white studio background, high-key lighting, sharp focus on product, slight depth of field on the model, bold colorful outfit with strong contrast tones, modern beauty advertising aesthetic, ultra-clean composition, commercial studio photography, glossy packaging detail visible, crisp shadows"
}
JSON
Create an infographic image of [LANDMARK], combining a real photograph of the landmark with blueprint-style technical annotations and diagrams overlaid on the image. Include the title “[LANDMARK]” in a hand-drawn box in the corner. Add white chalk-style sketches showing key structural data, important measurements, material quantities, internal diagrams, load-flow arrows, cross-sections, floor plans, and notable architectural or engineering features. Style: blueprint aesthetic with white line drawings on the photograph, technical/architectural annotation style, educational infographic feel, with the real environment visible behind the annotations.
curl -X POST https://runapi.ai/api/v1/gpt_image_2/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "gpt-image-2",
"prompt": "Create an infographic image of [LANDMARK], combining a real photograph of the landmark with blueprint-style technical annotations and diagrams overlaid on the image. Include the title “[LANDMARK]” in a hand-drawn box in the corner. Add white chalk-style sketches showing key structural data, important measurements, material quantities, internal diagrams, load-flow arrows, cross-sections, floor plans, and notable architectural or engineering features. Style: blueprint aesthetic with white line drawings on the photograph, technical/architectural annotation style, educational infographic feel, with the real environment visible behind the annotations."
}
JSON