Write your own prompt with GPT Image 2.5Open the Image generator: all models, shapes, up to 4 images →

AIモデル · このページで作成

GPT Image 1.5

8クレジットから · images with readable textに最適

Create images from a text prompt with OpenAI's GPT Image 1.5, or upload a photo and describe the change. It is especially good at following detailed prompts and writing legible text in images.

有料プランとクレジットパック

約10〜30秒

1枚8クレジット

画像の内容を入力

参考画像を追加 (任意)

AIがスタイルや構図の参考にします

アップロード

By uploading, you confirm you have the right to use this photo (see Acceptable Use).

アスペクト比

アイデア — クリックで試す

1枚8クレジット · クレジットパックが必要（$1.99から） · 無料の選択肢：AI Image Generator
モデル：GPT Image 1.5 · 通常10〜30秒

Eidora's GPT Image 1.5 page runs OpenAI's image model of that name through fal.ai: type a prompt to create an image, usually in 10 to 30 seconds, or upload a photo and describe the change, usually in 20 to 60 seconds. It follows detailed prompts closely and writes readable text into images such as signs, labels and posters. It needs a paid plan or a credit pack; each image uses 8 credits.

プロンプトと結果

プロンプトから画像へ

“A cozy independent bookshop on a rainy evening, warm window light spilling onto wet cobblestones, a hand-painted sign above the door that reads "PAGE & PINE", photorealistic”

プロンプト

入力

GPT Image 1.5 result: a rainy-evening bookshop with a sign reading PAGE & PINE

GPT Image 1.5 result in 16:9: a harbor city with a banner reading WELCOME TO NOVA BAY

サンプル結果

アフター

モデルの位置づけ

About this model

GPT Image 1.5 is OpenAI's image generation and editing model. It follows long, specific prompts closely and is one of the better models at putting correct, readable text into an image, such as signs, labels and posters. On this page you can type a prompt to create a new image, or upload a photo and say what to change. Eidora runs the real GPT Image 1.5 through fal.ai at medium quality; square images come out at 1024×1024 and wide or tall ones at 1536×1024 or 1024×1536.

Follows long, detailed prompts
Legible text in images (signs, labels, posters)
Edits uploaded photos from a prompt
Square, wide and tall outputs

おすすめ： Posters, social graphics, product mockups and any image that needs readable words in it.

Nano Banana 2 Seedream 5.0 Gempix 2 AI Image Generator

使い方の例

あなたが作れるもの

Unique Blog Visuals

Content Creators can generate unique header images and illustrations for their articles, avoiding generic stock photos. Simply describe the desired scene, or upload a rough sketch to refine it into a polished visual.

Marketing Visuals on Demand

Small Business Owners can quickly produce eye-catching graphics for social media campaigns or advertisements. Type a concept for a new ad, or upload an existing product image to give it a fresh look.

Concept Art Iteration

Game Developers can rapidly visualize character designs, environmental elements, or prop ideas. Provide a text description of your concept, or upload an initial sketch to iterate and refine its appearance.

Eidoraを選ぶ理由

作り方が違う、だから仕上がりがいい

Text to Image Creation

Generate original visuals from just a descriptive text prompt, perfect for new concepts and ideas.

Image-to-Image Transformation

Upload an existing image and use text prompts to alter its style, elements, or composition with precision.

Rapid Visual Prototyping

Quickly experiment with different visual ideas and styles for marketing campaigns or design projects, accelerating your workflow.

使い方

3ステップ。約1分。

Provide Input
Start by either typing a detailed text prompt describing your desired image or uploading an existing image.
Generate
Press Generate. Images from a prompt usually take 10 to 30 seconds; edits of an uploaded photo usually take 20 to 60 seconds.
Generate & Download
Check the result and download the image. Not quite right? Run it again.

GPT Image 1.5を今すぐ試す

✦ 今すぐ始める

よくある質問

知りたいことはここにあります。答えが見つかりませんか？

まだ質問がありますか？

サポートチームがお手伝いします。

サポートに連絡

GPT Image 1.5 is OpenAI's image model for creating and editing images from text. It is known for following detailed prompts and rendering readable text inside images.

Yes. Your prompt is sent to OpenAI's GPT Image 1.5 through fal.ai, a model hosting provider, at medium quality. Eidora is not affiliated with OpenAI.

This model needs a paid plan or a credit pack: Pro is $9.9/month for 300 credits, or buy a one-time pack (the $4.99 Starter pack has 100 credits), and each image uses 8 credits. A free account's credits work on the 4-credit tools.

Yes. Upload an image and describe the change, for example "replace the background with a beach at sunset". The upload goes to GPT Image 1.5's edit mode.

Square images are 1024×1024; wide and tall images are 1536×1024 or 1024×1536. Pick 1:1, 16:9, 4:3 or 3:4 in the studio before you generate; the output follows that shape.

Images from a prompt usually take 10 to 30 seconds; edits of an uploaded photo usually take 20 to 60 seconds.

It depends on applicable law and the model provider's current terms. An Eidora plan changes generation limits and history retention; it does not grant extra intellectual-property rights.

Your uploads, prompts and results are saved privately to your history so you can view and download them later, and only you can open them. To create a result, your input is sent to the AI model provider that runs the generation. We do not sell your content or use it to train AI models.