
Petunjuk terperinci untuk manga berbahasa Mandarin multibahasa.
Sebuah perintah yang sangat kompleks untuk menghasilkan manga satu halaman penuh yang menampilkan karakter tertentu, tata letak vertikal, dan rendering teks multibahasa yang tepat dalam bahasa Mandarin dan Inggris.
Ini adalah contoh kasus GPT Image 2 untuk Anime & Game . Gunakan contoh siap salin di bawah ini untuk menghasilkan visual serupa, dan tinjau atribusi Awesome GPT Image 2 Prompts serta hak penggunaan komersial sebelum digunakan kembali.
Free 1K preview
Generate one preview image instantly, no sign-up required.
Free text preview doesn’t preserve reference-image consistency.
Mengingatkan
Prompt siap salin
Generate a full-color Chinese-style comic strip. The protagonist is {argument name="character" default="OpenAI researcher, Chen Boyuan"} (first panel), who is dedicated to improving the text rendering capabilities of the ChatGPT Image 2 model in the upcoming release. (There's bubble tea in the background, and a banana stuck to the wall with a single strip of tape). When he tries to generate a hand-drawn, multilingual infographic poster about his hometown of {argument name="location" default="Wuxi"} on the computer screen, the model demonstrates its ability to render very small Chinese characters. His efforts pay off, and the team is amazed by the model's excellent multilingual text performance, seeing the various languages it can write. While resting and holding his phone in one hand, he receives a translated text message from Sam Altman (see the second image for his avatar), asking him to check the multilingual text rendered in a newly generated image congratulating the team, as Sam only understands English. However, add a humorous element: in the final panel of the comic, let Boyuan (in a typical comic style) be furious to see the phrase “稳稳地接住你” (steadily catch you) prominently displayed in the center of the image generated by Sam, while the rest of the image is rendered perfectly. This phrase has become a meme on the Chinese internet, seen as an unnatural but amusing phrase that GPT tends to use. Boyuan should shout angrily: “Oh my god! It learned ‘接住’ again!” (Next to him are smaller avatars of his teammates, sweating and saying: “We’re working on fixing it!”). At the very bottom of the comic, add a tiny Chinese footnote: “Note: The entire comic, including this footnote and the pictures within pictures, was generated in one go by GPT Image 2, without editing or multi-step processing.”
Additional Notes: Use a vertical image layout of 1440x2560. The first row shows the researcher working hard; the second row shows his multilingual achievements on the topic of {argument name="location" default="Wuxi"}; the third row shows the team's excitement; the fourth row is divided into two parts, the left side showing him resting and receiving a message on his phone, and the right side showing Sam's text message; the fifth row shows Sam's photo and Chen Boyuan's reaction. Do not use narration except for the first row. Avoid showing a map of China. All characters should be in a comic style. The banana background only appears in the first panel, and the tape should be a single strip, not a cross. The banana and tape decorations should be Easter eggs, small and inconspicuous. The OpenAI logo should only appear on Chen Boyuan's clothes, and nowhere else. There should be no mugs in the scene, as there is already bubble tea. Sam should only appear in the text message panel. The entire comic should be presented as a professional photo of a physical page from a comic book. In the lower right corner of the poster, add a small line of text: “Even the smallest Chinese characters are clearly readable:”, followed by an even smaller Chinese paragraph starting with “(This is a super small font test)Wuxi is the author's hometown, so I made this poster, and the Chinese is finally fixed. I haven't been home for years, and I really want to eat hairy crabs!” (super small font).Variabel perintah
Placeholder argumen yang dapat diedit ditemukan dalam prompt, beserta nilai defaultnya.
Best for
- - Anime & Game visual exploration
- - Image generation and reference-image edits
- - Reusable briefs that keep source attribution visible
Change these parts
- - Subject, product, character, or scene
- - Aspect ratio, camera, lighting, and background
- - Brand, text, color, and output constraints
Recommended model and settings
- - Model: gpt-image-2
- - Input mode: Gambar ke Gambar
- - Aspect ratio: source
- - Commercial status: review original source
How to use this prompt
- 1. Copy the prompt and preserve its structure for the first test.
- 2. Replace the subject, context, and publishing channel.
- 3. Change one camera, lighting, or style variable per iteration.
- 4. Inspect the output, source, text, and rights before reuse.
Limitations, source, and reuse cautions
- - Generated output is an editable draft, not factual, legal, or rights evidence.
- - Review the linked source, people, brands, logos, text, and third-party media before commercial use.
Lebih banyak kasus dalam kategori ini
Diprioritaskan berdasarkan kategori, kompatibilitas mode input, kualitas, dan risiko yang lebih rendah.
Catatan penggunaan kembali dan sumber
Gunakan perintah ini dengan aman setelah melihat pratinjau kasus.
- 1.Salin perintah tersebut atau buka langsung di Dovoo dengan tombol pembuatan.
- 2.Sesuaikan variabel, rasio aspek, dan gambar referensi untuk kebutuhan Anda sendiri.
- 3.Sebelum mempublikasikan atau menggunakan untuk tujuan berbayar, verifikasi hak sumber, persyaratan atribusi, dan risiko merek atau citra.





