How to write edit requests for Umber
Umber changes the pictures you give it from one sentence. The requests on this page are the ones behind the before-and-after pairs shown here, and the notes come from our own test runs.
Written from our own tests. Last checked October 9, 2026.
Say what to change, then what to keep
- Every request behind the pairs on this page names one change: “Switch her outfit to all black”, “Give the cat a red knitted beanie and a matching scarf”, “Make it a cozy candle-lit night”.
- Most then say what must stay: “keep her pose and the ginkgo street”, “keep him and the book”, “keep her face, pose and background”.
- One request, one kind of change: an outfit, a colour, the weather or the light.
What our tests showed
- Asked to change the colour of one coat and to keep everything else, it changed only the coat: the hoodie, trousers, leaves, bricks, face and pose stayed as they were.
- The same request written in English, Korean and Japanese gave the same result in our test, so you can write in your own language.
- With three pictures in one request it built one scene from them and followed the order in which the pictures were given.
- Asking for a different shape than the picture, a wide size for a tall photo, re-framed the scene instead of stretching it, so the composition changes.
- Exact likeness of a person is not guaranteed. Look at the face before you use a result.
Real results and the prompts behind them
Results made on Pickshot. The prompts are shown exactly as written, in English.
önce
Sonra
önce
Sonra
önce
Sonra
önce
Sonra
önce
Sonra
önce
SonraSettings of this model
- Gönderen
- Pickshot Select
- Tür
- AI görsel düzenleyici
- Oluşturma yöntemi
- Resim düzenleme
- Fiyat
- from 14 / image · Unlimited free use for members
Sorular
Can I write my edit request in Korean?
Yes. In our test, one request written in English, Korean and Japanese gave the same result. Your own words are sent as you wrote them.
Will the rest of the picture stay the same?
In our tests the parts we asked to keep stayed, but a change of size or shape re-frames the scene and a person’s exact likeness is not guaranteed. Check the result.
More prompting guides
- How to write prompts for GPT Image 2.6 FlareAI image model
- How to write prompts for GPT Image 2.6 SunburstAI image model
- How to write prompts for Nano Banana 2.1AI image model
- How to write prompts for MOSS ImageAI image model
- How to write prompts for Grok Imagine ProAI image model
- How to write prompts for Nano Banana ProAI image model
- How to write prompts for Nano Banana 2AI image model
- How to write prompts for GPT Image 2.5 FlareAI image model
- How to write prompts for IndigoAI image model
- How to write prompts for SaffronAI image model
- How to write prompts for CeladonAI image model
- How to write prompts for LapisAI image model
- How to write prompts for Kling Video 4.0AI video model
- How to write prompts for Seedance 2.5AI video model
- How to write prompts for Seedance 2.0 MiniAI video model
- How to write prompts for Kling V3AI video model
- How to write prompts for Kling O3 OmniAI video model
- How to write prompts for Veo 3.1AI video model
- How to write prompts for Veo 3.1 FastAI video model
- How to write prompts for SilkAI video model
- How to write prompts for LacquerAI video model
- How to write prompts for SatinAI video model
Pickshot Select models are chosen and offered by Pickshot. Provider notices are on the licenses page.
Bu sitedeki model, şirket ve ürün adları sahiplerinin ticari markalarıdır; Pickshot bunlarla bağlantılı değildir ve bunlar tarafından desteklenmez veya onaylanmaz.