P: Text and symbol generation in images

[Angelic_child5CF3]

I am trying to generate a logo with a desired text. It is not accepting it.

[Angelic_child5CF3]

Text and symbol generation in images is not supported yet in the Text to Image module. The quality of our models will improve with time, and generated content will better respect the prompt. If you are trying to create just text, please try the Text Effects module. (Merging all similar threads here so we can track the number of reports for this)

[Kartika Rawat]

Hi @otto_5475!

Sorry to hear that. I'm merging your thread here since it’s part of a similar discussion. Please see the correct answer above.

Let us know if this helps.

Thanks,

^KR

[sagoad73]

I attempted to generate an image for a personal article I am writing on X. I was excited to see the Firefly feature and burned one of my credits to generate an image. I have had an adobe account with monthly billing of $21.73 since October 27, 2022 and of course this is first time using the 25/25 of credits I had (and they don't roll over). I gave a very specific prompt, and Firefly was unable to generate an image with the correct spelling of words from the prompt.

My Prompt was - Create Image, with the following words; "Democrat Party", "Republican Party", "Reform Party", "Libertarian Party", "Green Party", "America Party", "Constitution Party", "Alliance Party", "Forward Party", "No Labels Party" in random locations and a black background

Please see the attached image of the junk I was provided.

[DeanUtian]

Hi @sagoad73 

Firefly has never been great at inserting text into an image. It is getting better but is still has problems. If you ask for a few words in an image, it may get it right in some generations. If you ask for a large number of words, it is unlikley that all the words will appear correctly. Maybe in future versions of Firefly, it will manage text better. For now, inserting text in images is not reliable.

[MaryAnn_Bradley3394]

•  

[Kartika Rawat]

Hi MaryAnn_Bradley3394!

Thanks for writing in. Currently, Firefly has limitations in creating text on generated images. I'm merging your thread here since it’s part of a similar discussion. Please see the correct answer above.

Let us know if this helps.

^KR

[ChrisWithAC]

When inputing a sign with a name the words aren't spelled right.

[Oh.N8]

Hey @ChrisWithAC 

Adobe Firefly does struggle with text 100%. I recommend generating your image and then taking the image to Adobe Express you have many more options and much more freedom and flexiblity in Adobe Express.

Cheers
Nate

[kenneth_1110]

You guys set the default fore color to Black on dark settings? Seriously?

[Oh.N8]

Hey @kenneth_1110 

This is frustrating for sure. In cases like this, I find using Adobe Express works far better. I have control over colour, text size, positioning, and many other features like being able to go back and change the text later.

Cheers

Nate

[Virtuoso]

How do I fix the problem of the app generating misspelled words? 

“A lined notebook page rests on a wooden desk as the camera slowly pans upward to reveal the word VIRTUOSO bursting out of the page in bold, 3D anamorphic style. Dramatic lighting highlights the sharp black shadows as the letters hover above the paper like a sculpture. A glowing flare pulses through each letter as the word slowly rotates in space, then slams down to cast a powerful shadow — ending with a flash and the tagline: ‘Rise Above. Create Beyond. VIRTUOSO.’”

:one_o_clock: Style: Cinematic, clean, slow zoom & rotation, realistic shadows

:artist_palette: Color mood: Warm tones with high contrast

:musical_notes: Sound: Deep whoosh + light bass hit for dramatic impact at end

[Monika Gause]

---

@Virtuoso  schrieb:

How do I fix the problem of the app generating misspelled words? 

“A lined notebook page rests on a wooden desk as the camera slowly pans upward to reveal the word VIRTUOSO bursting out of the page in bold, 3D anamorphic style. Dramatic lighting highlights the sharp black shadows as the letters hover above the paper like a sculpture. A glowing flare pulses through each letter as the word slowly rotates in space, then slams down to cast a powerful shadow — ending with a flash and the tagline: ‘Rise Above. Create Beyond. VIRTUOSO.’”

:one_o_clock: Style: Cinematic, clean, slow zoom & rotation, realistic shadows

:artist_palette: Color mood: Warm tones with high contrast

:musical_notes: Sound: Deep whoosh + light bass hit for dramatic impact at end

---

You edit the image in an image editor afterwards. Firefly cannot spell.

[Joseph37957209wq0w]

While using Firefly today (August 6) I prompted the platform to create a chart (assuming it would appear in English) but it appeared in a foreign language--- possibly Greek

[droopydog500]

Hello @Joseph37957209wq0w,

Thank you for your message. 

While it has gotten better, Firefly (and most other AI image generators) is generally not good at putting exact text from a prompt into an image. Sometimes it is perfect, but usually, it does not get it right.  The best solution is to use Adobe Express or Photoshop to add text in.  The more complicated the angle or perspective of the text, the more likely you will need Photoshop to get what you want.

Thanks,
    droopy

[angelac71422527]

I am making videos with minimum writing in English. Like Caption. My video comes back with chinese writing all over it. This has happen several times. Yet, the 100 credit is taken. It needs to writing in English and spell correctly. This product is not ready.

[Oh.N8]

Hey @angelac71422527 

I cases like this. Consider using Adobe Express to add the text.
1) Generate your video w/o the desided text
2) Download the video (maybe w sound effects)
3) Upload the video to Adobe Express and add your Text

Benefits
1) you can move the text
2) change the font, colour, and size
3) able to animate the text

I created a short video on how to:
Adding text to video in Adobe Express
Hope this helps.

Cheers

Nate