The new Gemini 3 Nano Banana Pro model, integrated into Adobe Firefly, offers enhanced image generation capabilities, particularly for creating sharper 2K images, maintaining text clarity, and blending complex scenes with greater precision, enabling new creative workflows beyond Photoshop.
Mind Map
Click to expand
Click to explore the full interactive mind map • Zoom, pan, and navigate
The new Nano Banana Pro is now in
Photoshop, and the jumping quality is
huge. This new version creates sharper
images at 2K. It keeps text clean and
readable, and it blends complex scenes
with way more precision. You can use
this new model in Photoshop. Right now,
it works just like Gemini 2.5, but the
results look much better. Instead of
repeating last month's tutorial, but
with a new model, I want to show you a
different workflow. This time, we'll use
Nano Banana Pro inside of Adobe Firefly.
If you still want the Photoshop
breakdown, just follow last month's
tutorial, but use the new model. The
link to that video is down below. My
name is Jesus Ramirez. Let me show you
how it works. First, go to firefly.adobe.com.
firefly.adobe.com.
From this dropown, make sure image is
selected. Then go into the models
dropown, which includes all of Adobe's
partner models, including models not
inside of Photoshop, like Gemini 3 Nano
Banana Pro. But instead of doing this, I
recommend clicking on the more button
that brings you into this generative
workspace and it makes things a lot
easier to see. Here's a tip. You can
click on this link to learn more about
how prompting works in Firefly. To
start, select the model that is the new
Gemini 3 with Nano Banana Pro. Then you
can select an aspect ratio. Any aspect
ratio will do. And you can upload up to
six reference images. Let me show you
how that works. I'm going to click on
this icon to upload my first image. and
I will select your device. You can also
use images found in your Adobe cloud
storage which include other previously
generated images and your Creative Cloud
libraries. I'll go into your device and
I'll upload this portrait of myself.
Then I'll click on this icon once again
to upload my second reference image.
Once again I'll do it from my device and
I will upload this photo of me as a
baby. Then I'll add the prompt.
have the man hold the baby. Then I'll
click on generate. And in a few moments,
we'll get an image of me holding myself
as a baby. And there you go. The image
looks fantastic. I'm wearing the same
outfit on both images, my black sweater,
and this little blue overall I was
wearing when I was several months old.
To download the image, you can click on
this download button. And this is not
all. Firefly has a fantastic feature I'm
sure you're going to love. Let me show
you how it works. Go back to the
homepage at firefly.adobe.com
or you can click on this icon and from
here click on ID8. This will bring you
to the Firefly boards. From here, click
on create board. Then bring images from
your device by clicking on upload. And
from here, select the images you want to
upload. You can do more than one at a
time. I'm just going to do one for now
so I can show you how to come back to
this screen. If you want to add a second
image once you're in the board, you can
click on this icon to add content.
Select your device and this time I will
bring in this jacket and I will make
this a much much smaller image. These
images are way too large. Of course, I
could also zoom out if I wanted to, but
I think in this case I'm simply going to
scale these images down by dragging on
the corner handles just so that we can
see them on screen. And what I'm going
to do is take advantage of one of the
great new features in Firefly Boards,
which are the presets. When you click on
this presets button, you will see
several generative AI workflows. All you
need to do is select the one that you
want to use. For example, we're going to
try the virtual tryon. When you click on
that, you will see that we are going to
use Gemini 2.5, not the new one. I'm
going to show you how to change that in
a moment to generate a virtual tryon.
So, first click on subject, then hover
over the image that you want to apply
the clothing to. Notice that I have an
eyropper. When I click on that photo of
myself, it loads it into the subject
box. Then you can click on clothing and
click on the clothing. And you don't
have to do anything else. No prompt
needed. Simply click on generate. But I
want to take advantage of the new Gemini
3 with Nano Banana Pro. To do that, all
I need to do is click on this icon that
reads view prompt. And from here, you
can click on this dropown and choose the
new Gemini 3 with Nano Banana Pro.
Also make sure that the aspect ratio
matches your image. In this case, I need
to select portrait. Then you can click
generate. In a few moments, we'll
generate an image where I'm wearing the
brown leather jacket. You can click on
the X to collapse the prompt and other
settings. Everything is still generating
in the background. And to come back to
it, you can click on the virtual try
preset. And there it is. My generation
is complete. Now, what I'll do is just
pan over to the right so that I can get
some space. And I can drag that new
generation onto the board. And there I
am. And let's compare the jacket that
I'm wearing versus a jacket we use as a
reference. It's pretty similar. It looks
fantastic. And to save this image to the
device, enable the generated image and
click on the download button. Another
important thing I should mention is that
the output at the moment is 2K. If you
upload an image that is a lower
resolution, then Gemini 3 will upscale
it automatically. It's like a free
generative upscale. Now, I'll quickly go
through a few presets and what my
results were using the same portrait.
This is the electric party preset, and
somehow Google Nano Banana 3 knew
exactly the outfit that I wore last year
at my Christmas party. Then we have the
Cartoon effect, which does a fantastic [music]
[music]
job. I really like this image. Then we
have character and product, where I
uploaded this shoe and Gemini generated
that image of me jumping wearing those sneakers.
sneakers.
This is the Y2K preset. The image is not
bad, but I'm not so sure about the
clothes that I'm wearing. And this is
the cinema preset. I really like it. It
feels like I'm a New York mobster. What
do you think? And of course, there's
plenty more presets that I recommend you
try out and see if you can use them in
your projects. Also, make sure that you
look at how the prompts are written. It
may help you spark some ideas for other
types of images. And by the way, you may
have noticed that I haven't been posting
much lately on this YouTube channel, and
I do apologize for that, but my very
first child was just born, and as you
can imagine, she's keeping you real
busy. But don't worry, I'll continue to
post on a weekly basis again very soon.
And if you haven't already, check out my
Photoshop AI mastery course and my
selections and masking mastery course.
The link is below in the description.
Click on any text or timestamp to jump to that moment in the video
Share:
Most transcripts ready in under 5 seconds
One-Click Copy125+ LanguagesSearch ContentJump to Timestamps
Paste YouTube URL
Enter any YouTube video link to get the full transcript
Transcript Extraction Form
Most transcripts ready in under 5 seconds
Get Our Chrome Extension
Get transcripts instantly without leaving YouTube. Install our Chrome extension for one-click access to any video's transcript directly on the watch page.
