How do I edit a photo instead of starting from text?

Select the model, upload a photo and explain both the intended change and the details to keep. Set the output options and generate. Text-only requests do not need an image. Compare the result with the source, especially faces, text and product outlines.

How many references and which upload formats are supported?

You can provide up to 10 JPG, PNG or WEBP files, each up to 10 MB. Describe the purpose of each reference; more images do not guarantee that every detail will remain unchanged.

Can I choose 4K, PNG, JPEG and an aspect ratio?

Choose 1K, 2K or 4K and PNG or JPEG. Available ratios are auto, 1:1, 4:3, 3:4, 16:9, 9:16, 3:2 and 2:3. Auto resolves to square for text-only requests and passes the automatic setting to the model for edits. Each request produces one image.

Is FLUX.3 Klein free, and how much does a generation cost?

You need an account and credits on GPT Image 2.5. Check your balance and the estimate before submitting: resolution and reference images affect the cost. Unlimited free use and a fixed completion time are not promised.

Is this FLUX.2 or the FLUX 3 video model?

This page uses FLUX.3 Klein for still images and editing. FLUX.2 has a separate page and FLUX 3 video is a different workflow. Other family features, including video and box-based editing, are not necessarily available here.

Will it preserve faces, logos and exact text?

Instructions and references communicate what to retain, but the result may differ. Review identity, anatomy, logos, spelling and important dimensions. Finish exact brand artwork or lettering in an image editor.

How do I download an image and use it commercially?

Once ready, inspect the image and use its download control. PNG and JPEG work in common editors. Commercial use depends on rights to your inputs and applicable model and service terms; third-party faces, art and trademarks are not automatically cleared.

FLUX.3 Klein Image Generator & Editor

FLUX.3 Klein Image Generator

Turn a written brief into an image, or upload photos and describe what to change with FLUX.3 Klein. Choose the composition, output size and format in one workspace; sign in and check the displayed credit cost before creating.

What is FLUX.3 Klein?

FLUX.3 Klein is a Black Forest Labs image model for text-to-image generation and reference-based editing. On GPT Image 2.5, start from a description or up to 10 images and request one PNG or JPEG at 1K, 2K or 4K. Use it for product scenes, visual concepts and photo variations, then review the output before sharing. This page serves the Klein image model, not FLUX 3 video or audio generation.

From your idea to an image you can use

Generate from a focused description

Start with the subject and the moment you want to show. Add the setting, lighting and camera angle, then specify the visual style. For a product, include its material and leave room around it. Review the first composition before changing the brief for another attempt.

Edit a photo with a clear instruction

Choose a clear source photo and describe the edit alongside the elements to retain. For example, ask for a new setting while keeping the product’s shape and viewpoint. Check the resulting edges, faces, labels and proportions against the original because other details may also change.

Combine up to 10 reference images

Add up to 10 JPG, PNG or WEBP images, each no larger than 10 MB. Tell the model which reference supplies the subject, environment or colour palette. A smaller, consistent set can be easier to interpret; the upload limit does not promise exact preservation.

Choose a composition for the destination

Pick 1:1 for a square, 4:3 or 3:2 for landscape, 3:4 or 2:3 for portrait, and 16:9 or 9:16 for wider or vertical layouts. Auto uses 1:1 for text-only requests and follows the references for edits. If you plan to add a headline, describe where to leave space.

Select 1K, 2K or 4K and a file format

Select 1K, 2K or 4K and save as PNG or JPEG. Each request creates one image, with pixel dimensions determined by resolution and ratio. A larger output is useful for larger placements, but inspect it at full size: higher resolution cannot fix misspelt text or distorted details.

Check lettering and fine detail

Keep requested text short and separate it clearly from the rest of the prompt. Inspect spelling, hands, reflections and repeated details in the finished image. Add critical lettering in a design editor when a poster or product label needs exact typography.

Build product and campaign concepts

Explore a product on a tabletop, a seasonal setting or a palette for a campaign. Change one prominent element at a time and compare the product outline, packaging and logos with the reference. A convincing image alone does not establish an exact product match or rights to a brand.

Review, download and use the result

Before submitting, sign in and review the displayed estimate and balance. Inspect the finished image, download it from the result and open the saved file before sharing or editing. Confirm rights to the source material and the applicable model and service terms before publication.

FLUX.3 Klein questions

FLUX.3 Klein Image Generator FAQ

Use FLUX.3 Klein to create an image from a written brief or edit a photo using references. Try a product scene, composition study or background change. This page provides image generation and editing, not video, sound or robot actions.

User reviews

2,000+ Happy Users

"I start a product concept with one clear reference and compare the bottle outline before moving on. Keeping the brief focused makes it easier for me to judge the background and lighting."

Maya Chen

Fictional user

"For a background change, I describe the new setting and the product details that should stay. I compare the outline and reflections with the reference before choosing a version."

Alex Morgan

Fictional user

"For packaging concepts, I treat the image as a composition draft. Exact labels and brand lettering go into my design file afterward, where I can check them carefully."

Noah Kim

Fictional user

"I start a product concept with one clear reference and compare the bottle outline before moving on. Keeping the brief focused makes it easier for me to judge the background and lighting."

Maya Chen

Fictional user

"For a background change, I describe the new setting and the product details that should stay. I compare the outline and reflections with the reference before choosing a version."

Alex Morgan

Fictional user

"For packaging concepts, I treat the image as a composition draft. Exact labels and brand lettering go into my design file afterward, where I can check them carefully."

Noah Kim

Fictional user

"I start a product concept with one clear reference and compare the bottle outline before moving on. Keeping the brief focused makes it easier for me to judge the background and lighting."

Maya Chen

Fictional user

"For a background change, I describe the new setting and the product details that should stay. I compare the outline and reflections with the reference before choosing a version."

Alex Morgan

Fictional user

"For packaging concepts, I treat the image as a composition draft. Exact labels and brand lettering go into my design file afterward, where I can check them carefully."

Noah Kim

Fictional user

"I start a product concept with one clear reference and compare the bottle outline before moving on. Keeping the brief focused makes it easier for me to judge the background and lighting."

Maya Chen

Fictional user

"For a background change, I describe the new setting and the product details that should stay. I compare the outline and reflections with the reference before choosing a version."

Alex Morgan

Fictional user

"For packaging concepts, I treat the image as a composition draft. Exact labels and brand lettering go into my design file afterward, where I can check them carefully."

Noah Kim

Fictional user

"For portrait variations, I describe which features should stay and review the face against the source. I would still check the hair and edges before putting an image into a client draft."

Daniel Reed

Fictional user

"I use a small set of references to communicate a colour direction. Giving each image a clear role helps me avoid mixing up the subject, materials and background."

Emma Wilson

Fictional user

"Before exporting a visual, I consider where it will be used and choose the resolution and PNG or JPEG format. I inspect the saved file at full size before handing it off."

Sara Ali

Fictional user

"For portrait variations, I describe which features should stay and review the face against the source. I would still check the hair and edges before putting an image into a client draft."

Daniel Reed

Fictional user

"I use a small set of references to communicate a colour direction. Giving each image a clear role helps me avoid mixing up the subject, materials and background."

Emma Wilson

Fictional user

"Before exporting a visual, I consider where it will be used and choose the resolution and PNG or JPEG format. I inspect the saved file at full size before handing it off."

Sara Ali

Fictional user

"For portrait variations, I describe which features should stay and review the face against the source. I would still check the hair and edges before putting an image into a client draft."

Daniel Reed

Fictional user

"I use a small set of references to communicate a colour direction. Giving each image a clear role helps me avoid mixing up the subject, materials and background."

Emma Wilson

Fictional user

"Before exporting a visual, I consider where it will be used and choose the resolution and PNG or JPEG format. I inspect the saved file at full size before handing it off."

Sara Ali

Fictional user

"For portrait variations, I describe which features should stay and review the face against the source. I would still check the hair and edges before putting an image into a client draft."

Daniel Reed

Fictional user

"I use a small set of references to communicate a colour direction. Giving each image a clear role helps me avoid mixing up the subject, materials and background."

Emma Wilson

Fictional user

"Before exporting a visual, I consider where it will be used and choose the resolution and PNG or JPEG format. I inspect the saved file at full size before handing it off."

Sara Ali

Fictional user

"I use a vertical composition to plan space for a campaign headline. I prefer to add the final text in my editor so I can control spelling and layout."

Sofia Martin

Fictional user

"When exploring portrait lighting, I change one main instruction at a time. I keep the original nearby to check facial proportions instead of judging only the overall atmosphere."

Luca Rossi

Fictional user

"I use a vertical composition to plan space for a campaign headline. I prefer to add the final text in my editor so I can control spelling and layout."

Sofia Martin

Fictional user

"When exploring portrait lighting, I change one main instruction at a time. I keep the original nearby to check facial proportions instead of judging only the overall atmosphere."

Luca Rossi

Fictional user

"I use a vertical composition to plan space for a campaign headline. I prefer to add the final text in my editor so I can control spelling and layout."

Sofia Martin

Fictional user

"When exploring portrait lighting, I change one main instruction at a time. I keep the original nearby to check facial proportions instead of judging only the overall atmosphere."

Luca Rossi

Fictional user

"I use a vertical composition to plan space for a campaign headline. I prefer to add the final text in my editor so I can control spelling and layout."

Sofia Martin

Fictional user

"When exploring portrait lighting, I change one main instruction at a time. I keep the original nearby to check facial proportions instead of judging only the overall atmosphere."

Luca Rossi

Fictional user

Create your next image with FLUX.3 Klein

Start with a short brief or a clear reference photo. Select FLUX.3 Klein, review the settings and credit cost, then generate and check your image.

Create with FLUX.3 Klein

+1k