FLUX.3 for Image Editing
Edit any image with a text instruction using FLUX.3 Image by Black Forest Labs. Upload an image, describe the change, add optional reference images, and hit run.
FLUX.3
Image
Image Editig
3
ABOUT THE WORKFLOW
Edit an Image
Upload an image and describe the change you want. FLUX.3 Image reads the photo and applies your instruction. Add up to nine reference images to bring in a face, a product, a style, or a detail from another source. The edited image comes back in seconds.
Partner node. This workflow calls an external API, so each run uses credits from your API wallet. No API key needed. Floyo handles the connection.
Model
FLUX.3 Image by Black Forest Labs. Strong at precise local edits without changing the rest of the image, identity-preserving multi-reference composition, and accurate in-image text rendering.
HOW IT WORKS
Step 1. Upload your image
The image you want to edit. Any photo, render, or screenshot works.
Works great with: photos · portraits · product shots · designs
Step 2. Describe the change
Write what to change and what to keep. Be specific. "Change the jacket to red leather, keep the background the same" works better than "make it different."
Step 3. Add reference images (optional)
Upload up to nine reference images. Use them to carry a face, a product, a texture, or a style into the main image. The model pulls from these references while following your prompt.
Step 4. Hit run and download
FLUX.3 Image applies the edit and returns the result. Preview it in the workflow, then download.
Ready for: Photoshop · Figma · Canva · any editor
First time? Leave every setting as-is. The defaults (auto aspect ratio · 1K · JPEG) are the right starting point for almost everyone.
RECOMMENDED SETTINGS
Quick-start guide. Find the goal that matches yours and copy the settings.
Standard edit (most people) — Auto aspect ratio · 1K · JPEG. The right starting point for almost everyone.
Want a higher resolution output — Switch resolution to 2K or 4K. Higher resolution costs more per run. Use 4K only when the final image needs to hold up at large sizes.
Guide the edit with references — Add reference images to bring in a face, a product, or a style. Say in the prompt what each reference contributes.
Editing or adding text in the image — FLUX.3 Image renders text accurately. Spell out the exact words you want in the prompt.
Short on words for the prompt — Turn on prompt expansion. The model elaborates on your description to fill in detail.
The edit is changing too much — Be more specific about what to keep. "Change X, keep Y and Z the same" gives the model a clear boundary.
Need a different file type — Switch the output format from JPEG to match where the image is going.
Prompt: Describe the change and what to preserve. "Replace the background with a rooftop at sunset, keep the person and lighting the same" is clearer than "change the background." When you add references, say what each one contributes to the edit.
LEARN
📹 Videos
ComfyUI 101 Free Course ft. Sebastian Kamph
Floyo 101 for Team Collaboration
✨ Quick links
USE CASES
🎨 Style Transfers and Restyling
Upload a photo and a style reference, then describe the look you want. FLUX.3 Image applies the style while preserving the structure of the original.
🛍️ Product and E-commerce Shots
Swap backgrounds, change materials, or place a product into a new scene. Use a reference image to bring in the exact product from another angle.
🧑 Portrait and Identity Edits
Carry a face from a reference into a new composition. The model preserves identity across references, so the person looks like themselves in the result.
🔤 Text and Typography in Images
Add or change legible text in an image. FLUX.3 Image renders type accurately, which sets it apart from most image models.
🖼️ Concept Art and Moodboarding
Combine multiple references into one edited frame. Feed in a lighting reference, a texture reference, and an environment photo, then describe how they fit together.
WHAT WORKS BEST / WHAT TO AVOID
✅ Works great
Clear, specific edit instructions
Single, well-lit source images
Reference images for faces, products, or styles
Adding or changing readable text
⚠️ May produce softer results
Vague instructions like "make it better"
Too many conflicting references at once
Heavy bokeh or shallow depth of field in the source
Extremely dark or noisy source images
FAQ
What is FLUX.3 Image and who made it?
FLUX.3 Image is an image model made by Black Forest Labs, the team behind Stable Diffusion and the FLUX series. It was released on October 1, 2026. It supports text-to-image generation, image editing, multi-reference composition, bounding-box placement, and in-image text rendering, with output up to 4K resolution.
How does multi-reference editing work in FLUX.3 Image?
You upload the image you want to edit plus up to nine reference images. In your prompt, you describe what to change and what each reference contributes. The model pulls subjects, styles, textures, or details from the references and applies them to the main image while following your text instruction. This is useful for carrying a specific face, product, or visual style into a new scene.
Does FLUX.3 Image render text accurately?
Yes. Accurate typography is one of its strengths. You can add, change, or place legible text in the image by spelling out the exact words in your prompt. This makes it a strong choice for signs, labels, titles, and any edit where readable text matters.
What is the difference between FLUX.3 Image Edit and FLUX.3 text-to-image?
This workflow is image-to-image editing: it starts from your uploaded photo and changes it based on your prompt. A text-to-image workflow creates a new image from a text description alone. Use this workflow to modify an existing image, and text-to-image to generate one from scratch.
Can I use FLUX.3 Image outputs commercially?
FLUX.3 Image is a proprietary model by Black Forest Labs. It is API-only, with commercial weights available on request. Commercial use is generally supported, but review Black Forest Labs' current terms to confirm the rights for your specific use case.
What resolution should I use for FLUX.3 Image edits?
1K is the default and works well for previews, concept work, and web use. Step up to 2K or 4K when the final image needs to hold detail at large print sizes or high-density displays. Higher resolution costs more per run.
How to run FLUX.3 Image Edit online?
You can run FLUX.3 Image Edit online through Floyo. No installation, no setup, no API key to wire up. Open the workflow in your browser, upload your inputs, and hit run. Free to try.
WHY FLOYO?
Floyo is the only platform with team collaboration for ComfyUI in the browser. You run workflows with no install. You share run history, assets, and models across your team. You pay only when you generate. Floyo supports open-source and closed-source models.
A designer runs an edit and likes the result. A teammate opens that exact run from shared history and keeps going. No file handoffs. No version confusion.
For studios and enterprise teams, Floyo adds private workspaces, pooled resources, and a team usage dashboard. Other ComfyUI cloud tools run for one person at a time. Floyo runs for the whole team, with transparent per-generation costs.
Ready to try it?
Upload an image, describe the change, and run it. The settings are already set.
Questions? Watch the free course or check the FAQ above.
Read more
