# FLUX 3 Image > Create and edit FLUX 3 Image photos at native 2K and 4K. Keep quoted text readable, use up to 10 photo references, and keep every image private on MixVio. - [Canonical FLUX 3 Image page](https://mixvio.ai/models/flux-3-image) - [Official model source](https://bfl.ai/models/flux-3-image) ## Route summary - **Provider:** Black Forest Labs - **Media:** image - **Inputs:** Text · Up to 10 photos - **Output:** 1K–4K PNG - **Credits:** 3–43 credits per output - **Availability:** Available ## Capabilities - **Prompt-led composition:** Name each object, where it sits, and the light. MixVio sends that prompt on text-to-image, and the photo follows the layout you wrote. - **Native 2K and 4K:** Choose 2K or 4K when the photo has to come out at that size. MixVio sends that resolution, so texture, faces, and color render at the size you picked. - **Edit and keep the rest:** Name the change and what must stay: the glaze, garment, or object, plus identity, pose, and background. Attach the photo on image edit, and MixVio sends that prompt. - **Up to 10 photo references:** On edit, attach 1 to 10 JPEG, PNG, or WebP photos and ask for one composed image. The first upload is image 1 and sets Auto. Later uploads are image 2 onward. The count does not change the credit quote. ## How to use 1. **Start from text or photos:** Open FLUX 3 Image with a text prompt, or attach one to ten owned photos for image edit. Prefill from a Key Feature or Example if you want. Nothing runs until you generate. Generate stays disabled on edit until a photo is attached. 2. **Write the scene, or the one change:** For a new photo, name the subject, where it sits, and the light. For an edit, name the change and what must stay. Refer to uploads as image 1 and image 2 when you need a role. 3. **Choose ratio and resolution, then generate:** Pick Auto or a fixed ratio, then 768sq, 1K, 2K, or 4K. Confirm the credit estimate and generate. Review the photo, then download or continue on image edit. MixVio does not expose a bounding-box drawer. ## Pricing Estimates below use the default 4-credit 1K image. The range is 3–43 credits; generate and edit share that MixVio rate. Confirm the exact reservation before you generate. - [MixVio pricing](https://mixvio.ai/pricing) ## FAQ ### What is FLUX 3 Image on MixVio? FLUX 3 Image is the Black Forest Labs image family for generating and editing photos. It is separate from FLUX 3 video. Text-to-image takes a prompt. Image edit takes a prompt plus 1 to 10 owned photos. [FLUX 3 Image](https://bfl.ai/models/flux-3-image) ### Is this the same as FLUX 3 video or FLUX.2 [max]? No. [FLUX 3](https://mixvio.ai/models/flux-3) on MixVio is video only, with durations and per-second credits. FLUX 3 Image is the photo family on this page. FLUX.2 [max] is a different image route and is not this model. ### Which resolutions and aspect ratios are supported? Both routes offer 768sq, 1K, 2K, and 4K. 768sq means about 0.6 megapixels: 768×768 at 1:1, with other ratios keeping a similar pixel count. The default is 1K. Ratios are Auto, 21:9, 2:1, 16:9, 3:2, 7:5, 4:3, 5:4, 1:1, 4:5, 3:4, 5:7, 2:3, 9:16, and 1:2. Auto is the default. On edit, Auto follows the first photo. 512sq, 1.5K, and 9:21 are not on this MixVio route. ### How many photo references can I attach? Text-to-image takes no photos. Image edit takes 1 to 10 JPEG, PNG, or WebP photos. Each photo needs at least 256 pixels on a side and at most 4,000,000 pixels. Order is image 1 through image 10. Adding more photos does not change the credit quote. ### How many credits does FLUX 3 Image use? FLUX 3 Image is available on the Free plan when your balance covers the quote. Generate and edit share one table: 3 credits at 768sq, 4 at 1K, 7 at 2K, and 43 at 4K. The generator shows the exact reservation before you submit. Failed runs cost no credits. ### Is FLUX 3 Image free? It is available on the Free plan, including 4K, when your balance covers the selected quote. Generation is not zero-credit. Free delivery limits such as a watermark may still apply. Failed runs cost no credits. ### How does FLUX 3 Image compare with GPT Image 2.5, GPT Image 2, and Nano Banana 2? Stay on FLUX 3 Image for native 2K and 4K photos, readable quoted text, and up to 10 photo references. Stay on GPT Image 2.5 for Flare or Sunburst and up to 16 references. Stay on GPT Image 2 for the High-only path. Prefer Nano Banana 2 for a lower-credit balanced loop. Specs in the comparison table are the live MixVio routes. ### Can I draw boxes to place objects? Not as a MixVio control. Official bounding-box layout is prompt text, not a canvas on this page. You can paste placement text into the prompt. MixVio does not add a box drawer, grounding toggle, prompt expansion switch, seed, or output batch. ### How long does a 4K image take? MixVio does not publish a fixed generation time. 4K can take longer than 1K, including a few minutes on a busy queue. The credit quote is shown before you generate. Review the photo when it lands in your private workspace. ### Can I use FLUX 3 Image photos commercially? Paid-plan outputs may be used commercially, subject to the Terms of Service and current Black Forest Labs terms. You must have rights to every prompt, reference, face, and brand. Free-plan outputs are for evaluation. MixVio does not guarantee exclusivity or trademark clearance. ### Are my prompts and outputs private on MixVio? Yes. Prompts are routed server-side, and final media is archived privately to your workspace. Keep private prompts and asset IDs out of shared links.