Flux Kontext provides Pro and Max text-generation and single-image-editing tasks. Describe a scene, subject and material for a new image, or provide one source and identify the wording, setting or visual style to change. The reference establishes the person, object and composition to retain; the prompt describes how the result should differ. Choose one of seven aspect ratios and PNG or JPG output, then compare the selected variant’s complete per-generation estimate.
Flux Kontext is developed by Black Forest Labs. Vidgo provides access to the model. Model names and trademarks belong to their respective owners.Choose Text to Image to create the complete composition from a prompt. Choose Image Editing when an existing photograph supplies the identity, object or scene to preserve. Both Pro and Max offer these two tasks with the same documented ratio and format controls; select a variant, test the intended change and review its current price.
Generate images from text prompts with Flux Kontext Pro Text to Image, choosing from seven aspect ratios and PNG or JPG output.
Edit one source image with text instructions using Flux Kontext Pro Edit, choosing from seven aspect ratios and PNG or JPG output.
Generate images from text prompts with Flux Kontext Max Text to Image, choosing from seven aspect ratios and PNG or JPG output.
Edit one source image with text instructions using Flux Kontext Max Edit, choosing from seven aspect ratios and PNG or JPG output.
Text generation uses prompt and optional size and output_format. Editing adds image_urls containing exactly one public image address. Specify the letters, surface, person, environment or medium to change, and name the details that should remain consistent. A single source can support a local revision, a new setting or a full rendering-style change.
| Model / task | Input and workflow |
|---|---|
| Flux Kontext Pro Text to Image | Generate images from text prompts with Flux Kontext Pro Text to Image, choosing from seven aspect ratios and PNG or JPG output. |
| Flux Kontext Pro Edit | Edit one source image with text instructions using Flux Kontext Pro Edit, choosing from seven aspect ratios and PNG or JPG output. |
| Flux Kontext Max Text to Image | Generate images from text prompts with Flux Kontext Max Text to Image, choosing from seven aspect ratios and PNG or JPG output. |
| Flux Kontext Max Edit | Edit one source image with text instructions using Flux Kontext Max Edit, choosing from seven aspect ratios and PNG or JPG output. |
The existing Pro and Max records show a storm-chasing scene, a deep-sea view, a renamed boat, a cellist placed on a frozen lake and a photograph rendered as stained glass. Each request describes its own subject and target result. Inspect the outputs and references alongside the prompts when planning your own edit.
Write the sky, people, camera viewpoint and physical activity. The Pro storm record asks for a rotating supercell above two observers and a pickup truck, with wind bending grass and lifting dust. Inspect the generated weather, composition and subject relationships for a narrative concept.
Describe the viewing surface, light sources and reflected interior. The Max submersible record asks for an anglerfish outside a thick acrylic porthole, a bioluminescent lure and faint cabin reflections. Inspect the actual glass, fish structure and lighting against the brief.
Provide one source and identify the exact old and new words. The Pro boat edit changes MARISOL to ALBATROS while matching white hand-painted letters, brush texture and weathering. Compare the edited hull with the source for spelling and retained scene details.
Use the source to establish the musician, chair, instrument and pose, then describe the destination and light. The Max edit places the same cellist on a frozen lake at blue hour with a warm lantern. Inspect identity, playing posture, contact and the requested cold-weather details.
Specify the medium, colors and structural details to retain. The Max turf-farm edit turns houses, meadow, waterfall and sheep into colored glass separated by dark lead lines. Compare source and result for object positions, light transmission and material texture.
The Pro case supplies a fishing-boat photograph and asks to replace its painted name while retaining the hull, beach and surroundings. The Max case supplies a cellist portrait and asks for the same musician, chair, cello and playing pose on a frozen lake with twilight and lantern light. Read the complete prompts and compare each source with its corresponding output.
Replace the painted name on the bow "MARISOL" with "ALBATROS". Paint the new letters in the same hand-painted white capital lettering style, same size, same brush texture, with the same chipping and weathering as the rest of the hull. Keep everything else unchanged: the boat, its sky blue hull and white stripe, the rope and buoy, the pebble beach, the palafito stilt houses, the hills, the overcast light and the camera framing.
Move this exact same musician, still seated on the same wooden chair and playing the same cello, from the practice room to the middle of a vast frozen lake at blue hour. Keep his face, curly black hair, round tortoiseshell glasses, closed eyes, moss-green cable-knit sweater with rolled sleeves, charcoal trousers, brown boots, bow position and the honey-brown cello with its worn varnish identical. The new setting: smooth dark ice with white cracks and a light dusting of snow around the chair, snow-covered pine forest and mountains on the far shore, a deep blue twilight sky with a thin pink glow on the horizon and the first stars. A small warm light from a lantern on the ice beside the chair lights his face and the cello, while the rest of the scene is cool blue. His breath is faintly visible in the cold air. Remove the practice room completely.
Prepare a written brief or one source image, identify the subject and the precise changes to make, and select the Pro or Max task. Reviewed images can support narrative scene development, object lettering, character relocation, material reinterpretation and photograph restoration concepts. Check identity, wording, composition and the requested details before using the result.
Describe the setting, people, activity and light, then generate the composition. Review physical relationships and atmosphere for a film concept, editorial illustration or visual research draft.
Supply the existing image and specify the exact old and new words and the surface finish to retain. Inspect spelling, placement and texture for a sign update or scene-revision proposal.
Provide one identity reference and describe the destination, pose and matched illumination. Review the edited character and contact with the new environment for a story scene or location concept.
Supply a photograph and describe glass, print, paint or another desired medium, with object positions to retain. Compare the transformed result with the source for an illustrated series or material study.
Provide the old photograph and identify damaged areas, color targets and details to preserve. Inspect the revised image against the original for a personal archive or restoration proposal.
Supply one scene and name the selected object and desired surrounding appearance. Describe the architecture, light and camera to retain, then inspect the edit for a scene or visual-development draft.
Flux Kontext uses per-generation pricing, with a separate current rate for Pro and Max. Within each variant, text generation and one-image editing use the corresponding task rate. The dynamic table reads each task’s current starting price. Choose the variant, framing and PNG/JPG output on the task page and review the complete estimate before submitting.
| Model | Provider | Workflow | Input material | Output framing | Starting rate |
|---|---|---|---|---|---|
| Flux Kontext Pro Text to Image | Black Forest Labs | Text to Image | Text prompt | 7 aspect ratios | $0.04 / generation |
| Flux Kontext Pro Edit | Black Forest Labs | Image Editing | Reference images: up to 1 | 7 aspect ratios | $0.04 / generation |
| Flux Kontext Max Text to Image | Black Forest Labs | Text to Image | Text prompt | 7 aspect ratios | $0.08 / generation |
| Flux Kontext Max Edit | Black Forest Labs | Image Editing | Reference images: up to 1 | 7 aspect ratios | $0.08 / generation |
Test your creative brief online, then bring the verified request into your application.
Write the complete scene or precise change, including exact wording and retained details. Add one public source for editing, select size and output_format and review the estimate. Generate and compare the result with the brief and original image, including identity, lettering, material and composition.
Choose a task, inspect its settings and cost, and follow the result from an online test to an authenticated API request.
Choose Pro or Max, then Text to Image for a written scene or Image Editing for one source photograph. Select one of seven ratios and PNG or JPG, describe the target content or change and review the corresponding generation estimate.
Open the matching task, enter your brief and supply the required images. Review the generated result against subject appearance, composition and the requested changes before carrying the workflow into a project.
Review the selected Pro or Max task’s current per-generation estimate. Compare complete request amounts and the planned test count for your material and editing goal when budgeting the project.
Read the actual prompt and inspect its source images and result together. Use those examples to understand how to assign input roles and describe the details to preserve or change in your own request.
Retain the task ID returned by the API to query status and retrieve completed file URLs. Use your online generation history to review earlier results and the creative direction you tested.
Use the documentation linked from each task for its exact model identifier, accepted inputs, authentication and response format. Integrate the same task you tested online so its media and settings match the request.
Flux Kontext is a Black Forest Labs image family with Pro and Max text-generation and single-image-editing tasks on Vidgo. Both variants offer seven ratios and PNG/JPG output. The editing source establishes the visual context, while the prompt identifies the intended change and details to retain.
Explore model introductions, API guides and platform comparisons to understand input preparation, request integration and cost planning for your project.
