Create task black-forest-labs/flux-kontext-dev
Official documentation: https://replicate.com/black-forest-labs/flux-kontext-dev
/replicate/v1/models/black-forest-labs/flux-kontext-dev/predictionsBody Parametersapplication/json
Input content
propertiesThe aspect ratio of the generated image. Use "match_input_image" to match the aspect ratio of the input image. Default value: "match_input_image".
Makes the model run faster, output quality may suffer slightly for more difficult prompts. Default value: true.
Cue words guide intensity. Default value: 2.5. Minimum value: 0, maximum value: 10
Pictures to use as reference. Must be in jpeg, png, gif or webp format.
Number of inference steps, default: 28. Minimum value: 4, maximum value: 50.
Output image format. Default: "webp".
The quality at which the output image is saved, from 0 to 100. 100 is the best quality, 0 is the lowest quality. Has nothing to do with .png output. Default value: 80. Minimum value: 0, maximum value: 100.
A text description of what you want generated, or instructions on how to edit a given image.
Responses
Creation time
Whether sensitive data has been removed
Error message
Resource or task ID
Input content
Run logs
Model name / model ID
Output result
Status
List of resource URLs
Version
