black-forest-labs/flux-pro-finetuned

Inference model for FLUX.1 [pro] using custom `finetune_id`

Capabilities

1:14:33:416:99:162:33:2Reference ImagesSeed

Cost

Community model (estimated from hardware time)

Input Parameters

Name	Type	Description	Default	Constraints
`finetune_id`*	string	Finetune ID for making images using a previously trained fine-tune. Only IDs from trainings made using Replicate's Flux Pro fine-tuning model are supported.	`—`	—
`prompt`*	string	Text prompt for image generation	`—`	—
`aspect_ratio`	string	Aspect ratio for the generated image	`"1:1"`	custom1:116:93:22:34:55:49:163:44:3
`finetune_strength`	number	Controls finetune influence	`1`	min: 0, max: 2
`guidance`	number	Controls the balance between adherence to the text prompt and image quality/diversity. Higher values make the output more closely match the prompt but may reduce overall image quality. Lower values allow for more creative freedom but might produce results less relevant to the prompt.	`3`	min: 2, max: 5
`height`	integer	Height of the generated image in text-to-image mode. Only used when aspect_ratio=custom. Must be a multiple of 32 (if it's not, it will be rounded to nearest multiple of 32). Note: Ignored in img2img and inpainting modes.	`—`	min: 256, max: 1440
`image_prompt`	string(uri)	Image to use with Flux Redux. This is used together with the text prompt to guide the generation towards the composition of the image_prompt. Must be jpeg, png, gif, or webp.	`—`	—
`output_format`	string	Format of the output images.	`"jpg"`	jpgpng
`prompt_upsampling`	boolean	Automatically modify the prompt for more creative generation	`false`	—
`safety_tolerance`	integer	Safety tolerance, 1 is most strict and 6 is most permissive	`2`	min: 1, max: 6
`seed`	integer	Random seed. Set for reproducible generation	`—`	—
`steps`	integer	Number of diffusion steps	`40`	min: 1, max: 50
`width`	integer	Width of the generated image in text-to-image mode. Only used when aspect_ratio=custom. Must be a multiple of 32 (if it's not, it will be rounded to nearest multiple of 32). Note: Ignored in img2img and inpainting modes.	`—`	min: 256, max: 1440

finetune_idrequiredstring

Finetune ID for making images using a previously trained fine-tune. Only IDs from trainings made using Replicate's Flux Pro fine-tuning model are supported.

promptrequiredstring

Text prompt for image generation

aspect_ratiostring

Aspect ratio for the generated image

Default: "1:1"

custom1:116:93:22:34:55:49:163:44:3

finetune_strengthnumber

Controls finetune influence

Default: 1min: 0, max: 2

guidancenumber

Controls the balance between adherence to the text prompt and image quality/diversity. Higher values make the output more closely match the prompt but may reduce overall image quality. Lower values allow for more creative freedom but might produce results less relevant to the prompt.

Default: 3min: 2, max: 5

heightinteger

Height of the generated image in text-to-image mode. Only used when aspect_ratio=custom. Must be a multiple of 32 (if it's not, it will be rounded to nearest multiple of 32). Note: Ignored in img2img and inpainting modes.

min: 256, max: 1440

image_promptstring

Image to use with Flux Redux. This is used together with the text prompt to guide the generation towards the composition of the image_prompt. Must be jpeg, png, gif, or webp.

output_formatstring

Format of the output images.

Default: "jpg"

jpgpng

prompt_upsamplingboolean

Automatically modify the prompt for more creative generation

Default: false

safety_toleranceinteger

Safety tolerance, 1 is most strict and 6 is most permissive

Default: 2min: 1, max: 6

seedinteger

Random seed. Set for reproducible generation

stepsinteger

Number of diffusion steps

Default: 40min: 1, max: 50

widthinteger

Width of the generated image in text-to-image mode. Only used when aspect_ratio=custom. Must be a multiple of 32 (if it's not, it will be rounded to nearest multiple of 32). Note: Ignored in img2img and inpainting modes.

min: 256, max: 1440

Version: 0515c6ddb21cUpdated: 7/25/202610.8K runs