Model availability and access depend on your workspace and plan.
About the model
FLUX.2 Pro, explained.
FLUX.2 Pro is a image model by Black Forest Labs. It supports image to image, text to image, partner, quality.
Supported capabilities
Image to image
Text to image
Partner
Quality
What you get back. Your generated image appears directly in your Relam chat.
Working with FLUX.2 Pro
Shape the result.
Seed
Optional input
Random seed. Set for reproducible generation
Width
Optional input
Width of the generated image. 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).
Height
Optional input
Height of the generated image. 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).
Prompt
Required input
Text prompt for image generation
Input Images
Optional input
List of input images for image-to-image generation. Maximum 8 images. Must be jpeg, png, gif, or webp. URLs will be converted to base64.
Output Quality
Optional input
Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs
Questions & answers
More about FLUX.2 Pro.
FLUX.2 Pro is a image model by Black Forest Labs. It supports image to image, text to image, partner, quality.
FLUX.2 Pro is a image model by Black Forest Labs. It supports image to image, text to image, partner, quality.
Black Forest Labs is the vendor behind FLUX.2 Pro, a image model available in the Relam catalogue.
Black Forest Labs is the vendor behind FLUX.2 Pro, a image model available in the Relam catalogue.
Random seed. Set for reproducible generation
Random seed. Set for reproducible generation
Width of the generated image. 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).
Width of the generated image. 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).
Height of the generated image. 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).
Height of the generated image. 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).
Text prompt for image generation This input is required.
Text prompt for image generation This input is required.
List of input images for image-to-image generation. Maximum 8 images. Must be jpeg, png, gif, or webp. URLs will be converted to base64.
List of input images for image-to-image generation. Maximum 8 images. Must be jpeg, png, gif, or webp. URLs will be converted to base64.
Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs
Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs
Safety tolerance, 1 is most strict and 5 is most permissive
Safety tolerance, 1 is most strict and 5 is most permissive
Resolution in megapixels. Up to 4 MP is possible, but 2 MP or below is recommended. The maximum image size is 2048x2048, which means that high-resolution images may not respect the resolution if aspect ratio is not 1:1. Resolution is not used when aspect_ratio is "custom". When aspect_ratio is "match_input_image", use "match_input_image" to match the input image"s resolution (clamped to 0.5-4 MP). Supported values are match_input_image, 0.5 MP, 1 MP, 2 MP, 4 MP. The model default is 1 MP. Your workspace may offer a narrower selection depending on your plan.
Resolution in megapixels. Up to 4 MP is possible, but 2 MP or below is recommended. The maximum image size is 2048x2048, which means that high-resolution images may not respect the resolution if aspect ratio is not 1:1. Resolution is not used when aspect_ratio is "custom". When aspect_ratio is "match_input_image", use "match_input_image" to match the input image"s resolution (clamped to 0.5-4 MP). Supported values are match_input_image, 0.5 MP, 1 MP, 2 MP, 4 MP. The model default is 1 MP. Your workspace may offer a narrower selection depending on your plan.
Aspect ratio for the generated image. Use "match_input_image" to match the first input image"s aspect ratio. Supported values are match_input_image, custom, 1:1, 16:9, 3:2, 2:3, 4:5, 5:4, 9:16, 3:4, 4:3. The model default is 1:1. Your workspace may offer a narrower selection depending on your plan.
Aspect ratio for the generated image. Use "match_input_image" to match the first input image"s aspect ratio. Supported values are match_input_image, custom, 1:1, 16:9, 3:2, 2:3, 4:5, 5:4, 9:16, 3:4, 4:3. The model default is 1:1. Your workspace may offer a narrower selection depending on your plan.
Format of the output images. Supported values are webp, jpg, png. The model default is png. Your workspace may offer a narrower selection depending on your plan.
Format of the output images. Supported values are webp, jpg, png. The model default is png. Your workspace may offer a narrower selection depending on your plan.
Open your Relam workspace and look for FLUX.2 Pro in the image model selector. Its required inputs are prompt. Available models, controls and access depend on your workspace and plan.
Open your Relam workspace and look for FLUX.2 Pro in the image model selector. Its required inputs are prompt. Available models, controls and access depend on your workspace and plan.
Safety Tolerance
Optional input
Safety tolerance, 1 is most strict and 5 is most permissive
Output & configuration
The details you control.
These options come from FLUX.2 Pro’s model specification. Your workspace shows the options included with your plan.
Resolution
Resolution in megapixels. Up to 4 MP is possible, but 2 MP or below is recommended. The maximum image size is 2048x2048, which means that high-resolution images may not respect the resolution if aspect ratio is not 1:1. Resolution is not used when aspect_ratio is "custom". When aspect_ratio is "match_input_image", use "match_input_image" to match the input image"s resolution (clamped to 0.5-4 MP).
match_input_image / 0.5 MP / 1 MP / 2 MP / 4 MP
Model default: 1 MP
Aspect ratio
Aspect ratio for the generated image. Use "match_input_image" to match the first input image"s aspect ratio.