You're looking at a specific version of this model. Jump to the model overview.
Input schema
The fields you can use to run this model with an API. If you don’t give a value for a field its default value will be used.
| Field | Type | Default value | Description |
|---|---|---|---|
| prompt |
string
|
Prompt for generated image. If you include the `trigger_word` used in the training process you are more likely to activate the trained object, style, or concept in the resulting image.
|
|
| flux_model_layers_to_patch |
string
(enum)
|
all
Options: all, custom (use a regular expression), all double_block layers, text layers in double_block, image layers in double_block, all single_block layers, attn (attention) layers, mlp (multi-layer perceptron) layers, mod (modulation) layers, every layer in double_block 0, every layer in double_block 1, every layer in double_block 2, every layer in double_block 3, every layer in double_block 4, every layer in double_block 5, every layer in double_block 6, every layer in double_block 7, every layer in double_block 8, every layer in double_block 9, every layer in double_block 10, every layer in double_block 11, every layer in double_block 12, every layer in double_block 13, every layer in double_block 14, every layer in double_block 15, every layer in double_block 16, every layer in double_block 17, every layer in double_block 18, every layer in single_block 0, every layer in single_block 1, every layer in single_block 2, every layer in single_block 3, every layer in single_block 4, every layer in single_block 5, every layer in single_block 6, every layer in single_block 7, every layer in single_block 8, every layer in single_block 9, every layer in single_block 10, every layer in single_block 11, every layer in single_block 12, every layer in single_block 13, every layer in single_block 14, every layer in single_block 15, every layer in single_block 16, every layer in single_block 17, every layer in single_block 18, every layer in single_block 19, every layer in single_block 20, every layer in single_block 21, every layer in single_block 22, every layer in single_block 23, every layer in single_block 24, every layer in single_block 25, every layer in single_block 26, every layer in single_block 27, every layer in single_block 28, every layer in single_block 29, every layer in single_block 30, every layer in single_block 31, every layer in single_block 32, every layer in single_block 33, every layer in single_block 34, every layer in single_block 35, every layer in single_block 36, every layer in single_block 37 |
An enumeration.
|
| flux_model_layers_value |
number
|
1.01
Max: 2 |
The new value for the selected layers
|
| weights_and_biases_to_patch |
string
(enum)
|
weights and biases
Options: weights and biases, just weights, just biases |
An enumeration.
|
| flux_model_layers_regular_expressions |
array
|
[]
|
A set of regular expressions and their target values. Each regular expression should be on a new line and the target value should be a float. For example: double_blocks\.([0-9]+)\.(img|txt)_(mod|attn|mlp)\.(lin|qkv|proj|0|2)\.(weight|bias)=1.01
|
| aspect_ratio |
string
(enum)
|
1:1
Options: 1:1, 16:9, 21:9, 3:2, 2:3, 4:5, 5:4, 3:4, 4:3, 9:16, 9:21 |
Aspect ratio for the generated image in text-to-image mode. The size will always be 1 megapixel, i.e. 1024x1024 if aspect ratio is 1:1. To use arbitrary width and height, set aspect ratio to 'custom'. Note: Ignored in img2img and inpainting modes.
|
| num_outputs |
integer
|
1
Min: 1 Max: 4 |
Number of images to output.
|
| num_inference_steps |
integer
|
28
Min: 1 Max: 50 |
Number of inference steps. More steps can give more detailed images, but take longer.
|
| guidance_scale |
number
|
3
Max: 10 |
Guidance scale for the diffusion process. Lower values can give more realistic images. Good values to try are 2, 2.5, 3 and 3.5
|
| max_shift |
number
|
1.15
Max: 10 |
Maximum shift
|
| base_shift |
number
|
0.5
Max: 10 |
Base shift
|
| output_format |
string
(enum)
|
webp
Options: webp, jpg, png |
Format of the output images
|
| output_quality |
integer
|
95
Max: 100 |
Quality of the output images, from 0 to 100. 100 is best quality, 0 is lowest quality.
|
| seed |
integer
|
Set a seed for reproducibility. Random by default.
|
Output schema
The shape of the response you’ll get when you run this model with an API.
{'items': {'format': 'uri', 'type': 'string'},
'title': 'Output',
'type': 'array'}