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.
|
|
| advanced_flux_model_layers_to_patch |
string
|
double_blocks\.([0-9]+)\.(img|txt)_(mod|attn|mlp)\.(lin|qkv|proj|0|2)\.(weight|bias)=1.01
single_blocks\.([0-9]+)\.(linear[12]|modulation\.lin)\.(weight|bias)=1.01
|
A set of regular expressions and their target values. Each regular expression should be on a new line. By default all layers are set to 1.01
|
| double_blocks_to_patch |
string
|
0-18
|
Specify double blocks to patch. For example: 0-18 or 0,2,4. Use 0-18 to patch all double blocks.
|
| double_block_targets |
string
(enum)
|
all
Options: none, all, all_img, all_txt, img_mod, img_attn, img_mlp, txt_mod, txt_attn, txt_mlp, txt_and_img_mod, txt_and_img_attn, txt_and_img_mlp |
Double blocks can patch image, text or both blocks, or specific modulations, attention, and mlp layers.
|
| double_block_subtype_targets |
string
(enum)
|
lin, qkv, proj
Options: none, lin, qkv, proj, lin, qkv, proj, lin, qkv, lin, proj, qkv, proj |
An enumeration.
|
| single_blocks_to_patch |
string
|
0-37
|
Specify single blocks to patch. For example: 0-18 or 0,2,4. Use 0-37 to patch all single blocks.
|
| single_block_targets |
string
(enum)
|
all
Options: none, all, all_linear, linear1, linear2, modulation.lin |
An enumeration.
|
| weights_and_biases_to_patch |
string
(enum)
|
weights_and_biases
Options: none, weights, biases, weights_and_biases |
An enumeration.
|
| simple_flux_model_layers_to_patch |
string
(enum)
|
all layers
Options: all layers, all double block layers, all single block layers, all attention (attn) layers, all mlp layers, all modulation (mod) layers, all linear (lin) layers, all qkv layers, all projection (proj) layers |
Alternatively pick a set of predefined layers to patch
|
| simple_flux_model_layers_to_patch_strength |
number
|
1
Max: 2 |
Strength of the patch
|
| 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'}