You're looking at a specific version of this model. Jump to the model overview.
its-magick /flux-multi-lora-loader:fa3f434d
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
|
|
| aspect_ratio |
string
(enum)
|
1:1
Options: 1:1, 3:2, 4:3, 16:9, 21:9, 2:3, 3:4, 9:16, 9:21, thumb, small, ad, hd, facebook, twitter, youtube, linkedin, pinterest, instagram, tiktok, snapchat, whatsapp, telegram, signal, discord, twitch, threads, stories, reels, igtv, linkedin_story, linkedin_post, linkedin_banner, linkedin_logo, linkedin_carousel, linkedin_profile, facebook_story, linkedin_cover, linkedin_video |
Aspect ratio for the generated image
|
| image |
string
|
Input image for image to image mode. The aspect ratio of your output will match this image
|
|
| 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
|
| guidance_scale |
number
|
3.5
Max: 10 |
Guidance scale for the diffusion process
|
| seed |
integer
|
Random seed. Set for reproducible generation
|
|
| output_format |
string
(enum)
|
webp
Options: webp, jpg, png |
Format of the output images
|
| output_quality |
integer
|
80
Max: 100 |
Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs
|
| hf_loras |
array
|
Huggingface path, or URL to the LoRA weights. Ex: alvdansen/frosting_lane_flux
|
|
| lora_scales |
array
|
Scale for the LoRA weights. Default value is 0.8
|
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'}