You're looking at a specific version of this model. Jump to the model overview.

bytedance /res-adapter:08a649ad

Playground API

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
model_name
string (enum)
ByteDance/SDXL-Lightning

Options:

Lykon/dreamshaper-xl-1-0, ByteDance/SDXL-Lightning, dreamlike-art/dreamlike-diffusion-1.0

Choose a stable diffusion model.
prompt
string
cinematic film still, photo of a girl, cyberpunk, neonpunk, headset, city at night, sony fe 12-24mm f/2.8 gm, close up, 32k uhd, wallpaper, analog film grain, SONY headset
Input prompt
negative_prompt
string
ugly, deformed, noisy, blurry, nsfw, low contrast, text, BadDream, 3d, cgi, render, fake, anime, open mouth, big forehead, long neck
Specify things to not see in the output
width
integer
512
Width of output image
height
integer
512
Height of output image
num_inference_steps
integer
4
Number of denoising steps
guidance_scale
number
0

Max: 20

Scale for classifier-free guidance
seed
integer
Random seed. Leave blank to randomize the seed
show_baseline
boolean
True
Show baseline without res-adapter for comparison.

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema 
{'properties': {'with_res_adapter': {'format': 'uri',
                                     'title': 'With Res Adapter',
                                     'type': 'string'},
                'without_res_adapter': {'format': 'uri',
                                        'title': 'Without Res Adapter',
                                        'type': 'string'}},
 'required': ['with_res_adapter'],
 'title': 'ModelOutput',
 'type': 'object'}