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

nightmareai /disco-diffusion:bccc8bd5

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
steps
integer
100
Number of steps, higher numbers will give more refined output but will take longer
prompt
string
A beautiful painting of a singular lighthouse, shining its light across a tumultuous sea of blood by greg rutkowski and thomas kinkade, Trending on artstation.
Text Prompt
width
integer
1280
Width of the output image, higher numbers will take longer
height
integer
768
Height of the output image, higher numbers will take longer
diffusion_model
string (enum)
512x512_diffusion_uncond_finetune_008100

Options:

512x512_diffusion_uncond_finetune_008100, 256x256_diffusion_uncond, pixel_art_diffusion_hard_256, pixel_art_diffusion_soft_256, pixelartdiffusion_expanded, pixelartdiffusion4k, PADexpanded, watercolordiffusion, watercolordiffusion_2, PulpSciFiDiffusion, 256x256_openai_comics_faces_by_alex_spirin_084000, lsun_uncond_100M_1200K_bs128, ukiyoe_diffusion_256_022000, liminal_diffusion, portrait_generator_v001_ema_0.9999_1MM, floraldiffusion

Diffusion Model
diffusion_sampling_mode
string (enum)
ddim

Options:

plms, ddim

Diffusion Sampling Mode
ViTB32
boolean
True
Use ViTB32 model
ViTB16
boolean
True
Use ViTB16 model
ViTL14
boolean
False
Use ViTB14 model
ViTL14_336
boolean
False
Use ViTL14_336 model
RN50
boolean
True
Use RN50 model
RN50x4
boolean
False
Use RN50x4 model
RN50x16
boolean
False
Use RN50x16 model
RN50x64
boolean
False
Use RN50x64 model
RN50x101
boolean
False
Use RN50x101 model
RN101
boolean
False
Use RN101 model
ViTB32_laion2b_e16
boolean
False
Use ViTB32_laion2b_e16 model
ViTB32_laion400m_e31
boolean
False
Use ViTB32_laion400m_e31 model
ViTB32_laion400m_e32
boolean
False
Use ViTB32_laion400m_e32 model
ViTB32quickgelu_laion400m_e31
boolean
False
Use ViTB32quickgelu_laion400m_e31 model
ViTB32quickgelu_laion400m_e32
boolean
False
Use ViTB32quickgelu_laion400m_e32 model
ViTB16_laion400m_e31
boolean
False
Use ViTB16_laion400m_e31 model
ViTB16_laion400m_e32
boolean
False
Use ViTB16_laion400m_e32 model
RN50_yffcc15m
boolean
False
Use RN50_yffcc15m model
RN50_cc12m
boolean
False
Use RN50_cc12m model
RN50_quickgelu_yfcc15m
boolean
False
Use RN50_quickgelu_yfcc15m model
RN50_quickgelu_cc12m
boolean
False
Use RN50_quickgelu_cc12m model
RN101_yfcc15m
boolean
False
Use RN101_yfcc15m model
RN101_quickgelu_yfcc15m
boolean
False
Use RN101_quickgelu_yfcc15m model
use_secondary_model
boolean
True
Use secondary model
clip_guidance_scale
integer
5000
CLIP Guidance Scale
tv_scale
integer
0
TV Scale
range_scale
integer
150
Range Scale
sat_scale
integer
0
Saturation Scale
cutn_batches
integer
4
Cut Batches
skip_augs
boolean
False
Skip Augmentations
init_image
string
Initial image to start generation from
target_image
string
Target image to generate towards, similarly to the text prompt
init_scale
integer
1000
Initial Scale
target_scale
integer
20000
Target Scale
skip_steps
integer
10
Skip Steps
display_rate
integer
20
Steps between outputs, lower numbers may slow down generation.
seed
integer

Max: 4294967295

Seed (leave empty to use a random seed)

Output schema

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

Schema
{'items': {'format': 'uri', 'type': 'string'},
 'title': 'Output',
 'type': 'array',
 'x-cog-array-type': 'iterator'}