You're looking at a specific version of this model. Jump to the model overview.
fewjative /ultimate-sd-upscale:5daf1012
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 |
|---|---|---|---|
| image |
string
|
Input image
|
|
| positive_prompt |
string
|
Hey! Have a nice day :D
|
Positive Prompt
|
| negative_prompt |
string
|
|
Negative Prompt
|
| upscaler |
string
(enum)
|
4x-UltraSharp
Options: 4x_NMKD-Siax_200k, 4x-UltraSharp, RealESRGAN_x4plus, RealESRGAN_x4plus_anime_6B |
Upscaler
|
| upscale_by |
number
|
2
|
Upscale By
|
| use_controlnet_tile |
boolean
|
True
|
Use ControlNet Tile
|
| controlnet_strength |
number
|
1
|
ControlNet Strength
|
| seed |
integer
|
Sampling seed, leave Empty for Random
|
|
| steps |
integer
|
20
|
Steps
|
| cfg |
number
|
8
|
CFG
|
| sampler_name |
string
(enum)
|
euler
Options: euler, euler_ancestral, heun, dpm_2, dpm_2_ancestral, lms, dpm_fast, dpm_adaptive, dpmpp_2s_ancestral, dpmpp_sde, dpmpp_sde_gpu, dpmpp_2m, dpmpp_2m_sde, dpmpp_2m_sde_gpu, dpmpp_3m_sde, dpmpp_3m_sde_gpu, dpmpp, ddim, uni_pc, uni_pc_bh2 |
Sampler
|
| scheduler |
string
(enum)
|
normal
Options: normal, karras, exponential, sgm_uniform, simple, ddim_uniform |
Scheduler
|
| denoise |
number
|
0.2
|
Denoise
|
| mode_type |
string
(enum)
|
Linear
Options: Linear, Chess, None |
Mode Type
|
| tile_width |
integer
|
512
|
Tile Width
|
| tile_height |
integer
|
512
|
Tile Height
|
| mask_blur |
integer
|
8
|
Mask Blur
|
| tile_padding |
integer
|
32
|
Tile Padding
|
| seam_fix_mode |
string
(enum)
|
None
Options: None, Band Pass, Half Tile, Half Tile + Intersections |
Seam Fix Mode
|
| seam_fix_denoise |
number
|
1
|
Seam Fix Denoise
|
| seam_fix_width |
integer
|
64
|
Seam Fix Width
|
| seam_fix_mask_blur |
integer
|
8
|
Seam Fix Mask Blur
|
| seam_fix_padding |
integer
|
16
|
Seam Fix Padding
|
| force_uniform_tiles |
boolean
|
True
|
Force Uniform Tiles
|
Output schema
The shape of the response you’ll get when you run this model with an API.
{'format': 'uri', 'title': 'Output', 'type': 'string'}