You're looking at a specific version of this model. Jump to the model overview.
philz1337x /multidiffusion-upscaler:88f19697
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 |
|---|---|---|---|
| sd_model |
string
(enum)
|
juggernaut_reborn.safetensors [338b85bc4f]
Options: epicrealism_naturalSinRC1VAE.safetensors [84d76a0328], juggernaut_reborn.safetensors [338b85bc4f], juggernaut_final.safetensors |
Stable Diffusion model checkpoint
|
| sd_vae |
string
(enum)
|
vae-ft-mse-840000-ema-pruned.safetensors
Options: None, vae-ft-mse-840000-ema-pruned.safetensors |
Stable Diffusion VAE checkpoint
|
| image |
string
|
input image
|
|
| prompt |
string
|
masterpiece, best quality, highres, <lora:more_details:0.5> <lora:SDXLrender_v2.0:1>
|
Prompt
|
| negative_prompt |
string
|
(worst quality, low quality, normal quality:2) JuggernautNegative-neg
|
Negative Prompt
|
| width |
integer
|
512
|
Width of output image
|
| height |
integer
|
512
|
Height of output image
|
| num_outputs |
integer
|
1
Min: 1 Max: 4 |
Number of images to output
|
| scheduler |
string
(enum)
|
DPM++ 3M SDE Karras
Options: DPM++ 2M Karras, DPM++ SDE Karras, DPM++ 2M SDE Exponential, DPM++ 2M SDE Karras, Euler a, Euler, LMS, Heun, DPM2, DPM2 a, DPM++ 2S a, DPM++ 2M, DPM++ SDE, DPM++ 2M SDE, DPM++ 2M SDE Heun, DPM++ 2M SDE Heun Karras, DPM++ 2M SDE Heun Exponential, DPM++ 3M SDE, DPM++ 3M SDE Karras, DPM++ 3M SDE Exponential, DPM fast, DPM adaptive, LMS Karras, DPM2 Karras, DPM2 a Karras, DPM++ 2S a Karras, Restart, DDIM, PLMS, UniPC |
scheduler
|
| num_inference_steps |
integer
|
18
Min: 1 Max: 100 |
Number of denoising steps
|
| guidance_scale |
number
|
6
Min: 1 Max: 50 |
Scale for classifier-free guidance
|
| seed |
integer
|
1337
|
Random seed. Leave blank to randomize the seed
|
| denoising_strength |
number
|
0.35
Max: 1 |
Denoising strength. 1.0 corresponds to full destruction of information in init image
|
| clip_stop_at_last_layers |
integer
|
1
|
CLIP stop at last layers
|
| enable_tiled_diffusion |
boolean
|
True
|
Enable tiled diffusion
|
| td_method |
string
(enum)
|
MultiDiffusion
Options: MultiDiffusion, Mixture of Diffusers |
Tiled diffusion method
|
| td_overwrite_size |
boolean
|
True
|
Overwrite size
|
| td_keep_input_size |
boolean
|
True
|
Keep input size
|
| td_image_width |
integer
|
1
|
Image width
|
| td_image_height |
integer
|
1
|
Image height
|
| td_tile_width |
integer
|
112
|
Tile width
|
| td_tile_height |
integer
|
144
|
Tile height
|
| td_overlap |
integer
|
4
|
Overlap
|
| td_tile_batch_size |
integer
|
8
|
Tile batch size
|
| td_upscaler_name |
string
(enum)
|
4x-UltraSharp
Options: None, Lanczos, 4x-UltraSharp, 4x_foolhardy_Remacri, ESRGAN_4x |
Upscaler name
|
| td_scale_factor |
number
|
2
|
Scale factor
|
| td_noise_inverse |
boolean
|
False
|
Noise inverse
|
| td_noise_inverse_steps |
integer
|
0
|
Noise inverse steps
|
| td_noise_inverse_renoise_strength |
number
|
0
|
Noise inverse renoise strength
|
| td_noise_inverse_renoise_kernel |
integer
|
3
|
Noise inverse renoise kernel
|
| enable_tiled_vae |
boolean
|
True
|
Enable tiled vae
|
| tv_encoder_tile_size |
integer
|
3072
|
Encoder tile size
|
| tv_decoder_tile_size |
integer
|
192
|
Decoder tile size
|
| tv_move_vae_to_gpu |
boolean
|
True
|
Move vae to gpu(if possible)
|
| tv_fast_decoder |
boolean
|
True
|
Fast decoder
|
| tv_fast_encoder |
boolean
|
True
|
Fast encoder
|
| tv_fast_encoder_color_fix |
boolean
|
True
|
Encoder color fix
|
| enable_controlnet |
boolean
|
True
|
Enable controlnet
|
| cn_module |
string
(enum)
|
tile_resample
Options: tile_resample |
Controlnet module
|
| cn_model |
string
(enum)
|
control_v11f1e_sd15_tile
Options: control_v11f1e_sd15_tile |
Controlnet model
|
| cn_weight |
number
|
0.6
|
Controlnet weight
|
| cn_resize_mode |
integer
|
1
|
Controlnet resize mode
|
| cn_lowvram |
boolean
|
False
|
Controlnet lowvram
|
| cn_downsample |
number
|
1
|
Controlnet downsample
|
| cn_guidance_start |
number
|
0
|
Controlnet guidance start
|
| cn_guidance_end |
number
|
1
|
Controlnet guidance end
|
| cn_control_mode |
integer
|
1
|
Controlnet control mode. 0= Balanced, 1 = My prompt is more important, 2 = ControlNet is more important
|
| cn_pixel_perfect |
boolean
|
True
|
Controlnet pixel perfect
|
| cn_threshold_a |
integer
|
1
|
Controlnet threshold a
|
| cn_threshold_b |
integer
|
1
|
Controlnet threshold b
|
| cn_preprocessor_res |
integer
|
512
|
Controlnet preprocessor res
|
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'}