philz1337x/multidiffusion-upscaler:88f19697 – Run with an API on Replicate

Version

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

philz1337x /multidiffusion-upscaler:88f19697

Playground API

Input

sd_model

string

Stable Diffusion model checkpoint

Default: "juggernaut_reborn.safetensors [338b85bc4f]"

sd_vae

string

Stable Diffusion VAE checkpoint

Default: "vae-ft-mse-840000-ema-pruned.safetensors"

image

*file

input image

prompt

string

Shift + Return to add a new line

masterpiece, best quality, highres, <lora:more_details:0.5> <lora:SDXLrender_v2.0:1>masterpiece, best quality, highres, <lora:more_details:0.5> <lora:SDXLrender_v2.0:1>

Prompt

Default: "masterpiece, best quality, highres, <lora:more_details:0.5> <lora:SDXLrender_v2.0:1>"

negative_prompt

string

Shift + Return to add a new line

(worst quality, low quality, normal quality:2) JuggernautNegative-neg(worst quality, low quality, normal quality:2) JuggernautNegative-neg

Negative Prompt

Default: "(worst quality, low quality, normal quality:2) JuggernautNegative-neg"

width

integer

Width of output image

Default: 512

height

integer

Height of output image

Default: 512

num_outputs

integer

(minimum: 1, maximum: 4)

Number of images to output

Default: 1

scheduler

string

scheduler

Default: "DPM++ 3M SDE Karras"

num_inference_steps

integer

(minimum: 1, maximum: 100)

Number of denoising steps

Default: 18

guidance_scale

number

(minimum: 1, maximum: 50)

Scale for classifier-free guidance

Default: 6

seed

integer

Random seed. Leave blank to randomize the seed

Default: 1337

denoising_strength

number

(minimum: 0, maximum: 1)

Denoising strength. 1.0 corresponds to full destruction of information in init image

Default: 0.35

clip_stop_at_last_layers

integer

CLIP stop at last layers

Default: 1

enable_tiled_diffusion

boolean

Enable tiled diffusion

Default: true

td_method

string

Tiled diffusion method

Default: "MultiDiffusion"

td_overwrite_size

boolean

Overwrite size

Default: true

td_keep_input_size

boolean

Keep input size

Default: true

td_image_width

integer

Image width

Default: 1

td_image_height

integer

Image height

Default: 1

td_tile_width

integer

Tile width

Default: 112

td_tile_height

integer

Tile height

Default: 144

td_overlap

integer

Overlap

Default: 4

td_tile_batch_size

integer

Tile batch size

Default: 8

td_upscaler_name

string

Upscaler name

Default: "4x-UltraSharp"

td_scale_factor

number

Scale factor

Default: 2

td_noise_inverse

boolean

Noise inverse

Default: false

td_noise_inverse_steps

integer

Noise inverse steps

Default: 0

td_noise_inverse_renoise_strength

number

Noise inverse renoise strength

Default: 0

td_noise_inverse_renoise_kernel

integer

Noise inverse renoise kernel

Default: 3

enable_tiled_vae

boolean

Enable tiled vae

Default: true

tv_encoder_tile_size

integer

Encoder tile size

Default: 3072

tv_decoder_tile_size

integer

Decoder tile size

Default: 192

tv_move_vae_to_gpu

boolean

Move vae to gpu(if possible)

Default: true

tv_fast_decoder

boolean

Fast decoder

Default: true

tv_fast_encoder

boolean

Fast encoder

Default: true

tv_fast_encoder_color_fix

boolean

Encoder color fix

Default: true

enable_controlnet

boolean

Enable controlnet

Default: true

cn_module

string

Controlnet module

Default: "tile_resample"

cn_model

string

Controlnet model

Default: "control_v11f1e_sd15_tile"

cn_weight

number

Controlnet weight

Default: 0.6

cn_resize_mode

integer

Controlnet resize mode

Default: 1

cn_lowvram

boolean

Controlnet lowvram

Default: false

cn_downsample

number

Controlnet downsample

Default: 1

cn_guidance_start

number

Controlnet guidance start

Default: 0

cn_guidance_end

number

Controlnet guidance end

Default: 1

cn_control_mode

integer

Controlnet control mode. 0= Balanced, 1 = My prompt is more important, 2 = ControlNet is more important

Default: 1

cn_pixel_perfect

boolean

Controlnet pixel perfect

Default: true

cn_threshold_a

integer

Controlnet threshold a

Default: 1

cn_threshold_b

integer

Controlnet threshold b

Default: 1

cn_preprocessor_res

integer

Controlnet preprocessor res

Default: 512

Run this model in Node.js with one line of code:

npx create-replicate --model=philz1337x/multidiffusion-upscaler

or set up a project from scratch

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run philz1337x/multidiffusion-upscaler using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "philz1337x/multidiffusion-upscaler:88f19697c15c8befccd557649fe6b01fcfa55ade961c2d1c3c23d9c986fdaff7",
  {
    input: {
      seed: 1337,
      width: 512,
      height: 512,
      prompt: "masterpiece, best quality, highres, <lora:more_details:0.5> <lora:SDXLrender_v2.0:1>",
      sd_vae: "vae-ft-mse-840000-ema-pruned.safetensors",
      cn_model: "control_v11f1e_sd15_tile",
      sd_model: "juggernaut_reborn.safetensors [338b85bc4f]",
      cn_module: "tile_resample",
      cn_weight: 0.6,
      scheduler: "DPM++ 3M SDE Karras",
      td_method: "MultiDiffusion",
      cn_lowvram: false,
      td_overlap: 4,
      num_outputs: 1,
      cn_downsample: 1,
      td_tile_width: 112,
      cn_resize_mode: 1,
      cn_threshold_a: 1,
      cn_threshold_b: 1,
      guidance_scale: 6,
      td_image_width: 1,
      td_tile_height: 144,
      cn_control_mode: 1,
      cn_guidance_end: 1,
      negative_prompt: "(worst quality, low quality, normal quality:2) JuggernautNegative-neg",
      td_image_height: 1,
      td_scale_factor: 2,
      tv_fast_decoder: true,
      tv_fast_encoder: true,
      cn_pixel_perfect: true,
      enable_tiled_vae: true,
      td_noise_inverse: false,
      td_upscaler_name: "4x-UltraSharp",
      cn_guidance_start: 0,
      enable_controlnet: true,
      td_overwrite_size: true,
      denoising_strength: 0.35,
      td_keep_input_size: true,
      td_tile_batch_size: 8,
      tv_move_vae_to_gpu: true,
      cn_preprocessor_res: 512,
      num_inference_steps: 18,
      tv_decoder_tile_size: 192,
      tv_encoder_tile_size: 3072,
      enable_tiled_diffusion: true,
      td_noise_inverse_steps: 0,
      clip_stop_at_last_layers: 1,
      tv_fast_encoder_color_fix: true,
      td_noise_inverse_renoise_kernel: 3,
      td_noise_inverse_renoise_strength: 0
    }
  }
);
console.log(output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run philz1337x/multidiffusion-upscaler using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "philz1337x/multidiffusion-upscaler:88f19697c15c8befccd557649fe6b01fcfa55ade961c2d1c3c23d9c986fdaff7",
    input={
        "seed": 1337,
        "width": 512,
        "height": 512,
        "prompt": "masterpiece, best quality, highres, <lora:more_details:0.5> <lora:SDXLrender_v2.0:1>",
        "sd_vae": "vae-ft-mse-840000-ema-pruned.safetensors",
        "cn_model": "control_v11f1e_sd15_tile",
        "sd_model": "juggernaut_reborn.safetensors [338b85bc4f]",
        "cn_module": "tile_resample",
        "cn_weight": 0.6,
        "scheduler": "DPM++ 3M SDE Karras",
        "td_method": "MultiDiffusion",
        "cn_lowvram": False,
        "td_overlap": 4,
        "num_outputs": 1,
        "cn_downsample": 1,
        "td_tile_width": 112,
        "cn_resize_mode": 1,
        "cn_threshold_a": 1,
        "cn_threshold_b": 1,
        "guidance_scale": 6,
        "td_image_width": 1,
        "td_tile_height": 144,
        "cn_control_mode": 1,
        "cn_guidance_end": 1,
        "negative_prompt": "(worst quality, low quality, normal quality:2) JuggernautNegative-neg",
        "td_image_height": 1,
        "td_scale_factor": 2,
        "tv_fast_decoder": True,
        "tv_fast_encoder": True,
        "cn_pixel_perfect": True,
        "enable_tiled_vae": True,
        "td_noise_inverse": False,
        "td_upscaler_name": "4x-UltraSharp",
        "cn_guidance_start": 0,
        "enable_controlnet": True,
        "td_overwrite_size": True,
        "denoising_strength": 0.35,
        "td_keep_input_size": True,
        "td_tile_batch_size": 8,
        "tv_move_vae_to_gpu": True,
        "cn_preprocessor_res": 512,
        "num_inference_steps": 18,
        "tv_decoder_tile_size": 192,
        "tv_encoder_tile_size": 3072,
        "enable_tiled_diffusion": True,
        "td_noise_inverse_steps": 0,
        "clip_stop_at_last_layers": 1,
        "tv_fast_encoder_color_fix": True,
        "td_noise_inverse_renoise_kernel": 3,
        "td_noise_inverse_renoise_strength": 0
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run philz1337x/multidiffusion-upscaler using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "88f19697c15c8befccd557649fe6b01fcfa55ade961c2d1c3c23d9c986fdaff7",
    "input": {
      "seed": 1337,
      "width": 512,
      "height": 512,
      "prompt": "masterpiece, best quality, highres, <lora:more_details:0.5> <lora:SDXLrender_v2.0:1>",
      "sd_vae": "vae-ft-mse-840000-ema-pruned.safetensors",
      "cn_model": "control_v11f1e_sd15_tile",
      "sd_model": "juggernaut_reborn.safetensors [338b85bc4f]",
      "cn_module": "tile_resample",
      "cn_weight": 0.6,
      "scheduler": "DPM++ 3M SDE Karras",
      "td_method": "MultiDiffusion",
      "cn_lowvram": false,
      "td_overlap": 4,
      "num_outputs": 1,
      "cn_downsample": 1,
      "td_tile_width": 112,
      "cn_resize_mode": 1,
      "cn_threshold_a": 1,
      "cn_threshold_b": 1,
      "guidance_scale": 6,
      "td_image_width": 1,
      "td_tile_height": 144,
      "cn_control_mode": 1,
      "cn_guidance_end": 1,
      "negative_prompt": "(worst quality, low quality, normal quality:2) JuggernautNegative-neg",
      "td_image_height": 1,
      "td_scale_factor": 2,
      "tv_fast_decoder": true,
      "tv_fast_encoder": true,
      "cn_pixel_perfect": true,
      "enable_tiled_vae": true,
      "td_noise_inverse": false,
      "td_upscaler_name": "4x-UltraSharp",
      "cn_guidance_start": 0,
      "enable_controlnet": true,
      "td_overwrite_size": true,
      "denoising_strength": 0.35,
      "td_keep_input_size": true,
      "td_tile_batch_size": 8,
      "tv_move_vae_to_gpu": true,
      "cn_preprocessor_res": 512,
      "num_inference_steps": 18,
      "tv_decoder_tile_size": 192,
      "tv_encoder_tile_size": 3072,
      "enable_tiled_diffusion": true,
      "td_noise_inverse_steps": 0,
      "clip_stop_at_last_layers": 1,
      "tv_fast_encoder_color_fix": true,
      "td_noise_inverse_renoise_kernel": 3,
      "td_noise_inverse_renoise_strength": 0
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

No output yet! Press "Submit" to start a prediction.