sd-lora-8/inference_2 – Run with an API on Replicate

sd-lora-8 / inference_2

Cold

Public
92 runs
L40S

Run with an API

Playground API Examples README Versions

Input

lora_url

*string

Shift + Return to add a new line

Load Lora model

prompt

string

Shift + Return to add a new line

Input prompt

Default: "A photo of TOK"

negative_prompt

string

Shift + Return to add a new line

plastic, blurry, grainy, [deformed | disfigured], poorly drawn, [bad : wrong] anatomy, [extra | missing | floating | disconnected] limb, (mutated hands and fingers), blurryplastic, blurry, grainy, [deformed | disfigured], poorly drawn, [bad : wrong] anatomy, [extra | missing | floating | disconnected] limb, (mutated hands and fingers), blurry

Input Negative Prompt

Default: "plastic, blurry, grainy, [deformed | disfigured], poorly drawn, [bad : wrong] anatomy, [extra | missing | floating | disconnected] limb, (mutated hands and fingers), blurry"

image

file

Input image for img2img or inpaint mode

mask

file

Input mask for inpaint mode. Black areas will be preserved, white areas will be inpainted.

pose_image

file

Input pose image for controlnet mode

width

integer

Width of output image

Default: 768

height

integer

Height of output image

Default: 1024

num_outputs

integer

(minimum: 1, maximum: 100)

Number of images to output.

Default: 1

scheduler

string

scheduler

Default: "DPM++SDEKarras"

num_inference_steps

integer

(minimum: 1, maximum: 500)

Number of denoising steps

Default: 50

guidance_scale

number

(minimum: 1, maximum: 50)

Scale for classifier-free guidance

Default: 3

prompt_strength

number

(minimum: 0, maximum: 1)

Prompt strength when using img2img / inpaint. 1.0 corresponds to full destruction of information in image

Default: 0.8

seed

integer

Random seed. Leave blank to randomize the seed

refine

string

Which refine style to use

Default: "no_refiner"

high_noise_frac

number

(minimum: 0, maximum: 1)

For expert_ensemble_refiner, the fraction of noise to use

Default: 0.8

refine_steps

integer

For base_image_refiner, the number of steps to refine, defaults to num_inference_steps

lora_scale

number

(minimum: 0, maximum: 1)

LoRA additive scale. Only applicable on trained models.

Default: 0.8

mask_blur_amount

number

Amount of blur to apply to the mask.

Default: 8

face_padding

number

Amount of padding (as percentage) to add to the face bounding box.

Default: 2

face_resize_to

integer

Resize the face bounding box to this size (in pixels).

Default: 1024

inpaint_prompt

string

Shift + Return to add a new line

Input inpaint prompt

Default: "A photo of TOK"

inpaint_negative_prompt

string

Shift + Return to add a new line

(worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth(worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth

Input inpaint negative prompt

Default: "(worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth"

inpaint_strength

number

(minimum: 0, maximum: 1)

Prompt strength when using inpaint. 1.0 corresponds to full destruction of information in image

Default: 0.35

inpaint_num_inference_steps

integer

(minimum: 1, maximum: 500)

Number of denoising steps for inpainting

Default: 25

inpaint_guidance_scale

number

(minimum: 1, maximum: 50)

Scale for classifier-free guidance for inpainting

Default: 3

controlnet_conditioning_scale

number

Scale for guidance for controlnet

Default: 1

upscale_face_image

boolean

Upscales face image before inpainting

Default: false

upscale_final_image

boolean

Upscales final image before returning

Default: false

include_debug_output_images

boolean

Include debug output in the output

Default: true

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

npx create-replicate --model=sd-lora-8/inference_2

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 sd-lora-8/inference_2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "sd-lora-8/inference_2:14a05fade3d3a5c701cc01d44a79065a0748a4850e2ed2c9b36ea347cb6f3bf5",
  {
    input: {
      width: 768,
      height: 1024,
      prompt: "A photo of TOK",
      refine: "no_refiner",
      scheduler: "DPM++SDEKarras",
      lora_scale: 0.8,
      num_outputs: 1,
      face_padding: 2,
      face_resize_to: 1024,
      guidance_scale: 3,
      inpaint_prompt: "A photo of TOK",
      high_noise_frac: 0.8,
      negative_prompt: "plastic, blurry, grainy, [deformed | disfigured], poorly drawn, [bad : wrong] anatomy, [extra | missing | floating | disconnected] limb, (mutated hands and fingers), blurry",
      prompt_strength: 0.8,
      inpaint_strength: 0.35,
      mask_blur_amount: 8,
      upscale_face_image: false,
      num_inference_steps: 50,
      upscale_final_image: false,
      inpaint_guidance_scale: 3,
      inpaint_negative_prompt: "(worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth",
      include_debug_output_images: true,
      inpaint_num_inference_steps: 25,
      controlnet_conditioning_scale: 1
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

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 sd-lora-8/inference_2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "sd-lora-8/inference_2:14a05fade3d3a5c701cc01d44a79065a0748a4850e2ed2c9b36ea347cb6f3bf5",
    input={
        "width": 768,
        "height": 1024,
        "prompt": "A photo of TOK",
        "refine": "no_refiner",
        "scheduler": "DPM++SDEKarras",
        "lora_scale": 0.8,
        "num_outputs": 1,
        "face_padding": 2,
        "face_resize_to": 1024,
        "guidance_scale": 3,
        "inpaint_prompt": "A photo of TOK",
        "high_noise_frac": 0.8,
        "negative_prompt": "plastic, blurry, grainy, [deformed | disfigured], poorly drawn, [bad : wrong] anatomy, [extra | missing | floating | disconnected] limb, (mutated hands and fingers), blurry",
        "prompt_strength": 0.8,
        "inpaint_strength": 0.35,
        "mask_blur_amount": 8,
        "upscale_face_image": False,
        "num_inference_steps": 50,
        "upscale_final_image": False,
        "inpaint_guidance_scale": 3,
        "inpaint_negative_prompt": "(worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth",
        "include_debug_output_images": True,
        "inpaint_num_inference_steps": 25,
        "controlnet_conditioning_scale": 1
    }
)
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 sd-lora-8/inference_2 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": "14a05fade3d3a5c701cc01d44a79065a0748a4850e2ed2c9b36ea347cb6f3bf5",
    "input": {
      "width": 768,
      "height": 1024,
      "prompt": "A photo of TOK",
      "refine": "no_refiner",
      "scheduler": "DPM++SDEKarras",
      "lora_scale": 0.8,
      "num_outputs": 1,
      "face_padding": 2,
      "face_resize_to": 1024,
      "guidance_scale": 3,
      "inpaint_prompt": "A photo of TOK",
      "high_noise_frac": 0.8,
      "negative_prompt": "plastic, blurry, grainy, [deformed | disfigured], poorly drawn, [bad : wrong] anatomy, [extra | missing | floating | disconnected] limb, (mutated hands and fingers), blurry",
      "prompt_strength": 0.8,
      "inpaint_strength": 0.35,
      "mask_blur_amount": 8,
      "upscale_face_image": false,
      "num_inference_steps": 50,
      "upscale_final_image": false,
      "inpaint_guidance_scale": 3,
      "inpaint_negative_prompt": "(worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth",
      "include_debug_output_images": true,
      "inpaint_num_inference_steps": 25,
      "controlnet_conditioning_scale": 1
    }
  }' \
  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.

Run time and cost

This model costs approximately $0.040 to run on Replicate, or 25 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia L40S GPU hardware. Predictions typically complete within 41 seconds. The predict time for this model varies significantly based on the inputs.

Readme

This model doesn't have a readme.