prompthunt/cog-sd15-inference – Run with an API on Replicate

prompthunt / cog-sd15-inference

Cold

Public
99 runs
L40S

Run with an API

Playground API Examples README Versions

Input

weights

string

Shift + Return to add a new line

LoRA weights to use. Leave blank to use the default weights.

prompt

string

Shift + Return to add a new line

Input prompt

Default: "An photo of cjw man"

negative_prompt

string

Shift + Return to add a new line

Specify things to not see in the output. Supported embeddings: realisticvision-negative-embedding, EasyNegative, FastNegativeV2, BadDream, ng_deepnegative_v1_75t, UnrealisticDream, negative_hand-neg

Default: ""

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.

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: "K_EULER"

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: 7.5

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

should_swap_face

boolean

Should swap face

Default: false

source_image

file

Source image for face swap

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

disable_safety_checker

boolean

Disable safety checker for generated images. This feature is only available through the API. See [https://replicate.com/docs/how-does-replicate-work#safety](https://replicate.com/docs/how-does-replicate-work#safety)

Default: true

pose_image

file

Pose image for controlnet

controlnet_conditioning_scale

number

(minimum: 0, maximum: 4)

How strong the controlnet conditioning is

Default: 0.75

controlnet_start

number

(minimum: 0, maximum: 1)

When controlnet conditioning starts

Default: 0

controlnet_end

number

(minimum: 0, maximum: 1)

When controlnet conditioning ends

Default: 1

fix_face

boolean

Fix the face in the image

Default: false

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: 512

upscale_face

boolean

Upscale the face using GFPGAN

Default: false

inpaint_prompt

string

Shift + Return to add a new line

Input prompt

Default: "A photo of cjw man"

inpaint_negative_prompt

string

Shift + Return to add a new line

Input Negative Prompt

Default: ""

inpaint_num_inference_steps

integer

(minimum: 1, maximum: 500)

Number of denoising steps

Default: 25

inpaint_guidance_scale

number

(minimum: 1, maximum: 50)

Scale for classifier-free guidance

Default: 3

inpaint_strength

number

(minimum: 0, maximum: 1)

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

Default: 0.35

inpaint_lora_scale

number

(minimum: 0, maximum: 1)

LoRA additive scale. Only applicable on trained models.

Default: 0.6

inpaint_controlnet_conditioning_scale

number

(minimum: 0, maximum: 4)

How strong the controlnet conditioning is

Default: 0.75

inpaint_controlnet_start

number

(minimum: 0, maximum: 1)

When controlnet conditioning starts

Default: 0

inpaint_controlnet_end

number

(minimum: 0, maximum: 1)

When controlnet conditioning ends

Default: 1

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

npx create-replicate --model=prompthunt/cog-sd15-inference

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 prompthunt/cog-sd15-inference using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "prompthunt/cog-sd15-inference:99a1d34ebb68fafd5f177c1abcce2a56feb596af9fbb85057394591e13958c2f",
  {
    input: {
      width: 512,
      height: 512,
      prompt: "An photo of cjw man",
      refine: "no_refiner",
      fix_face: false,
      scheduler: "K_EULER",
      num_outputs: 1,
      face_padding: 2,
      upscale_face: false,
      controlnet_end: 1,
      face_resize_to: 512,
      guidance_scale: 7.5,
      inpaint_prompt: "A photo of cjw man",
      high_noise_frac: 0.8,
      negative_prompt: "",
      prompt_strength: 0.8,
      controlnet_start: 0,
      inpaint_strength: 0.35,
      mask_blur_amount: 8,
      should_swap_face: false,
      inpaint_lora_scale: 0.6,
      num_inference_steps: 50,
      inpaint_controlnet_end: 1,
      inpaint_guidance_scale: 3,
      inpaint_negative_prompt: "",
      inpaint_controlnet_start: 0,
      inpaint_num_inference_steps: 25,
      controlnet_conditioning_scale: 0.75,
      inpaint_controlnet_conditioning_scale: 0.75
    }
  }
);

// 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 prompthunt/cog-sd15-inference using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "prompthunt/cog-sd15-inference:99a1d34ebb68fafd5f177c1abcce2a56feb596af9fbb85057394591e13958c2f",
    input={
        "width": 512,
        "height": 512,
        "prompt": "An photo of cjw man",
        "refine": "no_refiner",
        "fix_face": False,
        "scheduler": "K_EULER",
        "num_outputs": 1,
        "face_padding": 2,
        "upscale_face": False,
        "controlnet_end": 1,
        "face_resize_to": 512,
        "guidance_scale": 7.5,
        "inpaint_prompt": "A photo of cjw man",
        "high_noise_frac": 0.8,
        "negative_prompt": "",
        "prompt_strength": 0.8,
        "controlnet_start": 0,
        "inpaint_strength": 0.35,
        "mask_blur_amount": 8,
        "should_swap_face": False,
        "inpaint_lora_scale": 0.6,
        "num_inference_steps": 50,
        "inpaint_controlnet_end": 1,
        "inpaint_guidance_scale": 3,
        "inpaint_negative_prompt": "",
        "inpaint_controlnet_start": 0,
        "inpaint_num_inference_steps": 25,
        "controlnet_conditioning_scale": 0.75,
        "inpaint_controlnet_conditioning_scale": 0.75
    }
)
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 prompthunt/cog-sd15-inference 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": "99a1d34ebb68fafd5f177c1abcce2a56feb596af9fbb85057394591e13958c2f",
    "input": {
      "width": 512,
      "height": 512,
      "prompt": "An photo of cjw man",
      "refine": "no_refiner",
      "fix_face": false,
      "scheduler": "K_EULER",
      "num_outputs": 1,
      "face_padding": 2,
      "upscale_face": false,
      "controlnet_end": 1,
      "face_resize_to": 512,
      "guidance_scale": 7.5,
      "inpaint_prompt": "A photo of cjw man",
      "high_noise_frac": 0.8,
      "negative_prompt": "",
      "prompt_strength": 0.8,
      "controlnet_start": 0,
      "inpaint_strength": 0.35,
      "mask_blur_amount": 8,
      "should_swap_face": false,
      "inpaint_lora_scale": 0.6,
      "num_inference_steps": 50,
      "inpaint_controlnet_end": 1,
      "inpaint_guidance_scale": 3,
      "inpaint_negative_prompt": "",
      "inpaint_controlnet_start": 0,
      "inpaint_num_inference_steps": 25,
      "controlnet_conditioning_scale": 0.75,
      "inpaint_controlnet_conditioning_scale": 0.75
    }
  }' \
  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 $0.010 to run on Replicate, or 100 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 11 seconds.

Readme

This model doesn't have a readme.