dazaleas/sd15-cog – Run with an API on Replicate

dazaleas / sd15-cog

Inference SD 1.5 with cog including several models.

Cold

Public
1.8K runs
A100 (80GB)

Iterate in the playground

Run with an API

Playground API Examples README Versions

Input

model

string

The model to use

Default: "pastelmix.safetensors"

vae

string

The vae to use

Default: "None"

prompt

string

Shift + Return to add a new line

self-portrait oil painting of a beautiful young woman wearing an intricate dress, 8k, uhd, photorealistic, godraysself-portrait oil painting of a beautiful young woman wearing an intricate dress, 8k, uhd, photorealistic, godrays

The prompt

Default: "masterpiece, illustration, portrait of a beautiful young woman"

negative_prompt

string

Shift + Return to add a new line

low quality, bad quality, worst quality, background art, mirror, reflectionlow quality, bad quality, worst quality, background art, mirror, reflection

The negative prompt (For things you don't want)

Default: "low quality, bad quality, worst quality"

sampler_name

string

The sampler used when generating

Default: "DPM++ 2M Karras"

steps

integer

(minimum: 1, maximum: 100)

The steps when generating

Default: 35

cfg_scale

number

(minimum: 1, maximum: 20)

CFG Scale defines how much attention the model pays to the prompt when generating

Default: 7

width

integer

(minimum: 1, maximum: 2048)

The width of the image

Default: 768

height

integer

(minimum: 1, maximum: 2048)

The height of the image

Default: 768

batch_size

integer

(minimum: 1, maximum: 4)

Number of images to generate (1-4)

Default: 1

enable_hr

boolean

Generate high resoultion version

Default: false

hr_scale

integer

(minimum: 1, maximum: 4)

The scale to resize

Default: 2

denoising_strength

number

(minimum: 0, maximum: 1)

The strength when applying denoising

Default: 0.35

hr_second_pass_steps

integer

(minimum: 0, maximum: 30)

The steps when performing second pass

Default: 18

hr_upscaler

string

The upscaler to use when performing second pass

Default: "R-ESRGAN 4x+ Anime6B"

seed

integer

The seed used when generating, set to -1 for random seed

Default: -1

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

npx create-replicate --model=dazaleas/sd15-cog

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

const output = await replicate.run(
  "dazaleas/sd15-cog:cd92f61dbf76d2e58b882dad9daf578f918d0309e6d19d188d48d226866a820e",
  {
    input: {
      vae: "consistency.pt",
      seed: -1,
      model: "xxmix.safetensors",
      steps: 35,
      width: 768,
      height: 768,
      prompt: "self-portrait oil painting of a beautiful young woman wearing an intricate dress, 8k, uhd, photorealistic, godrays",
      hr_scale: 2,
      cfg_scale: 7,
      enable_hr: false,
      batch_size: 1,
      hr_upscaler: "4x_fatal_Anime_500000_G",
      sampler_name: "DPM++ SDE Karras",
      negative_prompt: "low quality, bad quality, worst quality, background art, mirror, reflection",
      denoising_strength: 0.35,
      hr_second_pass_steps: 18
    }
  }
);

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

output = replicate.run(
    "dazaleas/sd15-cog:cd92f61dbf76d2e58b882dad9daf578f918d0309e6d19d188d48d226866a820e",
    input={
        "vae": "consistency.pt",
        "seed": -1,
        "model": "xxmix.safetensors",
        "steps": 35,
        "width": 768,
        "height": 768,
        "prompt": "self-portrait oil painting of a beautiful young woman wearing an intricate dress, 8k, uhd, photorealistic, godrays",
        "hr_scale": 2,
        "cfg_scale": 7,
        "enable_hr": False,
        "batch_size": 1,
        "hr_upscaler": "4x_fatal_Anime_500000_G",
        "sampler_name": "DPM++ SDE Karras",
        "negative_prompt": "low quality, bad quality, worst quality, background art, mirror, reflection",
        "denoising_strength": 0.35,
        "hr_second_pass_steps": 18
    }
)
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 dazaleas/sd15-cog 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": "dazaleas/sd15-cog:cd92f61dbf76d2e58b882dad9daf578f918d0309e6d19d188d48d226866a820e",
    "input": {
      "vae": "consistency.pt",
      "seed": -1,
      "model": "xxmix.safetensors",
      "steps": 35,
      "width": 768,
      "height": 768,
      "prompt": "self-portrait oil painting of a beautiful young woman wearing an intricate dress, 8k, uhd, photorealistic, godrays",
      "hr_scale": 2,
      "cfg_scale": 7,
      "enable_hr": false,
      "batch_size": 1,
      "hr_upscaler": "4x_fatal_Anime_500000_G",
      "sampler_name": "DPM++ SDE Karras",
      "negative_prompt": "low quality, bad quality, worst quality, background art, mirror, reflection",
      "denoising_strength": 0.35,
      "hr_second_pass_steps": 18
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2023-10-25T07:12:45.686020Z",
  "created_at": "2023-10-25T07:12:40.807666Z",
  "data_removed": false,
  "error": null,
  "id": "xrs4xd3b5rmdzszfricd2b3gtm",
  "input": {
    "vae": "consistency.pt",
    "seed": -1,
    "model": "xxmix.safetensors",
    "steps": 35,
    "width": 768,
    "height": 768,
    "prompt": "self-portrait oil painting of a beautiful young woman wearing an intricate dress, 8k, uhd, photorealistic, godrays",
    "hr_scale": 2,
    "cfg_scale": 7,
    "enable_hr": false,
    "batch_size": 1,
    "hr_upscaler": "4x_fatal_Anime_500000_G",
    "sampler_name": "DPM++ SDE Karras",
    "negative_prompt": "low quality, bad quality, worst quality, background art, mirror, reflection",
    "denoising_strength": 0.35,
    "hr_second_pass_steps": 18
  },
  "logs": "Checking model and vae...\nPrevious model: xxmix.safetensors\nModel is already up-to-date.\nPrevious vae: consistency.pt\nVAE is already up-to-date.\nDone, time used: 4.8160552978515625e-05 seconds.\n  0%|          | 0/35 [00:00<?, ?it/s]\nTotal progress: 648it [07:16,  3.85s/it]\u001b[A\n  3%|▎         | 1/35 [00:00<00:03,  8.54it/s]\nTotal progress: 649it [07:16,  2.73s/it]\u001b[A\n  6%|▌         | 2/35 [00:00<00:03,  8.56it/s]\nTotal progress: 650it [07:16,  1.95s/it]\u001b[A\n  9%|▊         | 3/35 [00:00<00:03,  8.57it/s]\nTotal progress: 651it [07:16,  1.40s/it]\u001b[A\n 11%|█▏        | 4/35 [00:00<00:03,  8.59it/s]\nTotal progress: 652it [07:16,  1.01s/it]\u001b[A\n 14%|█▍        | 5/35 [00:00<00:03,  8.60it/s]\nTotal progress: 653it [07:16,  1.34it/s]\u001b[A\n 17%|█▋        | 6/35 [00:00<00:03,  8.59it/s]\nTotal progress: 654it [07:16,  1.80it/s]\u001b[A\n 20%|██        | 7/35 [00:00<00:03,  8.59it/s]\nTotal progress: 655it [07:16,  2.36it/s]\u001b[A\n 23%|██▎       | 8/35 [00:00<00:03,  8.59it/s]\nTotal progress: 656it [07:16,  3.01it/s]\u001b[A\n 26%|██▌       | 9/35 [00:01<00:03,  8.59it/s]\nTotal progress: 657it [07:17,  3.74it/s]\u001b[A\n 29%|██▊       | 10/35 [00:01<00:02,  8.59it/s]\nTotal progress: 658it [07:17,  4.51it/s]\u001b[A\n 31%|███▏      | 11/35 [00:01<00:02,  8.60it/s]\nTotal progress: 659it [07:17,  5.26it/s]\u001b[A\n 34%|███▍      | 12/35 [00:01<00:02,  8.62it/s]\nTotal progress: 660it [07:17,  5.96it/s]\u001b[A\n 37%|███▋      | 13/35 [00:01<00:02,  8.60it/s]\nTotal progress: 661it [07:17,  6.56it/s]\u001b[A\n 40%|████      | 14/35 [00:01<00:02,  8.62it/s]\nTotal progress: 662it [07:17,  7.07it/s]\u001b[A\n 43%|████▎     | 15/35 [00:01<00:02,  8.61it/s]\nTotal progress: 663it [07:17,  7.47it/s]\u001b[A\n 46%|████▌     | 16/35 [00:01<00:02,  8.63it/s]\nTotal progress: 664it [07:17,  7.79it/s]\u001b[A\n 49%|████▊     | 17/35 [00:01<00:02,  8.64it/s]\nTotal progress: 665it [07:17,  8.04it/s]\u001b[A\n 51%|█████▏    | 18/35 [00:02<00:01,  8.64it/s]\nTotal progress: 666it [07:18,  8.21it/s]\u001b[A\n 54%|█████▍    | 19/35 [00:02<00:01,  8.61it/s]\nTotal progress: 667it [07:18,  8.30it/s]\u001b[A\n 57%|█████▋    | 20/35 [00:02<00:01,  8.61it/s]\nTotal progress: 668it [07:18,  8.39it/s]\u001b[A\n 60%|██████    | 21/35 [00:02<00:01,  8.63it/s]\nTotal progress: 669it [07:18,  8.48it/s]\u001b[A\n 63%|██████▎   | 22/35 [00:02<00:01,  8.67it/s]\nTotal progress: 670it [07:18,  8.56it/s]\u001b[A\n 66%|██████▌   | 23/35 [00:02<00:01,  8.65it/s]\nTotal progress: 671it [07:18,  8.58it/s]\u001b[A\n 69%|██████▊   | 24/35 [00:02<00:01,  8.68it/s]\nTotal progress: 672it [07:18,  8.63it/s]\u001b[A\n 71%|███████▏  | 25/35 [00:02<00:01,  8.71it/s]\nTotal progress: 673it [07:18,  8.67it/s]\u001b[A\n 74%|███████▍  | 26/35 [00:03<00:01,  8.69it/s]\nTotal progress: 674it [07:19,  8.66it/s]\u001b[A\n 77%|███████▋  | 27/35 [00:03<00:00,  8.72it/s]\nTotal progress: 675it [07:19,  8.70it/s]\u001b[A\n 80%|████████  | 28/35 [00:03<00:00,  8.74it/s]\nTotal progress: 676it [07:19,  8.73it/s]\u001b[A\n 83%|████████▎ | 29/35 [00:03<00:00,  8.72it/s]\nTotal progress: 677it [07:19,  8.71it/s]\u001b[A\n 86%|████████▌ | 30/35 [00:03<00:00,  8.74it/s]\nTotal progress: 678it [07:19,  8.71it/s]\u001b[A\n 89%|████████▊ | 31/35 [00:03<00:00,  8.71it/s]\nTotal progress: 679it [07:19,  8.71it/s]\u001b[A\n 91%|█████████▏| 32/35 [00:03<00:00,  8.77it/s]\nTotal progress: 680it [07:19,  8.77it/s]\u001b[A\n 94%|█████████▍| 33/35 [00:03<00:00,  8.80it/s]\nTotal progress: 681it [07:19,  8.80it/s]\u001b[A\n 97%|█████████▋| 34/35 [00:03<00:00,  8.86it/s]\n100%|██████████| 35/35 [00:03<00:00,  8.80it/s]\nTotal progress: 682it [07:19,  8.86it/s]\u001b[A",
  "metrics": {
    "predict_time": 4.94606,
    "total_time": 4.878354
  },
  "output": [
    "https://replicate.delivery/pbxt/2IWR4absHC4bKBcDHZyjOEftyFsaUCWfad5uSxUeCzUbPOjjA/1698217964_0.png"
  ],
  "started_at": "2023-10-25T07:12:40.739960Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/xrs4xd3b5rmdzszfricd2b3gtm",
    "cancel": "https://api.replicate.com/v1/predictions/xrs4xd3b5rmdzszfricd2b3gtm/cancel"
  },
  "version": "b3090867978df33330d841904d50b83ebff7dcda040b5f6ab22538bd75e7f3dd"
}

Generated in

5.0 seconds

Tweak itReport

Checking model and vae...
Previous model: xxmix.safetensors
Model is already up-to-date.
Previous vae: consistency.pt
VAE is already up-to-date.
Done, time used: 4.8160552978515625e-05 seconds.
  0%|          | 0/35 [00:00<?, ?it/s]
Total progress: 648it [07:16,  3.85s/it]
  3%|▎         | 1/35 [00:00<00:03,  8.54it/s]
Total progress: 649it [07:16,  2.73s/it]
  6%|▌         | 2/35 [00:00<00:03,  8.56it/s]
Total progress: 650it [07:16,  1.95s/it]
  9%|▊         | 3/35 [00:00<00:03,  8.57it/s]
Total progress: 651it [07:16,  1.40s/it]
 11%|█▏        | 4/35 [00:00<00:03,  8.59it/s]
Total progress: 652it [07:16,  1.01s/it]
 14%|█▍        | 5/35 [00:00<00:03,  8.60it/s]
Total progress: 653it [07:16,  1.34it/s]
 17%|█▋        | 6/35 [00:00<00:03,  8.59it/s]
Total progress: 654it [07:16,  1.80it/s]
 20%|██        | 7/35 [00:00<00:03,  8.59it/s]
Total progress: 655it [07:16,  2.36it/s]
 23%|██▎       | 8/35 [00:00<00:03,  8.59it/s]
Total progress: 656it [07:16,  3.01it/s]
 26%|██▌       | 9/35 [00:01<00:03,  8.59it/s]
Total progress: 657it [07:17,  3.74it/s]
 29%|██▊       | 10/35 [00:01<00:02,  8.59it/s]
Total progress: 658it [07:17,  4.51it/s]
 31%|███▏      | 11/35 [00:01<00:02,  8.60it/s]
Total progress: 659it [07:17,  5.26it/s]
 34%|███▍      | 12/35 [00:01<00:02,  8.62it/s]
Total progress: 660it [07:17,  5.96it/s]
 37%|███▋      | 13/35 [00:01<00:02,  8.60it/s]
Total progress: 661it [07:17,  6.56it/s]
 40%|████      | 14/35 [00:01<00:02,  8.62it/s]
Total progress: 662it [07:17,  7.07it/s]
 43%|████▎     | 15/35 [00:01<00:02,  8.61it/s]
Total progress: 663it [07:17,  7.47it/s]
 46%|████▌     | 16/35 [00:01<00:02,  8.63it/s]
Total progress: 664it [07:17,  7.79it/s]
 49%|████▊     | 17/35 [00:01<00:02,  8.64it/s]
Total progress: 665it [07:17,  8.04it/s]
 51%|█████▏    | 18/35 [00:02<00:01,  8.64it/s]
Total progress: 666it [07:18,  8.21it/s]
 54%|█████▍    | 19/35 [00:02<00:01,  8.61it/s]
Total progress: 667it [07:18,  8.30it/s]
 57%|█████▋    | 20/35 [00:02<00:01,  8.61it/s]
Total progress: 668it [07:18,  8.39it/s]
 60%|██████    | 21/35 [00:02<00:01,  8.63it/s]
Total progress: 669it [07:18,  8.48it/s]
 63%|██████▎   | 22/35 [00:02<00:01,  8.67it/s]
Total progress: 670it [07:18,  8.56it/s]
 66%|██████▌   | 23/35 [00:02<00:01,  8.65it/s]
Total progress: 671it [07:18,  8.58it/s]
 69%|██████▊   | 24/35 [00:02<00:01,  8.68it/s]
Total progress: 672it [07:18,  8.63it/s]
 71%|███████▏  | 25/35 [00:02<00:01,  8.71it/s]
Total progress: 673it [07:18,  8.67it/s]
 74%|███████▍  | 26/35 [00:03<00:01,  8.69it/s]
Total progress: 674it [07:19,  8.66it/s]
 77%|███████▋  | 27/35 [00:03<00:00,  8.72it/s]
Total progress: 675it [07:19,  8.70it/s]
 80%|████████  | 28/35 [00:03<00:00,  8.74it/s]
Total progress: 676it [07:19,  8.73it/s]
 83%|████████▎ | 29/35 [00:03<00:00,  8.72it/s]
Total progress: 677it [07:19,  8.71it/s]
 86%|████████▌ | 30/35 [00:03<00:00,  8.74it/s]
Total progress: 678it [07:19,  8.71it/s]
 89%|████████▊ | 31/35 [00:03<00:00,  8.71it/s]
Total progress: 679it [07:19,  8.71it/s]
 91%|█████████▏| 32/35 [00:03<00:00,  8.77it/s]
Total progress: 680it [07:19,  8.77it/s]
 94%|█████████▍| 33/35 [00:03<00:00,  8.80it/s]
Total progress: 681it [07:19,  8.80it/s]
 97%|█████████▋| 34/35 [00:03<00:00,  8.86it/s]
100%|██████████| 35/35 [00:03<00:00,  8.80it/s]
Total progress: 682it [07:19,  8.86it/s]

This output was created using a different version of the model, dazaleas/sd15-cog:b3090867.

Examples

View more examples

Run time and cost

This model costs approximately $0.038 to run on Replicate, or 26 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 A100 (80GB) GPU hardware. Predictions typically complete within 28 seconds. The predict time for this model varies significantly based on the inputs.

Readme

This model doesn't have a readme.