brewwh/cog-a1111-ui – Run with an API on Replicate

brewwh / cog-a1111-ui

A collection of anime stable diffusion models with VAEs and LORAs.

Cold

Public
3.7K runs
A100 (80GB)

Run with an API

Playground API Examples README Versions

Input

model

string

The model to use

Default: "xxmix.safetensors"

vae

string

The vae to use

Default: "None"

prompt

string

Shift + Return to add a new line

masterpiece, illustration, portrait of a beautiful young womanmasterpiece, illustration, portrait of a beautiful young woman

The prompt

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

negative_prompt

string

Shift + Return to add a new line

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: 15

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: 0.38

hr_second_pass_steps

integer

(minimum: 0, maximum: 30)

The steps when performing second pass

Default: 8

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=brewwh/cog-a1111-ui

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 brewwh/cog-a1111-ui using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "brewwh/cog-a1111-ui:15680039e93e5d25a863e8a5a4f82dcc5398011c321ca86362a20f71b09fb7ff",
  {
    input: {
      vae: "ema_original.pt",
      seed: -1,
      model: "anythingv.safetensors",
      steps: 15,
      width: 768,
      height: 768,
      prompt: "masterpiece, illustration, portrait of a beautiful young woman",
      hr_scale: 2,
      cfg_scale: 7,
      enable_hr: true,
      batch_size: 4,
      hr_upscaler: "R-ESRGAN 4x+ Anime6B",
      sampler_name: "DPM++ 2M Karras",
      negative_prompt: "low quality, bad quality, worst quality",
      denoising_strength: 0.38,
      hr_second_pass_steps: 8
    }
  }
);
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 brewwh/cog-a1111-ui using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "brewwh/cog-a1111-ui:15680039e93e5d25a863e8a5a4f82dcc5398011c321ca86362a20f71b09fb7ff",
    input={
        "vae": "ema_original.pt",
        "seed": -1,
        "model": "anythingv.safetensors",
        "steps": 15,
        "width": 768,
        "height": 768,
        "prompt": "masterpiece, illustration, portrait of a beautiful young woman",
        "hr_scale": 2,
        "cfg_scale": 7,
        "enable_hr": True,
        "batch_size": 4,
        "hr_upscaler": "R-ESRGAN 4x+ Anime6B",
        "sampler_name": "DPM++ 2M Karras",
        "negative_prompt": "low quality, bad quality, worst quality",
        "denoising_strength": 0.38,
        "hr_second_pass_steps": 8
    }
)
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 brewwh/cog-a1111-ui 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": "15680039e93e5d25a863e8a5a4f82dcc5398011c321ca86362a20f71b09fb7ff",
    "input": {
      "vae": "ema_original.pt",
      "seed": -1,
      "model": "anythingv.safetensors",
      "steps": 15,
      "width": 768,
      "height": 768,
      "prompt": "masterpiece, illustration, portrait of a beautiful young woman",
      "hr_scale": 2,
      "cfg_scale": 7,
      "enable_hr": true,
      "batch_size": 4,
      "hr_upscaler": "R-ESRGAN 4x+ Anime6B",
      "sampler_name": "DPM++ 2M Karras",
      "negative_prompt": "low quality, bad quality, worst quality",
      "denoising_strength": 0.38,
      "hr_second_pass_steps": 8
    }
  }' \
  https://api.replicate.com/v1/predictions

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

You can run this model locally using Cog. First, install Cog:

brew install cog

If you don’t have Homebrew, there are other installation options available.

Run this to download the model and run it in your local environment:

cog predict r8.im/brewwh/cog-a1111-ui@sha256:15680039e93e5d25a863e8a5a4f82dcc5398011c321ca86362a20f71b09fb7ff \
  -i 'vae="ema_original.pt"' \
  -i 'seed=-1' \
  -i 'model="anythingv.safetensors"' \
  -i 'steps=15' \
  -i 'width=768' \
  -i 'height=768' \
  -i 'prompt="masterpiece, illustration, portrait of a beautiful young woman"' \
  -i 'hr_scale=2' \
  -i 'cfg_scale=7' \
  -i 'enable_hr=true' \
  -i 'batch_size=4' \
  -i 'hr_upscaler="R-ESRGAN 4x+ Anime6B"' \
  -i 'sampler_name="DPM++ 2M Karras"' \
  -i 'negative_prompt="low quality, bad quality, worst quality"' \
  -i 'denoising_strength=0.38' \
  -i 'hr_second_pass_steps=8'

To learn more, take a look at the Cog documentation.

Run this to download the model and run it in your local environment:

docker run -d -p 5000:5000 --gpus=all r8.im/brewwh/cog-a1111-ui@sha256:15680039e93e5d25a863e8a5a4f82dcc5398011c321ca86362a20f71b09fb7ff
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "vae": "ema_original.pt",
      "seed": -1,
      "model": "anythingv.safetensors",
      "steps": 15,
      "width": 768,
      "height": 768,
      "prompt": "masterpiece, illustration, portrait of a beautiful young woman",
      "hr_scale": 2,
      "cfg_scale": 7,
      "enable_hr": true,
      "batch_size": 4,
      "hr_upscaler": "R-ESRGAN 4x+ Anime6B",
      "sampler_name": "DPM++ 2M Karras",
      "negative_prompt": "low quality, bad quality, worst quality",
      "denoising_strength": 0.38,
      "hr_second_pass_steps": 8
    }
  }' \
  http://localhost:5000/predictions

To learn more, take a look at the Cog documentation.

Output

{
  "completed_at": "2023-12-28T02:23:39.851271Z",
  "created_at": "2023-12-28T02:18:14.619446Z",
  "data_removed": false,
  "error": null,
  "id": "4dn2julbjkhmib5trn755xiz4m",
  "input": {
    "vae": "ema_original.pt",
    "seed": -1,
    "model": "anythingv.safetensors",
    "steps": 15,
    "width": 768,
    "height": 768,
    "prompt": "masterpiece, illustration, portrait of a beautiful young woman",
    "hr_scale": 2,
    "cfg_scale": 7,
    "enable_hr": true,
    "batch_size": 4,
    "hr_upscaler": "R-ESRGAN 4x+ Anime6B",
    "sampler_name": "DPM++ 2M Karras",
    "negative_prompt": "low quality, bad quality, worst quality",
    "denoising_strength": 0.38,
    "hr_second_pass_steps": 8
  },
  "logs": "Checking model and vae...\nPrevious model: xxmix.safetensors\nUpdating the model...\nLoading weights [1cb9f9c58a] from cache\nLoading VAE weights specified in settings: cached ema_original.pt\nApplying xformers cross attention optimization.\nWeights loaded in 0.6s (apply weights to model: 0.2s, move model to device: 0.3s).\nPrevious vae: ema_original.pt\nVAE is already up-to-date.\nDone, time used: 1.7655346393585205 seconds.\nTotal progress: 0it [00:00, ?it/s]\u001b[A\n  0%|          | 0/15 [00:00<?, ?it/s]\nTotal progress: 1it [00:00,  1.24it/s]\u001b[A\n  7%|▋         | 1/15 [00:00<00:03,  4.21it/s]\nTotal progress: 2it [00:00,  2.32it/s]\u001b[A\n 13%|█▎        | 2/15 [00:00<00:02,  5.06it/s]\nTotal progress: 3it [00:01,  3.22it/s]\u001b[A\n 20%|██        | 3/15 [00:00<00:02,  5.42it/s]\nTotal progress: 4it [00:01,  3.92it/s]\u001b[A\n 27%|██▋       | 4/15 [00:00<00:01,  5.60it/s]\nTotal progress: 5it [00:01,  4.46it/s]\u001b[A\n 33%|███▎      | 5/15 [00:00<00:01,  5.70it/s]\nTotal progress: 6it [00:01,  4.86it/s]\u001b[A\n 40%|████      | 6/15 [00:01<00:01,  5.77it/s]\nTotal progress: 7it [00:01,  5.16it/s]\u001b[A\n 47%|████▋     | 7/15 [00:01<00:01,  5.81it/s]\nTotal progress: 8it [00:01,  5.37it/s]\u001b[A\n 53%|█████▎    | 8/15 [00:01<00:01,  5.84it/s]\nTotal progress: 9it [00:02,  5.52it/s]\u001b[A\n 60%|██████    | 9/15 [00:01<00:01,  5.85it/s]\nTotal progress: 10it [00:02,  5.63it/s]\u001b[A\n 67%|██████▋   | 10/15 [00:01<00:00,  5.86it/s]\nTotal progress: 11it [00:02,  5.71it/s]\u001b[A\n 73%|███████▎  | 11/15 [00:01<00:00,  5.87it/s]\nTotal progress: 12it [00:02,  5.76it/s]\u001b[A\n 80%|████████  | 12/15 [00:02<00:00,  5.88it/s]\nTotal progress: 13it [00:02,  5.81it/s]\u001b[A\n 87%|████████▋ | 13/15 [00:02<00:00,  5.89it/s]\nTotal progress: 14it [00:03,  5.84it/s]\u001b[A\n 93%|█████████▎| 14/15 [00:02<00:00,  5.89it/s]\n100%|██████████| 15/15 [00:02<00:00,  5.89it/s]\n100%|██████████| 15/15 [00:02<00:00,  5.74it/s]\nTotal progress: 15it [00:03,  5.85it/s]\u001b[ATile 1/25\nTile 2/25\nTile 3/25\nTile 4/25\nTile 5/25\nTile 6/25\nTile 7/25\nTile 8/25\nTile 9/25\nTile 10/25\nTile 11/25\nTile 12/25\nTile 13/25\nTile 14/25\nTile 15/25\nTile 16/25\nTile 17/25\nTile 18/25\nTile 19/25\nTile 20/25\nTile 21/25\nTile 22/25\nTile 23/25\nTile 24/25\nTile 25/25\nTile 1/25\nTile 2/25\nTile 3/25\nTile 4/25\nTile 5/25\nTile 6/25\nTile 7/25\nTile 8/25\nTile 9/25\nTile 10/25\nTile 11/25\nTile 12/25\nTile 13/25\nTile 14/25\nTile 15/25\nTile 16/25\nTile 17/25\nTile 18/25\nTile 19/25\nTile 20/25\nTile 21/25\nTile 22/25\nTile 23/25\nTile 24/25\nTile 25/25\nTile 1/25\nTile 2/25\nTile 3/25\nTile 4/25\nTile 5/25\nTile 6/25\nTile 7/25\nTile 8/25\nTile 9/25\nTile 10/25\nTile 11/25\nTile 12/25\nTile 13/25\nTile 14/25\nTile 15/25\nTile 16/25\nTile 17/25\nTile 18/25\nTile 19/25\nTile 20/25\nTile 21/25\nTile 22/25\nTile 23/25\nTile 24/25\nTile 25/25\nTile 1/25\nTile 2/25\nTile 3/25\nTile 4/25\nTile 5/25\nTile 6/25\nTile 7/25\nTile 8/25\nTile 9/25\nTile 10/25\nTile 11/25\nTile 12/25\nTile 13/25\nTile 14/25\nTile 15/25\nTile 16/25\nTile 17/25\nTile 18/25\nTile 19/25\nTile 20/25\nTile 21/25\nTile 22/25\nTile 23/25\nTile 24/25\nTile 25/25\n  0%|          | 0/8 [00:00<?, ?it/s]\nTotal progress: 16it [00:09,  1.93s/it]\u001b[A\n 12%|█▎        | 1/8 [00:01<00:08,  1.16s/it]\nTotal progress: 17it [00:10,  1.70s/it]\u001b[A\n 25%|██▌       | 2/8 [00:02<00:06,  1.15s/it]\nTotal progress: 18it [00:11,  1.53s/it]\u001b[A\n 38%|███▊      | 3/8 [00:03<00:05,  1.15s/it]\nTotal progress: 19it [00:12,  1.42s/it]\u001b[A\n 50%|█████     | 4/8 [00:04<00:04,  1.15s/it]\nTotal progress: 20it [00:13,  1.34s/it]\u001b[A\n 62%|██████▎   | 5/8 [00:05<00:03,  1.15s/it]\nTotal progress: 21it [00:14,  1.29s/it]\u001b[A\n 75%|███████▌  | 6/8 [00:06<00:02,  1.16s/it]\nTotal progress: 22it [00:16,  1.25s/it]\u001b[A\n 88%|████████▊ | 7/8 [00:08<00:01,  1.16s/it]\n100%|██████████| 8/8 [00:09<00:00,  1.16s/it]\n100%|██████████| 8/8 [00:09<00:00,  1.16s/it]\nTotal progress: 23it [00:17,  1.22s/it]\u001b[A",
  "metrics": {
    "predict_time": 27.555119,
    "total_time": 325.231825
  },
  "output": [
    "https://replicate.delivery/pbxt/iFn9MIgCESagBZRGdFVgf12YzYfcF99VUs6cUkf7XghSxRNkA/1703730213_0.png",
    "https://replicate.delivery/pbxt/FkWNrmi5l4ZAJFTSRkUHMhAqSW4FKSQtE3NF6BeJLdaVcUDJA/1703730213_1.png",
    "https://replicate.delivery/pbxt/i8I5us1AlQ69PFT7gRi5eWeD21386C0vxpPEy8ooe9bVxRNkA/1703730213_2.png",
    "https://replicate.delivery/pbxt/q0cLoUVqGiLJIpYv1NuLhwPCoo97Y9GvkVcuqK7uZHyKOqhE/1703730213_3.png"
  ],
  "started_at": "2023-12-28T02:23:12.296152Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/4dn2julbjkhmib5trn755xiz4m",
    "cancel": "https://api.replicate.com/v1/predictions/4dn2julbjkhmib5trn755xiz4m/cancel"
  },
  "version": "181fdde502e52ce3df9c8e6626b549019e4d81a13971a5ea93874898ba4b3e32"
}

Generated in

27.6 seconds

Tweak itReport

Checking model and vae...
Previous model: xxmix.safetensors
Updating the model...
Loading weights [1cb9f9c58a] from cache
Loading VAE weights specified in settings: cached ema_original.pt
Applying xformers cross attention optimization.
Weights loaded in 0.6s (apply weights to model: 0.2s, move model to device: 0.3s).
Previous vae: ema_original.pt
VAE is already up-to-date.
Done, time used: 1.7655346393585205 seconds.
Total progress: 0it [00:00, ?it/s]
  0%|          | 0/15 [00:00<?, ?it/s]
Total progress: 1it [00:00,  1.24it/s]
  7%|▋         | 1/15 [00:00<00:03,  4.21it/s]
Total progress: 2it [00:00,  2.32it/s]
 13%|█▎        | 2/15 [00:00<00:02,  5.06it/s]
Total progress: 3it [00:01,  3.22it/s]
 20%|██        | 3/15 [00:00<00:02,  5.42it/s]
Total progress: 4it [00:01,  3.92it/s]
 27%|██▋       | 4/15 [00:00<00:01,  5.60it/s]
Total progress: 5it [00:01,  4.46it/s]
 33%|███▎      | 5/15 [00:00<00:01,  5.70it/s]
Total progress: 6it [00:01,  4.86it/s]
 40%|████      | 6/15 [00:01<00:01,  5.77it/s]
Total progress: 7it [00:01,  5.16it/s]
 47%|████▋     | 7/15 [00:01<00:01,  5.81it/s]
Total progress: 8it [00:01,  5.37it/s]
 53%|█████▎    | 8/15 [00:01<00:01,  5.84it/s]
Total progress: 9it [00:02,  5.52it/s]
 60%|██████    | 9/15 [00:01<00:01,  5.85it/s]
Total progress: 10it [00:02,  5.63it/s]
 67%|██████▋   | 10/15 [00:01<00:00,  5.86it/s]
Total progress: 11it [00:02,  5.71it/s]
 73%|███████▎  | 11/15 [00:01<00:00,  5.87it/s]
Total progress: 12it [00:02,  5.76it/s]
 80%|████████  | 12/15 [00:02<00:00,  5.88it/s]
Total progress: 13it [00:02,  5.81it/s]
 87%|████████▋ | 13/15 [00:02<00:00,  5.89it/s]
Total progress: 14it [00:03,  5.84it/s]
 93%|█████████▎| 14/15 [00:02<00:00,  5.89it/s]
100%|██████████| 15/15 [00:02<00:00,  5.89it/s]
100%|██████████| 15/15 [00:02<00:00,  5.74it/s]
Total progress: 15it [00:03,  5.85it/s]Tile 1/25
Tile 2/25
Tile 3/25
Tile 4/25
Tile 5/25
Tile 6/25
Tile 7/25
Tile 8/25
Tile 9/25
Tile 10/25
Tile 11/25
Tile 12/25
Tile 13/25
Tile 14/25
Tile 15/25
Tile 16/25
Tile 17/25
Tile 18/25
Tile 19/25
Tile 20/25
Tile 21/25
Tile 22/25
Tile 23/25
Tile 24/25
Tile 25/25
Tile 1/25
Tile 2/25
Tile 3/25
Tile 4/25
Tile 5/25
Tile 6/25
Tile 7/25
Tile 8/25
Tile 9/25
Tile 10/25
Tile 11/25
Tile 12/25
Tile 13/25
Tile 14/25
Tile 15/25
Tile 16/25
Tile 17/25
Tile 18/25
Tile 19/25
Tile 20/25
Tile 21/25
Tile 22/25
Tile 23/25
Tile 24/25
Tile 25/25
Tile 1/25
Tile 2/25
Tile 3/25
Tile 4/25
Tile 5/25
Tile 6/25
Tile 7/25
Tile 8/25
Tile 9/25
Tile 10/25
Tile 11/25
Tile 12/25
Tile 13/25
Tile 14/25
Tile 15/25
Tile 16/25
Tile 17/25
Tile 18/25
Tile 19/25
Tile 20/25
Tile 21/25
Tile 22/25
Tile 23/25
Tile 24/25
Tile 25/25
Tile 1/25
Tile 2/25
Tile 3/25
Tile 4/25
Tile 5/25
Tile 6/25
Tile 7/25
Tile 8/25
Tile 9/25
Tile 10/25
Tile 11/25
Tile 12/25
Tile 13/25
Tile 14/25
Tile 15/25
Tile 16/25
Tile 17/25
Tile 18/25
Tile 19/25
Tile 20/25
Tile 21/25
Tile 22/25
Tile 23/25
Tile 24/25
Tile 25/25
  0%|          | 0/8 [00:00<?, ?it/s]
Total progress: 16it [00:09,  1.93s/it]
 12%|█▎        | 1/8 [00:01<00:08,  1.16s/it]
Total progress: 17it [00:10,  1.70s/it]
 25%|██▌       | 2/8 [00:02<00:06,  1.15s/it]
Total progress: 18it [00:11,  1.53s/it]
 38%|███▊      | 3/8 [00:03<00:05,  1.15s/it]
Total progress: 19it [00:12,  1.42s/it]
 50%|█████     | 4/8 [00:04<00:04,  1.15s/it]
Total progress: 20it [00:13,  1.34s/it]
 62%|██████▎   | 5/8 [00:05<00:03,  1.15s/it]
Total progress: 21it [00:14,  1.29s/it]
 75%|███████▌  | 6/8 [00:06<00:02,  1.16s/it]
Total progress: 22it [00:16,  1.25s/it]
 88%|████████▊ | 7/8 [00:08<00:01,  1.16s/it]
100%|██████████| 8/8 [00:09<00:00,  1.16s/it]
100%|██████████| 8/8 [00:09<00:00,  1.16s/it]
Total progress: 23it [00:17,  1.22s/it]

This example was created by a different version, brewwh/cog-a1111-ui:181fdde5.

Examples

View more examples

Run time and cost

This model runs on Nvidia A100 (80GB) GPU hardware. We don't yet have enough runs of this model to provide performance information.

Readme

Usage: - Similar to how you’d use Automatic1111.

List of LoRAs:

add_detail.safetensors noise_offset.safetensors more_details.safetensors anxiang.safetensors

Usage: <lora:add_detail:1.0>

List of Embeddings:

bad-artist.pt bad-hands-5.pt EasyNegative.safetensors negative_hand-neg.pt ng_deepnegative_v1_75t.pt verybadimagenegative_v1.3.pt

Usage: bad-artist in negative.