fofr/ays-text-to-image – Run with an API on Replicate

Input

prompt

string

Shift + Return to add a new line

Default: "a photo of an astronaut riding a unicorn"

negative_prompt

string

Shift + Return to add a new line

The negative prompt to guide image generation.

Default: ""

checkpoint

string

The SDXL model to use for generation

Default: "albedobaseXL_v21.safetensors"

width

integer

Default: 1024

height

integer

Default: 1024

num_outputs

integer

(minimum: 1, maximum: 10)

Number of outputs

Default: 1

sampler_name

string

An enumeration.

Default: "euler"

guidance_scale

number

(minimum: 0, maximum: 30)

Scale for classifier-free guidance

Default: 7.5

steps

integer

(minimum: 10, maximum: 100)

Number of diffusion steps. (A minimum of 10 with AYS)

Default: 10

seed

integer

output_format

string

Format of the output images

Default: "webp"

output_quality

integer

(minimum: 0, maximum: 100)

Quality of the output images, from 0 to 100. 100 is best quality, 0 is lowest quality.

Default: 80

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

npx create-replicate --model=fofr/ays-text-to-image

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 fofr/ays-text-to-image using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "fofr/ays-text-to-image:a004c3ac8f62ac95a90b5a0c264beb47b66a6d1f8141b76fb27cd90e9a8bfe8e",
  {
    input: {
      steps: 10,
      width: 1156,
      height: 768,
      prompt: "a beautiful portrait photo of a cat",
      checkpoint: "ProteusV0.4.safetensors",
      num_outputs: 1,
      sampler_name: "euler",
      output_format: "webp",
      guidance_scale: 7.5,
      output_quality: 80,
      negative_prompt: ""
    }
  }
);
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 fofr/ays-text-to-image using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "fofr/ays-text-to-image:a004c3ac8f62ac95a90b5a0c264beb47b66a6d1f8141b76fb27cd90e9a8bfe8e",
    input={
        "steps": 10,
        "width": 1156,
        "height": 768,
        "prompt": "a beautiful portrait photo of a cat",
        "checkpoint": "ProteusV0.4.safetensors",
        "num_outputs": 1,
        "sampler_name": "euler",
        "output_format": "webp",
        "guidance_scale": 7.5,
        "output_quality": 80,
        "negative_prompt": ""
    }
)
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 fofr/ays-text-to-image 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": "a004c3ac8f62ac95a90b5a0c264beb47b66a6d1f8141b76fb27cd90e9a8bfe8e",
    "input": {
      "steps": 10,
      "width": 1156,
      "height": 768,
      "prompt": "a beautiful portrait photo of a cat",
      "checkpoint": "ProteusV0.4.safetensors",
      "num_outputs": 1,
      "sampler_name": "euler",
      "output_format": "webp",
      "guidance_scale": 7.5,
      "output_quality": 80,
      "negative_prompt": ""
    }
  }' \
  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/fofr/ays-text-to-image@sha256:a004c3ac8f62ac95a90b5a0c264beb47b66a6d1f8141b76fb27cd90e9a8bfe8e \
  -i 'steps=10' \
  -i 'width=1156' \
  -i 'height=768' \
  -i 'prompt="a beautiful portrait photo of a cat"' \
  -i 'checkpoint="ProteusV0.4.safetensors"' \
  -i 'num_outputs=1' \
  -i 'sampler_name="euler"' \
  -i 'output_format="webp"' \
  -i 'guidance_scale=7.5' \
  -i 'output_quality=80' \
  -i 'negative_prompt=""'

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/fofr/ays-text-to-image@sha256:a004c3ac8f62ac95a90b5a0c264beb47b66a6d1f8141b76fb27cd90e9a8bfe8e
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "steps": 10,
      "width": 1156,
      "height": 768,
      "prompt": "a beautiful portrait photo of a cat",
      "checkpoint": "ProteusV0.4.safetensors",
      "num_outputs": 1,
      "sampler_name": "euler",
      "output_format": "webp",
      "guidance_scale": 7.5,
      "output_quality": 80,
      "negative_prompt": ""
    }
  }' \
  http://localhost:5000/predictions

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

Output

{
  "completed_at": "2024-11-28T11:06:18.936209Z",
  "created_at": "2024-11-28T11:06:17.686000Z",
  "data_removed": false,
  "error": null,
  "id": "50t317j6tsrm80cke9sv9hen68",
  "input": {
    "steps": 10,
    "width": 1156,
    "height": 768,
    "prompt": "a beautiful portrait photo of a cat",
    "checkpoint": "ProteusV0.4.safetensors",
    "num_outputs": 1,
    "sampler_name": "euler",
    "output_format": "webp",
    "guidance_scale": 7.5,
    "output_quality": 80,
    "negative_prompt": ""
  },
  "logs": "Random seed set to: 3470234499\nChecking inputs\n====================================\nChecking weights\n✅ ProteusV0.4.safetensors\n====================================\nRunning workflow\ngot prompt\nExecuting node 21, title: SamplerCustom, class type: SamplerCustom\n  0%|          | 0/10 [00:00<?, ?it/s]\n 20%|██        | 2/10 [00:00<00:00, 16.72it/s]\n 40%|████      | 4/10 [00:00<00:00, 13.17it/s]\n 60%|██████    | 6/10 [00:00<00:00, 12.32it/s]\n 80%|████████  | 8/10 [00:00<00:00, 11.94it/s]\n100%|██████████| 10/10 [00:00<00:00, 11.76it/s]\n100%|██████████| 10/10 [00:00<00:00, 12.21it/s]\nExecuting node 8, title: VAE Decode, class type: VAEDecode\nExecuting node 9, title: Save Image, class type: SaveImage\nPrompt executed in 1.14 seconds\noutputs:  {'9': {'images': [{'filename': 'ComfyUI_00001_.png', 'subfolder': '', 'type': 'output'}]}}\n====================================\nContents of /tmp/outputs:\nComfyUI_00001_.png",
  "metrics": {
    "predict_time": 1.242096476,
    "total_time": 1.250209
  },
  "output": [
    "https://replicate.delivery/xezq/7B9xH1LJjI59N9FtDkG40mHM3sSB3b5MRxwOV7nCbfPVBw6JA/ComfyUI_00001_.webp"
  ],
  "started_at": "2024-11-28T11:06:17.694113Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-loykbbdz3uq6jpzs7p2mgf6joe6dssl2y3hesyhgle6hgchcubtq",
    "get": "https://api.replicate.com/v1/predictions/50t317j6tsrm80cke9sv9hen68",
    "cancel": "https://api.replicate.com/v1/predictions/50t317j6tsrm80cke9sv9hen68/cancel"
  },
  "version": "a004c3ac8f62ac95a90b5a0c264beb47b66a6d1f8141b76fb27cd90e9a8bfe8e"
}

Generated in

1.3 seconds

Tweak it ShareReport

Run time and cost

This model costs approximately $0.041 to run on Replicate, or 24 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 43 seconds. The predict time for this model varies significantly based on the inputs.