mcai/deliberate-v2 – Run with an API on Replicate

mcai / deliberate-v2

Generate a new image given any input text with Deliberate v2

Cold

Public
650.2K runs
A100 (80GB)

Run with an API

Playground API Examples README Versions

Input

prompt

string

Shift + Return to add a new line

Digital photo of car on the empty parking slot, (((blue and white))) 1956 Renault Dauphine , heavy rain, on aesthetic light glow in the cloudy sky, neon sign in the dark night, winter night, falling snow, foggy night , strong rim lighting, soft contrasted, thunder lightning in the stormy sky, 8k uhd, dlsr, Oled, dark lighting, high quality, film grain, Fujifilm XT3, highly detailed, excellent composition, cinematic concept art, dramatic lighting, trending on artstation by Kaiwan Shaban, James O'Brien, Vadim Ignatiev,Digital photo of car on the empty parking slot, (((blue and white))) 1956 Renault Dauphine , heavy rain, on aesthetic light glow in the cloudy sky, neon sign in the dark night, winter night, falling snow, foggy night , strong rim lighting, soft contrasted, thunder lightning in the stormy sky, 8k uhd, dlsr, Oled, dark lighting, high quality, film grain, Fujifilm XT3, highly detailed, excellent composition, cinematic concept art, dramatic lighting, trending on artstation by Kaiwan Shaban, James O'Brien, Vadim Ignatiev,

Input prompt

Default: ""

negative_prompt

string

Shift + Return to add a new line

disfigured, kitsch, ugly, oversaturated, greain, low-res, Deformed, blurry, bad anatomy, disfigured, poorly drawn face, mutation, mutated, extra limb, ugly, poorly drawn hands, missing limb, blurry, floating limbs, disconnected limbs, malformed hands, blur, out of focus, long neck, long body, ugly, disgusting, poorly drawn, childish, mutilated, mangled, old, surreal, calligraphy, sign, writing, watermark, text, body out of frame, extra legs, extra arms, extra feet, out of frame, poorly drawn feet, cross-eye, blurry, bad anatomydisfigured, kitsch, ugly, oversaturated, greain, low-res, Deformed, blurry, bad anatomy, disfigured, poorly drawn face, mutation, mutated, extra limb, ugly, poorly drawn hands, missing limb, blurry, floating limbs, disconnected limbs, malformed hands, blur, out of focus, long neck, long body, ugly, disgusting, poorly drawn, childish, mutilated, mangled, old, surreal, calligraphy, sign, writing, watermark, text, body out of frame, extra legs, extra arms, extra feet, out of frame, poorly drawn feet, cross-eye, blurry, bad anatomy

Specify things to not see in the output

Default: "disfigured, kitsch, ugly, oversaturated, greain, low-res, deformed, blurry, bad anatomy, poorly drawn face, mutation, mutated, extra limb, poorly drawn hands, missing limb, floating limbs, disconnected limbs, malformed hands, blur, out of focus, long neck, long body, disgusting, poorly drawn, childish, mutilated, mangled, old, surreal, calligraphy, sign, writing, watermark, text, body out of frame, extra legs, extra arms, extra feet, out of frame, poorly drawn feet, cross-eye"

width

integer

Width of output image. Maximum size is 1024x768 or 768x1024 because of memory limits

Default: 512

height

integer

Height of output image. Maximum size is 1024x768 or 768x1024 because of memory limits

Default: 768

num_outputs

integer

(minimum: 1, maximum: 4)

Number of images to output.

Default: 1

num_inference_steps

integer

(minimum: 1, maximum: 500)

Number of denoising steps

Default: 30

guidance_scale

number

(minimum: 1, maximum: 20)

Scale for classifier-free guidance

Default: 7.5

scheduler

string

Choose a scheduler.

Default: "EulerAncestralDiscrete"

seed

integer

Random seed. Leave blank to randomize the seed

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

npx create-replicate --model=mcai/deliberate-v2

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 mcai/deliberate-v2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "mcai/deliberate-v2:8e6663822bbbc982648e3c34214cf42d29fe421b2620cc33d8bda767fc57fe5a",
  {
    input: {
      width: 512,
      height: 768,
      prompt: "Digital photo of car on the empty parking slot, (((blue and white))) 1956 Renault Dauphine , heavy rain, on aesthetic light glow in the cloudy sky, neon sign in the dark night, winter night, falling snow, foggy night , strong rim lighting, soft contrasted, thunder lightning in the stormy sky, 8k uhd, dlsr, Oled, dark lighting, high quality, film grain, Fujifilm XT3, highly detailed, excellent composition, cinematic concept art, dramatic lighting, trending on artstation by Kaiwan Shaban, James O'Brien, Vadim Ignatiev,",
      scheduler: "EulerAncestralDiscrete",
      num_outputs: 1,
      guidance_scale: 7.5,
      negative_prompt: "disfigured, kitsch, ugly, oversaturated, greain, low-res, Deformed, blurry, bad anatomy, disfigured, poorly drawn face, mutation, mutated, extra limb, ugly, poorly drawn hands, missing limb, blurry, floating limbs, disconnected limbs, malformed hands, blur, out of focus, long neck, long body, ugly, disgusting, poorly drawn, childish, mutilated, mangled, old, surreal, calligraphy, sign, writing, watermark, text, body out of frame, extra legs, extra arms, extra feet, out of frame, poorly drawn feet, cross-eye, blurry, bad anatomy",
      num_inference_steps: 30
    }
  }
);
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 mcai/deliberate-v2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "mcai/deliberate-v2:8e6663822bbbc982648e3c34214cf42d29fe421b2620cc33d8bda767fc57fe5a",
    input={
        "width": 512,
        "height": 768,
        "prompt": "Digital photo of car on the empty parking slot, (((blue and white))) 1956 Renault Dauphine , heavy rain, on aesthetic light glow in the cloudy sky, neon sign in the dark night, winter night, falling snow, foggy night , strong rim lighting, soft contrasted, thunder lightning in the stormy sky, 8k uhd, dlsr, Oled, dark lighting, high quality, film grain, Fujifilm XT3, highly detailed, excellent composition, cinematic concept art, dramatic lighting, trending on artstation by Kaiwan Shaban, James O'Brien, Vadim Ignatiev,",
        "scheduler": "EulerAncestralDiscrete",
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "negative_prompt": "disfigured, kitsch, ugly, oversaturated, greain, low-res, Deformed, blurry, bad anatomy, disfigured, poorly drawn face, mutation, mutated, extra limb, ugly, poorly drawn hands, missing limb, blurry, floating limbs, disconnected limbs, malformed hands, blur, out of focus, long neck, long body, ugly, disgusting, poorly drawn, childish, mutilated, mangled, old, surreal, calligraphy, sign, writing, watermark, text, body out of frame, extra legs, extra arms, extra feet, out of frame, poorly drawn feet, cross-eye, blurry, bad anatomy",
        "num_inference_steps": 30
    }
)
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 mcai/deliberate-v2 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": "8e6663822bbbc982648e3c34214cf42d29fe421b2620cc33d8bda767fc57fe5a",
    "input": {
      "width": 512,
      "height": 768,
      "prompt": "Digital photo of car on the empty parking slot, (((blue and white))) 1956 Renault Dauphine , heavy rain, on aesthetic light glow in the cloudy sky, neon sign in the dark night, winter night, falling snow, foggy night , strong rim lighting, soft contrasted, thunder lightning in the stormy sky, 8k uhd, dlsr, Oled, dark lighting, high quality, film grain, Fujifilm XT3, highly detailed, excellent composition, cinematic concept art, dramatic lighting, trending on artstation by Kaiwan Shaban, James O\'Brien, Vadim Ignatiev,",
      "scheduler": "EulerAncestralDiscrete",
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "negative_prompt": "disfigured, kitsch, ugly, oversaturated, greain, low-res, Deformed, blurry, bad anatomy, disfigured, poorly drawn face, mutation, mutated, extra limb, ugly, poorly drawn hands, missing limb, blurry, floating limbs, disconnected limbs, malformed hands, blur, out of focus, long neck, long body, ugly, disgusting, poorly drawn, childish, mutilated, mangled, old, surreal, calligraphy, sign, writing, watermark, text, body out of frame, extra legs, extra arms, extra feet, out of frame, poorly drawn feet, cross-eye, blurry, bad anatomy",
      "num_inference_steps": 30
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2023-05-11T02:35:38.367137Z",
  "created_at": "2023-05-11T02:35:30.372313Z",
  "data_removed": false,
  "error": null,
  "id": "2olwhulca5g6dbklcse2ztqpw4",
  "input": {
    "width": 512,
    "height": 768,
    "prompt": "Digital photo of car on the empty parking slot, (((blue and white))) 1956 Renault Dauphine , heavy rain, on aesthetic light glow in the cloudy sky, neon sign in the dark night, winter night, falling snow, foggy night , strong rim lighting, soft contrasted, thunder lightning in the stormy sky, 8k uhd, dlsr, Oled, dark lighting, high quality, film grain, Fujifilm XT3, highly detailed, excellent composition, cinematic concept art, dramatic lighting, trending on artstation by Kaiwan Shaban, James O'Brien, Vadim Ignatiev,",
    "scheduler": "EulerAncestralDiscrete",
    "num_outputs": 1,
    "guidance_scale": 7.5,
    "negative_prompt": "disfigured, kitsch, ugly, oversaturated, greain, low-res, Deformed, blurry, bad anatomy, disfigured, poorly drawn face, mutation, mutated, extra limb, ugly, poorly drawn hands, missing limb, blurry, floating limbs, disconnected limbs, malformed hands, blur, out of focus, long neck, long body, ugly, disgusting, poorly drawn, childish, mutilated, mangled, old, surreal, calligraphy, sign, writing, watermark, text, body out of frame, extra legs, extra arms, extra feet, out of frame, poorly drawn feet, cross-eye, blurry, bad anatomy",
    "num_inference_steps": 30
  },
  "logs": "Using seed: 266\nThe following part of your input was truncated because CLIP can only handle sequences up to 77 tokens: [\", dark lighting, high quality, film grain, fujifilm xt 3, highly detailed, excellent composition, cinematic concept art, dramatic lighting, trending on artstation by kaiwan shaban, james o'brien, vadim ignatiev,\"]\n  0%|          | 0/30 [00:00<?, ?it/s]\n  3%|▎         | 1/30 [00:00<00:08,  3.60it/s]\n  7%|▋         | 2/30 [00:00<00:06,  4.05it/s]\n 10%|█         | 3/30 [00:00<00:06,  4.24it/s]\n 13%|█▎        | 4/30 [00:00<00:06,  4.33it/s]\n 17%|█▋        | 5/30 [00:01<00:05,  4.39it/s]\n 20%|██        | 6/30 [00:01<00:05,  4.43it/s]\n 23%|██▎       | 7/30 [00:01<00:05,  4.45it/s]\n 27%|██▋       | 8/30 [00:01<00:04,  4.46it/s]\n 30%|███       | 9/30 [00:02<00:04,  4.47it/s]\n 33%|███▎      | 10/30 [00:02<00:04,  4.47it/s]\n 37%|███▋      | 11/30 [00:02<00:04,  4.47it/s]\n 40%|████      | 12/30 [00:02<00:04,  4.48it/s]\n 43%|████▎     | 13/30 [00:02<00:03,  4.48it/s]\n 47%|████▋     | 14/30 [00:03<00:03,  4.47it/s]\n 50%|█████     | 15/30 [00:03<00:03,  4.48it/s]\n 53%|█████▎    | 16/30 [00:03<00:03,  4.47it/s]\n 57%|█████▋    | 17/30 [00:03<00:02,  4.48it/s]\n 60%|██████    | 18/30 [00:04<00:02,  4.46it/s]\n 63%|██████▎   | 19/30 [00:04<00:02,  4.45it/s]\n 67%|██████▋   | 20/30 [00:04<00:02,  4.45it/s]\n 70%|███████   | 21/30 [00:04<00:02,  4.48it/s]\n 73%|███████▎  | 22/30 [00:04<00:01,  4.42it/s]\n 77%|███████▋  | 23/30 [00:05<00:01,  4.42it/s]\n 80%|████████  | 24/30 [00:05<00:01,  4.43it/s]\n 83%|████████▎ | 25/30 [00:05<00:01,  4.44it/s]\n 87%|████████▋ | 26/30 [00:05<00:00,  4.45it/s]\n 90%|█████████ | 27/30 [00:06<00:00,  4.45it/s]\n 93%|█████████▎| 28/30 [00:06<00:00,  4.45it/s]\n 97%|█████████▋| 29/30 [00:06<00:00,  4.45it/s]\n100%|██████████| 30/30 [00:06<00:00,  4.44it/s]\n100%|██████████| 30/30 [00:06<00:00,  4.43it/s]",
  "metrics": {
    "predict_time": 8.045979,
    "total_time": 7.994824
  },
  "output": [
    "https://replicate.delivery/pbxt/oreIe1ZQ0Sr5j0y8SscEUATRzPc70kwECtD1JRizr5z5Zg6QA/out-0.png"
  ],
  "started_at": "2023-05-11T02:35:30.321158Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/2olwhulca5g6dbklcse2ztqpw4",
    "cancel": "https://api.replicate.com/v1/predictions/2olwhulca5g6dbklcse2ztqpw4/cancel"
  },
  "version": "0882be3a1a415a2fba0575e6aab071c686ddcd4a7a2d02de451f8a2810847f49"
}

Generated in

8.1 seconds

Tweak itReport

Using seed: 266
The following part of your input was truncated because CLIP can only handle sequences up to 77 tokens: [", dark lighting, high quality, film grain, fujifilm xt 3, highly detailed, excellent composition, cinematic concept art, dramatic lighting, trending on artstation by kaiwan shaban, james o'brien, vadim ignatiev,"]
  0%|          | 0/30 [00:00<?, ?it/s]
  3%|▎         | 1/30 [00:00<00:08,  3.60it/s]
  7%|▋         | 2/30 [00:00<00:06,  4.05it/s]
 10%|█         | 3/30 [00:00<00:06,  4.24it/s]
 13%|█▎        | 4/30 [00:00<00:06,  4.33it/s]
 17%|█▋        | 5/30 [00:01<00:05,  4.39it/s]
 20%|██        | 6/30 [00:01<00:05,  4.43it/s]
 23%|██▎       | 7/30 [00:01<00:05,  4.45it/s]
 27%|██▋       | 8/30 [00:01<00:04,  4.46it/s]
 30%|███       | 9/30 [00:02<00:04,  4.47it/s]
 33%|███▎      | 10/30 [00:02<00:04,  4.47it/s]
 37%|███▋      | 11/30 [00:02<00:04,  4.47it/s]
 40%|████      | 12/30 [00:02<00:04,  4.48it/s]
 43%|████▎     | 13/30 [00:02<00:03,  4.48it/s]
 47%|████▋     | 14/30 [00:03<00:03,  4.47it/s]
 50%|█████     | 15/30 [00:03<00:03,  4.48it/s]
 53%|█████▎    | 16/30 [00:03<00:03,  4.47it/s]
 57%|█████▋    | 17/30 [00:03<00:02,  4.48it/s]
 60%|██████    | 18/30 [00:04<00:02,  4.46it/s]
 63%|██████▎   | 19/30 [00:04<00:02,  4.45it/s]
 67%|██████▋   | 20/30 [00:04<00:02,  4.45it/s]
 70%|███████   | 21/30 [00:04<00:02,  4.48it/s]
 73%|███████▎  | 22/30 [00:04<00:01,  4.42it/s]
 77%|███████▋  | 23/30 [00:05<00:01,  4.42it/s]
 80%|████████  | 24/30 [00:05<00:01,  4.43it/s]
 83%|████████▎ | 25/30 [00:05<00:01,  4.44it/s]
 87%|████████▋ | 26/30 [00:05<00:00,  4.45it/s]
 90%|█████████ | 27/30 [00:06<00:00,  4.45it/s]
 93%|█████████▎| 28/30 [00:06<00:00,  4.45it/s]
 97%|█████████▋| 29/30 [00:06<00:00,  4.45it/s]
100%|██████████| 30/30 [00:06<00:00,  4.44it/s]
100%|██████████| 30/30 [00:06<00:00,  4.43it/s]

This example was created by a different version, mcai/deliberate-v2:0882be3a.

Examples

View more examples

Run time and cost

This model costs approximately $0.0015 to run on Replicate, or 666 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 2 seconds.

Readme

…

Model description

…

Intended use

…

Ethical considerations

…

Caveats and recommendations

…