heedster/realistic-vision-v5 – Run with an API on Replicate

heedster / realistic-vision-v5

Deployment of Realistic vision v5.0 with xformers for fast inference

Cold

Public
1.2M runs
A100 (80GB)

Run with an API

Playground API Examples README Versions

Input

prompt

string

Shift + Return to add a new line

RAW photo, a portrait photo of a latina woman in casual clothes, natural skin, 8k uhd, high quality, film grain, Fujifilm XT3RAW photo, a portrait photo of a latina woman in casual clothes, natural skin, 8k uhd, high quality, film grain, Fujifilm XT3

Default: "RAW photo, a portrait photo of a latina woman in casual clothes, natural skin, 8k uhd, high quality, film grain, Fujifilm XT3"

negative_prompt

string

Shift + Return to add a new line

(deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, close up, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck(deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, close up, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck

Default: "(deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, close up, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck"

steps

integer

(minimum: 0, maximum: 100)

num_inference_steps

Default: 20

guidance

number

Guidance scale (3.5 - 7)

Default: 5

width

integer

(minimum: 0, maximum: 1920)

Width

Default: 512

height

integer

(minimum: 0, maximum: 1920)

Height

Default: 728

seed

integer

Seed (0 = random, maximum: 2147483647)

Default: 0

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

npx create-replicate --model=heedster/realistic-vision-v5

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 heedster/realistic-vision-v5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "heedster/realistic-vision-v5:c0259010b93e7a4102a4ba946d70e06d7d0c7dc007201af443cfc8f943ab1d3c",
  {
    input: {
      seed: 0,
      steps: 20,
      width: 512,
      height: 728,
      prompt: "RAW photo, a portrait photo of a latina woman in casual clothes, natural skin, 8k uhd, high quality, film grain, Fujifilm XT3",
      guidance: 5,
      negative_prompt: "(deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, close up, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck"
    }
  }
);
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 heedster/realistic-vision-v5 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "heedster/realistic-vision-v5:c0259010b93e7a4102a4ba946d70e06d7d0c7dc007201af443cfc8f943ab1d3c",
    input={
        "seed": 0,
        "steps": 20,
        "width": 512,
        "height": 728,
        "prompt": "RAW photo, a portrait photo of a latina woman in casual clothes, natural skin, 8k uhd, high quality, film grain, Fujifilm XT3",
        "guidance": 5,
        "negative_prompt": "(deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, close up, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck"
    }
)
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 heedster/realistic-vision-v5 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": "c0259010b93e7a4102a4ba946d70e06d7d0c7dc007201af443cfc8f943ab1d3c",
    "input": {
      "seed": 0,
      "steps": 20,
      "width": 512,
      "height": 728,
      "prompt": "RAW photo, a portrait photo of a latina woman in casual clothes, natural skin, 8k uhd, high quality, film grain, Fujifilm XT3",
      "guidance": 5,
      "negative_prompt": "(deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, close up, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck"
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2023-07-28T12:54:35.866109Z",
  "created_at": "2023-07-28T12:54:33.533109Z",
  "data_removed": false,
  "error": null,
  "id": "exol3grbmex2jvqhsmzm7h5htq",
  "input": {
    "steps": 20,
    "width": 512,
    "height": 728,
    "prompt": "RAW photo, a portrait photo of a latina woman in casual clothes, natural skin, 8k uhd, high quality, film grain, Fujifilm XT3",
    "guidance": 5,
    "negative_prompt": "(deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, close up, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck"
  },
  "logs": "0%|          | 0/20 [00:00<?, ?it/s]\n 10%|█         | 2/20 [00:00<00:01, 14.66it/s]\n 20%|██        | 4/20 [00:00<00:01, 14.70it/s]\n 30%|███       | 6/20 [00:00<00:00, 14.85it/s]\n 40%|████      | 8/20 [00:00<00:00, 14.65it/s]\n 50%|█████     | 10/20 [00:00<00:00, 14.86it/s]\n 60%|██████    | 12/20 [00:00<00:00, 15.01it/s]\n 70%|███████   | 14/20 [00:00<00:00, 15.10it/s]\n 80%|████████  | 16/20 [00:01<00:00, 15.19it/s]\n 90%|█████████ | 18/20 [00:01<00:00, 15.23it/s]\n100%|██████████| 20/20 [00:01<00:00, 15.19it/s]\n100%|██████████| 20/20 [00:01<00:00, 15.03it/s]",
  "metrics": {
    "predict_time": 2.363836,
    "total_time": 2.333
  },
  "output": "https://replicate.delivery/pbxt/6GzgXMQEnfRiGirhuRhZjsMQypDQQ7AcfQasxbewWLQWktoiA/ai.png",
  "started_at": "2023-07-28T12:54:33.502273Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/exol3grbmex2jvqhsmzm7h5htq",
    "cancel": "https://api.replicate.com/v1/predictions/exol3grbmex2jvqhsmzm7h5htq/cancel"
  },
  "version": "c0259010b93e7a4102a4ba946d70e06d7d0c7dc007201af443cfc8f943ab1d3c"
}

Generated in

2.4 seconds

Tweak itReport

Examples

View more examples

Run time and cost

This model costs approximately $0.0050 to run on Replicate, or 200 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 4 seconds. The predict time for this model varies significantly based on the inputs.

Readme

Deployment of Realistic vision v5.0 with xformers for fast inference