fermatresearch/photorealistic-fx – Run with an API on Replicate

fermatresearch / photorealistic-fx

RunDiffusion FX Photorealistic model, developed by RunDiffusion.

Cold

Public
41.5K runs
A100 (80GB)

Run with an API

Playground API Examples README Versions

Input

prompt

string

Shift + Return to add a new line

close up of a tiger staring at the camera with a fierce expression and the mouth open, bokeh effect, jungle, sharp teeth, huntingclose up of a tiger staring at the camera with a fierce expression and the mouth open, bokeh effect, jungle, sharp teeth, hunting

Input prompt

Default: "a zoo in space"

negative_prompt

string

Shift + Return to add a new line

(semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, 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(semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, 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

Specify things to not see in the output

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: 512

image

file

(Img2Img) Initial image to generate variations of. If this is not none, Img2Img will be invoked.

prompt_strength

number

Prompt strength when using init image. 1.0 corresponds to full destruction of information in init image

Default: 0.8

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: "K_EULER_ANCESTRAL"

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=fermatresearch/photorealistic-fx

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 fermatresearch/photorealistic-fx using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "fermatresearch/photorealistic-fx:580cd5e6de394d3ced207a7e4275d7d9b7e0174212f3bbe108e290e25a859a3e",
  {
    input: {
      width: 768,
      height: 1024,
      prompt: "close up of a tiger staring at the camera with a fierce expression and the mouth open, bokeh effect, jungle, sharp teeth, hunting",
      scheduler: "K_EULER_ANCESTRAL",
      num_outputs: 1,
      guidance_scale: 7.5,
      negative_prompt: "(semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, 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",
      prompt_strength: 0.8,
      num_inference_steps: 30
    }
  }
);

// 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 fermatresearch/photorealistic-fx using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "fermatresearch/photorealistic-fx:580cd5e6de394d3ced207a7e4275d7d9b7e0174212f3bbe108e290e25a859a3e",
    input={
        "width": 768,
        "height": 1024,
        "prompt": "close up of a tiger staring at the camera with a fierce expression and the mouth open, bokeh effect, jungle, sharp teeth, hunting",
        "scheduler": "K_EULER_ANCESTRAL",
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "negative_prompt": "(semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, 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",
        "prompt_strength": 0.8,
        "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 fermatresearch/photorealistic-fx 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": "580cd5e6de394d3ced207a7e4275d7d9b7e0174212f3bbe108e290e25a859a3e",
    "input": {
      "width": 768,
      "height": 1024,
      "prompt": "close up of a tiger staring at the camera with a fierce expression and the mouth open, bokeh effect, jungle, sharp teeth, hunting",
      "scheduler": "K_EULER_ANCESTRAL",
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "negative_prompt": "(semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, 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",
      "prompt_strength": 0.8,
      "num_inference_steps": 30
    }
  }' \
  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/fermatresearch/photorealistic-fx@sha256:580cd5e6de394d3ced207a7e4275d7d9b7e0174212f3bbe108e290e25a859a3e \
  -i 'width=768' \
  -i 'height=1024' \
  -i 'prompt="close up of a tiger staring at the camera with a fierce expression and the mouth open, bokeh effect, jungle, sharp teeth, hunting"' \
  -i 'scheduler="K_EULER_ANCESTRAL"' \
  -i 'num_outputs=1' \
  -i 'guidance_scale=7.5' \
  -i 'negative_prompt="(semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, 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"' \
  -i 'prompt_strength=0.8' \
  -i 'num_inference_steps=30'

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/fermatresearch/photorealistic-fx@sha256:580cd5e6de394d3ced207a7e4275d7d9b7e0174212f3bbe108e290e25a859a3e
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "width": 768,
      "height": 1024,
      "prompt": "close up of a tiger staring at the camera with a fierce expression and the mouth open, bokeh effect, jungle, sharp teeth, hunting",
      "scheduler": "K_EULER_ANCESTRAL",
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "negative_prompt": "(semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, 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",
      "prompt_strength": 0.8,
      "num_inference_steps": 30
    }
  }' \
  http://localhost:5000/predictions

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

Output

{
  "completed_at": "2023-06-13T13:33:10.227866Z",
  "created_at": "2023-06-13T13:33:04.674532Z",
  "data_removed": false,
  "error": null,
  "id": "7zjbjarbwfds3tgvc7jt2i54zu",
  "input": {
    "width": 768,
    "height": "1024",
    "prompt": "close up of a tiger staring at the camera with a fierce expression and the mouth open, bokeh effect, jungle, sharp teeth, hunting",
    "scheduler": "K_EULER_ANCESTRAL",
    "num_outputs": 1,
    "guidance_scale": 7.5,
    "negative_prompt": "(semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, 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",
    "prompt_strength": 0.8,
    "num_inference_steps": 30
  },
  "logs": "Using seed: 30772\n  0%|          | 0/30 [00:00<?, ?it/s]\n  3%|▎         | 1/30 [00:00<00:05,  5.69it/s]\n  7%|▋         | 2/30 [00:00<00:04,  6.29it/s]\n 10%|█         | 3/30 [00:00<00:04,  6.51it/s]\n 13%|█▎        | 4/30 [00:00<00:03,  6.62it/s]\n 17%|█▋        | 5/30 [00:00<00:03,  6.69it/s]\n 20%|██        | 6/30 [00:00<00:03,  6.73it/s]\n 23%|██▎       | 7/30 [00:01<00:03,  6.74it/s]\n 27%|██▋       | 8/30 [00:01<00:03,  6.76it/s]\n 30%|███       | 9/30 [00:01<00:03,  6.78it/s]\n 33%|███▎      | 10/30 [00:01<00:02,  6.79it/s]\n 37%|███▋      | 11/30 [00:01<00:02,  6.80it/s]\n 40%|████      | 12/30 [00:01<00:02,  6.80it/s]\n 43%|████▎     | 13/30 [00:01<00:02,  6.80it/s]\n 47%|████▋     | 14/30 [00:02<00:02,  6.80it/s]\n 50%|█████     | 15/30 [00:02<00:02,  6.81it/s]\n 53%|█████▎    | 16/30 [00:02<00:02,  6.81it/s]\n 57%|█████▋    | 17/30 [00:02<00:01,  6.80it/s]\n 60%|██████    | 18/30 [00:02<00:01,  6.80it/s]\n 63%|██████▎   | 19/30 [00:02<00:01,  6.80it/s]\n 67%|██████▋   | 20/30 [00:02<00:01,  6.80it/s]\n 70%|███████   | 21/30 [00:03<00:01,  6.80it/s]\n 73%|███████▎  | 22/30 [00:03<00:01,  6.80it/s]\n 77%|███████▋  | 23/30 [00:03<00:01,  6.80it/s]\n 80%|████████  | 24/30 [00:03<00:00,  6.80it/s]\n 83%|████████▎ | 25/30 [00:03<00:00,  6.80it/s]\n 87%|████████▋ | 26/30 [00:03<00:00,  6.81it/s]\n 90%|█████████ | 27/30 [00:03<00:00,  6.81it/s]\n 93%|█████████▎| 28/30 [00:04<00:00,  6.81it/s]\n 97%|█████████▋| 29/30 [00:04<00:00,  6.80it/s]\n100%|██████████| 30/30 [00:04<00:00,  6.81it/s]\n100%|██████████| 30/30 [00:04<00:00,  6.76it/s]",
  "metrics": {
    "predict_time": 5.591633,
    "total_time": 5.553334
  },
  "output": [
    "https://replicate.delivery/pbxt/DTtIuZRWFiojIJG3ZABnY2e7pf4oTlxxgjYvzouRnUCVIiFRA/out-0.png"
  ],
  "started_at": "2023-06-13T13:33:04.636233Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/7zjbjarbwfds3tgvc7jt2i54zu",
    "cancel": "https://api.replicate.com/v1/predictions/7zjbjarbwfds3tgvc7jt2i54zu/cancel"
  },
  "version": "580cd5e6de394d3ced207a7e4275d7d9b7e0174212f3bbe108e290e25a859a3e"
}

Generated in

5.6 seconds

Tweak itReport

Examples

View more examples

Run time and cost

This model costs approximately $0.0073 to run on Replicate, or 136 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 6 seconds.

Readme

This model doesn't have a readme.