artificialguybr/cinematic.redmond – Run with an API on Replicate

artificialguybr / cinematic.redmond

Cinematic.Redmond has a high capacity to generate Cinematic, artistic images, cars, people, and a wide variety of themes

Cold

Public
15.5K runs
L40S
GitHub
License

Iterate in playground

Run with an API

Playground API Examples README Versions

Input

prompt

string

Shift + Return to add a new line

A cinematic film still of a (Movie Still) from Suicide Squad , (extremely intricate:1.3), (realistic), portrait of a girl, the most beautiful in the world, Margot Robbie as Harley Quinn, colorful hair, pigtails, blue eyes, baseball bat, teeth, (detailed face, detailed eyes, clear skin, clear eyes), photorealistic, award winning, professional photograph of a stunning woman detailed, sharp focus, dramatic, award winning, cinematic lighting, volumetrics dtx 
A cinematic film still of a (Movie Still) from Suicide Squad , (extremely intricate:1.3), (realistic), portrait of a girl, the most beautiful in the world, Margot Robbie as Harley Quinn, colorful hair, pigtails, blue eyes, baseball bat, teeth, (detailed face, detailed eyes, clear skin, clear eyes), photorealistic, award winning, professional photograph of a stunning woman detailed, sharp focus, dramatic, award winning, cinematic lighting, volumetrics dtx 

Input prompt

Default: "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"

negative_prompt

string

Shift + Return to add a new line

Input Negative Prompt

Default: "text, watermark, blur, deformed, noised"

width

integer

Width of output image. Lower if out of memory

Default: 1656

height

integer

Height of output image. Lower if out of memory

Default: 744

num_images

integer

(minimum: 1, maximum: 8)

Number of images per prompt

Default: 1

num_inference_steps

integer

(minimum: 1, maximum: 100)

Number of denoising steps

Default: 30

guidance_scale

number

(minimum: 1, maximum: 20)

Scale for classifier-free guidance

Default: 6

seed

integer

Random seed. Leave blank to randomize the seed

disable_safety_checker

boolean

Disable safety checker for generated images. This feature is only available through the API

Default: false

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

npx create-replicate --model=artificialguybr/cinematic.redmond

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";
import fs from "node:fs";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run artificialguybr/cinematic.redmond using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "artificialguybr/cinematic.redmond:96fdefbd19563d6a391c18e1954085ca1b2f3c6b6b88b4e1f808e7e7bd4a873c",
  {
    input: {
      width: 1656,
      height: 744,
      prompt: "A cinematic film still of a (Movie Still) from Suicide Squad , (extremely intricate:1.3), (realistic), portrait of a girl, the most beautiful in the world, Margot Robbie as Harley Quinn, colorful hair, pigtails, blue eyes, baseball bat, teeth, (detailed face, detailed eyes, clear skin, clear eyes), photorealistic, award winning, professional photograph of a stunning woman detailed, sharp focus, dramatic, award winning, cinematic lighting, volumetrics dtx \n",
      num_images: 1,
      guidance_scale: 6,
      negative_prompt: "text, watermark, blur, deformed, noised",
      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 artificialguybr/cinematic.redmond using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "artificialguybr/cinematic.redmond:96fdefbd19563d6a391c18e1954085ca1b2f3c6b6b88b4e1f808e7e7bd4a873c",
    input={
        "width": 1656,
        "height": 744,
        "prompt": "A cinematic film still of a (Movie Still) from Suicide Squad , (extremely intricate:1.3), (realistic), portrait of a girl, the most beautiful in the world, Margot Robbie as Harley Quinn, colorful hair, pigtails, blue eyes, baseball bat, teeth, (detailed face, detailed eyes, clear skin, clear eyes), photorealistic, award winning, professional photograph of a stunning woman detailed, sharp focus, dramatic, award winning, cinematic lighting, volumetrics dtx \n",
        "num_images": 1,
        "guidance_scale": 6,
        "negative_prompt": "text, watermark, blur, deformed, noised",
        "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 artificialguybr/cinematic.redmond 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": "artificialguybr/cinematic.redmond:96fdefbd19563d6a391c18e1954085ca1b2f3c6b6b88b4e1f808e7e7bd4a873c",
    "input": {
      "width": 1656,
      "height": 744,
      "prompt": "A cinematic film still of a (Movie Still) from Suicide Squad , (extremely intricate:1.3), (realistic), portrait of a girl, the most beautiful in the world, Margot Robbie as Harley Quinn, colorful hair, pigtails, blue eyes, baseball bat, teeth, (detailed face, detailed eyes, clear skin, clear eyes), photorealistic, award winning, professional photograph of a stunning woman detailed, sharp focus, dramatic, award winning, cinematic lighting, volumetrics dtx \\n",
      "num_images": 1,
      "guidance_scale": 6,
      "negative_prompt": "text, watermark, blur, deformed, noised",
      "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": "2024-03-21T23:02:57.086263Z",
  "created_at": "2024-03-21T23:02:47.775359Z",
  "data_removed": false,
  "error": null,
  "id": "busjgltb33r7puf2slkhjwq5m4",
  "input": {
    "width": 1656,
    "height": 744,
    "prompt": "A cinematic film still of a (Movie Still) from Suicide Squad , (extremely intricate:1.3), (realistic), portrait of a girl, the most beautiful in the world, Margot Robbie as Harley Quinn, colorful hair, pigtails, blue eyes, baseball bat, teeth, (detailed face, detailed eyes, clear skin, clear eyes), photorealistic, award winning, professional photograph of a stunning woman detailed, sharp focus, dramatic, award winning, cinematic lighting, volumetrics dtx \n",
    "num_images": 1,
    "guidance_scale": 6,
    "negative_prompt": "text, watermark, blur, deformed, noised",
    "num_inference_steps": 30
  },
  "logs": "Using seed: 51751\ntxt2img mode\nThe following part of your input was truncated because CLIP can only handle sequences up to 77 tokens: [', professional photograph of a stunning woman detailed, sharp focus, dramatic, award winning, cinematic lighting, volumetrics dtx']\nThe following part of your input was truncated because CLIP can only handle sequences up to 77 tokens: [', professional photograph of a stunning woman detailed, sharp focus, dramatic, award winning, cinematic lighting, volumetrics dtx']\n  0%|          | 0/30 [00:00<?, ?it/s]\n  3%|▎         | 1/30 [00:00<00:04,  7.07it/s]\n  7%|▋         | 2/30 [00:00<00:05,  4.77it/s]\n 10%|█         | 3/30 [00:00<00:06,  4.32it/s]\n 13%|█▎        | 4/30 [00:00<00:06,  4.13it/s]\n 17%|█▋        | 5/30 [00:01<00:06,  4.04it/s]\n 20%|██        | 6/30 [00:01<00:06,  3.98it/s]\n 23%|██▎       | 7/30 [00:01<00:05,  3.95it/s]\n 27%|██▋       | 8/30 [00:01<00:05,  3.92it/s]\n 30%|███       | 9/30 [00:02<00:05,  3.91it/s]\n 33%|███▎      | 10/30 [00:02<00:05,  3.90it/s]\n 37%|███▋      | 11/30 [00:02<00:04,  3.89it/s]\n 40%|████      | 12/30 [00:02<00:04,  3.89it/s]\n 43%|████▎     | 13/30 [00:03<00:04,  3.89it/s]\n 47%|████▋     | 14/30 [00:03<00:04,  3.89it/s]\n 50%|█████     | 15/30 [00:03<00:03,  3.89it/s]\n 53%|█████▎    | 16/30 [00:04<00:03,  3.90it/s]\n 57%|█████▋    | 17/30 [00:04<00:03,  3.90it/s]\n 60%|██████    | 18/30 [00:04<00:03,  3.90it/s]\n 63%|██████▎   | 19/30 [00:04<00:02,  3.90it/s]\n 67%|██████▋   | 20/30 [00:05<00:02,  3.90it/s]\n 70%|███████   | 21/30 [00:05<00:02,  3.90it/s]\n 73%|███████▎  | 22/30 [00:05<00:02,  3.90it/s]\n 77%|███████▋  | 23/30 [00:05<00:01,  3.90it/s]\n 80%|████████  | 24/30 [00:06<00:01,  3.90it/s]\n 83%|████████▎ | 25/30 [00:06<00:01,  3.89it/s]\n 87%|████████▋ | 26/30 [00:06<00:01,  3.89it/s]\n 90%|█████████ | 27/30 [00:06<00:00,  3.89it/s]\n 93%|█████████▎| 28/30 [00:07<00:00,  3.89it/s]\n 97%|█████████▋| 29/30 [00:07<00:00,  3.89it/s]\n100%|██████████| 30/30 [00:07<00:00,  3.89it/s]\n100%|██████████| 30/30 [00:07<00:00,  3.95it/s]\nInference took: 8.21s\nPrediction took: 8.21s",
  "metrics": {
    "predict_time": 9.274828,
    "total_time": 9.310904
  },
  "output": [
    "https://replicate.delivery/pbxt/dRfqIaXP7U1tLqAFOFHxeIr2HaksXqEM7uOfeqcEGDHDqbKKB/out-0.jpg"
  ],
  "started_at": "2024-03-21T23:02:47.811435Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/busjgltb33r7puf2slkhjwq5m4",
    "cancel": "https://api.replicate.com/v1/predictions/busjgltb33r7puf2slkhjwq5m4/cancel"
  },
  "version": "96fdefbd19563d6a391c18e1954085ca1b2f3c6b6b88b4e1f808e7e7bd4a873c"
}

Generated in

9.3 seconds

Tweak itReport

Using seed: 51751
txt2img mode
The following part of your input was truncated because CLIP can only handle sequences up to 77 tokens: [', professional photograph of a stunning woman detailed, sharp focus, dramatic, award winning, cinematic lighting, volumetrics dtx']
The following part of your input was truncated because CLIP can only handle sequences up to 77 tokens: [', professional photograph of a stunning woman detailed, sharp focus, dramatic, award winning, cinematic lighting, volumetrics dtx']
  0%|          | 0/30 [00:00<?, ?it/s]
  3%|▎         | 1/30 [00:00<00:04,  7.07it/s]
  7%|▋         | 2/30 [00:00<00:05,  4.77it/s]
 10%|█         | 3/30 [00:00<00:06,  4.32it/s]
 13%|█▎        | 4/30 [00:00<00:06,  4.13it/s]
 17%|█▋        | 5/30 [00:01<00:06,  4.04it/s]
 20%|██        | 6/30 [00:01<00:06,  3.98it/s]
 23%|██▎       | 7/30 [00:01<00:05,  3.95it/s]
 27%|██▋       | 8/30 [00:01<00:05,  3.92it/s]
 30%|███       | 9/30 [00:02<00:05,  3.91it/s]
 33%|███▎      | 10/30 [00:02<00:05,  3.90it/s]
 37%|███▋      | 11/30 [00:02<00:04,  3.89it/s]
 40%|████      | 12/30 [00:02<00:04,  3.89it/s]
 43%|████▎     | 13/30 [00:03<00:04,  3.89it/s]
 47%|████▋     | 14/30 [00:03<00:04,  3.89it/s]
 50%|█████     | 15/30 [00:03<00:03,  3.89it/s]
 53%|█████▎    | 16/30 [00:04<00:03,  3.90it/s]
 57%|█████▋    | 17/30 [00:04<00:03,  3.90it/s]
 60%|██████    | 18/30 [00:04<00:03,  3.90it/s]
 63%|██████▎   | 19/30 [00:04<00:02,  3.90it/s]
 67%|██████▋   | 20/30 [00:05<00:02,  3.90it/s]
 70%|███████   | 21/30 [00:05<00:02,  3.90it/s]
 73%|███████▎  | 22/30 [00:05<00:02,  3.90it/s]
 77%|███████▋  | 23/30 [00:05<00:01,  3.90it/s]
 80%|████████  | 24/30 [00:06<00:01,  3.90it/s]
 83%|████████▎ | 25/30 [00:06<00:01,  3.89it/s]
 87%|████████▋ | 26/30 [00:06<00:01,  3.89it/s]
 90%|█████████ | 27/30 [00:06<00:00,  3.89it/s]
 93%|█████████▎| 28/30 [00:07<00:00,  3.89it/s]
 97%|█████████▋| 29/30 [00:07<00:00,  3.89it/s]
100%|██████████| 30/30 [00:07<00:00,  3.89it/s]
100%|██████████| 30/30 [00:07<00:00,  3.95it/s]
Inference took: 8.21s
Prediction took: 8.21s

Examples

View more examples

Run time and cost

This model costs approximately $0.0045 to run on Replicate, or 222 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 5 seconds. The predict time for this model varies significantly based on the inputs.

Readme

Cinematic.Redmond is here!

I’m grateful for the GPU time from Redmond.AI that allowed me to make this model!

This is a Cinematic model fine-tuned on SD XL 1.0!

The model has a high capacity to generate Cinematic, artistic images, cars, people, and a wide variety of themes. It’s a versatile model.

I really hope you like the model and use it.

I recommend generating it in cinematic proportion like 16:9, 2:1 etc.

If you like the model and think it’s worth it, you can make a donation to my Patreon or Ko-fi.

Follow me in my twitter to get acess before for all new models:

https://twitter.com/artificialguybr/