qunash/iphone_camera_style – Run with an API on Replicate

qunash / iphone_camera_style

Trained on iPhone photos of Tokyo. Add "shot on TOKSTYL camera" at the end of your prompts.

Warm

Public
1.1K runs
H100

Run with an API

Playground API Examples README Versions

Input

prompt

*string

Shift + Return to add a new line

A cinematic abstract painting of a self-assured woman with a messy mid-length haircut. She is wearing a T-shirt and baggy pants, sitting in a hanging chair with her legs crossed. A large, fluffy cat is sitting on her legs. The artist uses warm and cool colors, such as oranges, blacks, and whites, to create a dynamic and emotive atmosphere. The bold, expressive brushstrokes bring the scene to life, while the muted background with hints of blues and yellows contrasts with the vibrant hues of the central figures. By Sasan. shot on TOKSTYL camera.A cinematic abstract painting of a self-assured woman with a messy mid-length haircut. She is wearing a T-shirt and baggy pants, sitting in a hanging chair with her legs crossed. A large, fluffy cat is sitting on her legs. The artist uses warm and cool colors, such as oranges, blacks, and whites, to create a dynamic and emotive atmosphere. The bold, expressive brushstrokes bring the scene to life, while the muted background with hints of blues and yellows contrasts with the vibrant hues of the central figures. By Sasan. shot on TOKSTYL camera.

Prompt for generated image. If you include the `trigger_word` used in the training process you are more likely to activate the trained object, style, or concept in the resulting image.

image

file

Input image for image to image or inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored.

mask

file

Image mask for image inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored.

aspect_ratio

string

Aspect ratio for the generated image. If custom is selected, uses height and width below & will run in bf16 mode

Default: "1:1"

prompt_strength

number

(minimum: 0, maximum: 1)

Prompt strength when using img2img. 1.0 corresponds to full destruction of information in image

Default: 0.8

num_outputs

integer

(minimum: 1, maximum: 4)

Number of outputs to generate

Default: 1

num_inference_steps

integer

(minimum: 1, maximum: 50)

Number of denoising steps. More steps can give more detailed images, but take longer.

Default: 28

go_fast

boolean

Run faster predictions with model optimized for speed (currently fp8 quantized); disable to run in original bf16

Default: false

megapixels

string

Approximate number of megapixels for generated image

Default: "1"

Including height and 10 more...

height

integer

(minimum: 256, maximum: 1440)

Height of generated image. Only works if `aspect_ratio` is set to custom. Will be rounded to nearest multiple of 16. Incompatible with fast generation

width

integer

(minimum: 256, maximum: 1440)

Width of generated image. Only works if `aspect_ratio` is set to custom. Will be rounded to nearest multiple of 16. Incompatible with fast generation

model

string

Which model to run inference with. The dev model performs best with around 28 inference steps but the schnell model only needs 4 steps.

Default: "dev"

guidance_scale

number

(minimum: 0, maximum: 10)

Guidance scale for the diffusion process. Lower values can give more realistic images. Good values to try are 2, 2.5, 3 and 3.5

Default: 3

seed

integer

Random seed. Set for reproducible generation

output_format

string

Format of the output images

Default: "webp"

output_quality

integer

(minimum: 0, maximum: 100)

Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs

Default: 80

disable_safety_checker

boolean

Disable safety checker for generated images.

Default: false

lora_scale

number

(minimum: -1, maximum: 3)

Determines how strongly the main LoRA should be applied. Sane results between 0 and 1 for base inference. For go_fast we apply a 1.5x multiplier to this value; we've generally seen good performance when scaling the base value by that amount. You may still need to experiment to find the best value for your particular lora.

Default: 1

extra_lora

string

Shift + Return to add a new line

Load LoRA weights. Supports Replicate models in the format <owner>/<username> or <owner>/<username>/<version>, HuggingFace URLs in the format huggingface.co/<owner>/<model-name>, CivitAI URLs in the format civitai.com/models/<id>[/<model-name>], or arbitrary .safetensors URLs from the Internet. For example, 'fofr/flux-pixar-cars'

extra_lora_scale

number

(minimum: -1, maximum: 3)

Determines how strongly the extra LoRA should be applied. Sane results between 0 and 1 for base inference. For go_fast we apply a 1.5x multiplier to this value; we've generally seen good performance when scaling the base value by that amount. You may still need to experiment to find the best value for your particular lora.

Default: 1

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

npx create-replicate --model=qunash/iphone_camera_style

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 qunash/iphone_camera_style using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "qunash/iphone_camera_style:e5582a4cac8eb6f5016386303b71e9a43dd9f26939c74b7fbb62343af9594653",
  {
    input: {
      model: "dev",
      prompt: "A cinematic abstract painting of a self-assured woman with a messy mid-length haircut. She is wearing a T-shirt and baggy pants, sitting in a hanging chair with her legs crossed. A large, fluffy cat is sitting on her legs. The artist uses warm and cool colors, such as oranges, blacks, and whites, to create a dynamic and emotive atmosphere. The bold, expressive brushstrokes bring the scene to life, while the muted background with hints of blues and yellows contrasts with the vibrant hues of the central figures. By Sasan. shot on TOKSTYL camera.",
      go_fast: false,
      lora_scale: 1,
      megapixels: "1",
      num_outputs: 4,
      aspect_ratio: "1:1",
      output_format: "webp",
      guidance_scale: 3.5,
      output_quality: 80,
      prompt_strength: 0.8,
      extra_lora_scale: 0.8,
      num_inference_steps: 28
    }
  }
);

// 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 qunash/iphone_camera_style using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "qunash/iphone_camera_style:e5582a4cac8eb6f5016386303b71e9a43dd9f26939c74b7fbb62343af9594653",
    input={
        "model": "dev",
        "prompt": "A cinematic abstract painting of a self-assured woman with a messy mid-length haircut. She is wearing a T-shirt and baggy pants, sitting in a hanging chair with her legs crossed. A large, fluffy cat is sitting on her legs. The artist uses warm and cool colors, such as oranges, blacks, and whites, to create a dynamic and emotive atmosphere. The bold, expressive brushstrokes bring the scene to life, while the muted background with hints of blues and yellows contrasts with the vibrant hues of the central figures. By Sasan. shot on TOKSTYL camera.",
        "go_fast": False,
        "lora_scale": 1,
        "megapixels": "1",
        "num_outputs": 4,
        "aspect_ratio": "1:1",
        "output_format": "webp",
        "guidance_scale": 3.5,
        "output_quality": 80,
        "prompt_strength": 0.8,
        "extra_lora_scale": 0.8,
        "num_inference_steps": 28
    }
)
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 qunash/iphone_camera_style 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": "e5582a4cac8eb6f5016386303b71e9a43dd9f26939c74b7fbb62343af9594653",
    "input": {
      "model": "dev",
      "prompt": "A cinematic abstract painting of a self-assured woman with a messy mid-length haircut. She is wearing a T-shirt and baggy pants, sitting in a hanging chair with her legs crossed. A large, fluffy cat is sitting on her legs. The artist uses warm and cool colors, such as oranges, blacks, and whites, to create a dynamic and emotive atmosphere. The bold, expressive brushstrokes bring the scene to life, while the muted background with hints of blues and yellows contrasts with the vibrant hues of the central figures. By Sasan. shot on TOKSTYL camera.",
      "go_fast": false,
      "lora_scale": 1,
      "megapixels": "1",
      "num_outputs": 4,
      "aspect_ratio": "1:1",
      "output_format": "webp",
      "guidance_scale": 3.5,
      "output_quality": 80,
      "prompt_strength": 0.8,
      "extra_lora_scale": 0.8,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2024-09-01T15:01:58.417039Z",
  "created_at": "2024-09-01T15:01:14.680000Z",
  "data_removed": false,
  "error": null,
  "id": "kwbm8dp171rm60chnrdbg4p32c",
  "input": {
    "model": "dev",
    "prompt": "A cinematic abstract painting of a self-assured woman with a messy mid-length haircut. She is wearing a T-shirt and baggy pants, sitting in a hanging chair with her legs crossed. A large, fluffy cat is sitting on her legs. The artist uses warm and cool colors, such as oranges, blacks, and whites, to create a dynamic and emotive atmosphere. The bold, expressive brushstrokes bring the scene to life, while the muted background with hints of blues and yellows contrasts with the vibrant hues of the central figures. By Sasan. shot on TOKSTYL camera.",
    "lora_scale": 1,
    "num_outputs": 4,
    "aspect_ratio": "1:1",
    "output_format": "webp",
    "guidance_scale": 3.5,
    "output_quality": 80,
    "extra_lora_scale": 0.8,
    "num_inference_steps": 28
  },
  "logs": "Using seed: 64929\nPrompt: A cinematic abstract painting of a self-assured woman with a messy mid-length haircut. She is wearing a T-shirt and baggy pants, sitting in a hanging chair with her legs crossed. A large, fluffy cat is sitting on her legs. The artist uses warm and cool colors, such as oranges, blacks, and whites, to create a dynamic and emotive atmosphere. The bold, expressive brushstrokes bring the scene to life, while the muted background with hints of blues and yellows contrasts with the vibrant hues of the central figures. By Sasan. shot on TOKSTYL camera.\ntxt2img mode\nUsing dev model\nfree=9374762504192\nDownloading weights\n2024-09-01T15:01:17Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmp801mu_te/weights url=https://replicate.delivery/yhqm/BRTUKRMXKZb4LJmgxf2ePi6EkxLiJM66ovfqKj2twc1XZFxmA/trained_model.tar\n2024-09-01T15:01:19Z | INFO  | [ Complete ] dest=/tmp/tmp801mu_te/weights size=\"172 MB\" total_elapsed=1.539s url=https://replicate.delivery/yhqm/BRTUKRMXKZb4LJmgxf2ePi6EkxLiJM66ovfqKj2twc1XZFxmA/trained_model.tar\nDownloaded weights in 1.57s\nLoaded LoRAs in 10.65s\nThe following part of your input was truncated because CLIP can only handle sequences up to 77 tokens: ['atmosphere. the bold, expressive brushstrokes bring the scene to life, while the muted background with hints of blues and yellows contrasts with the vibrant hues of the central figures. by sasan. shot on tokstyl camera.', 'atmosphere. the bold, expressive brushstrokes bring the scene to life, while the muted background with hints of blues and yellows contrasts with the vibrant hues of the central figures. by sasan. shot on tokstyl camera.', 'atmosphere. the bold, expressive brushstrokes bring the scene to life, while the muted background with hints of blues and yellows contrasts with the vibrant hues of the central figures. by sasan. shot on tokstyl camera.', 'atmosphere. the bold, expressive brushstrokes bring the scene to life, while the muted background with hints of blues and yellows contrasts with the vibrant hues of the central figures. by sasan. shot on tokstyl camera.']\n  0%|          | 0/28 [00:00<?, ?it/s]\n  4%|▎         | 1/28 [00:01<00:27,  1.01s/it]\n  7%|▋         | 2/28 [00:01<00:22,  1.13it/s]\n 11%|█         | 3/28 [00:02<00:23,  1.06it/s]\n 14%|█▍        | 4/28 [00:03<00:23,  1.03it/s]\n 18%|█▊        | 5/28 [00:04<00:22,  1.02it/s]\n 21%|██▏       | 6/28 [00:05<00:21,  1.01it/s]\n 25%|██▌       | 7/28 [00:06<00:20,  1.00it/s]\n 29%|██▊       | 8/28 [00:07<00:20,  1.00s/it]\n 32%|███▏      | 9/28 [00:08<00:19,  1.00s/it]\n 36%|███▌      | 10/28 [00:09<00:18,  1.01s/it]\n 39%|███▉      | 11/28 [00:10<00:17,  1.01s/it]\n 43%|████▎     | 12/28 [00:11<00:16,  1.01s/it]\n 46%|████▋     | 13/28 [00:12<00:15,  1.01s/it]\n 50%|█████     | 14/28 [00:13<00:14,  1.01s/it]\n 54%|█████▎    | 15/28 [00:14<00:13,  1.01s/it]\n 57%|█████▋    | 16/28 [00:15<00:12,  1.01s/it]\n 61%|██████    | 17/28 [00:16<00:11,  1.01s/it]\n 64%|██████▍   | 18/28 [00:17<00:10,  1.01s/it]\n 68%|██████▊   | 19/28 [00:19<00:09,  1.01s/it]\n 71%|███████▏  | 20/28 [00:20<00:08,  1.01s/it]\n 75%|███████▌  | 21/28 [00:21<00:07,  1.01s/it]\n 79%|███████▊  | 22/28 [00:22<00:06,  1.01s/it]\n 82%|████████▏ | 23/28 [00:23<00:05,  1.01s/it]\n 86%|████████▌ | 24/28 [00:24<00:04,  1.01s/it]\n 89%|████████▉ | 25/28 [00:25<00:03,  1.01s/it]\n 93%|█████████▎| 26/28 [00:26<00:02,  1.01s/it]\n 96%|█████████▋| 27/28 [00:27<00:01,  1.01s/it]\n100%|██████████| 28/28 [00:28<00:00,  1.01s/it]\n100%|██████████| 28/28 [00:28<00:00,  1.00s/it]",
  "metrics": {
    "predict_time": 40.494763442,
    "total_time": 43.737039
  },
  "output": [
    "https://replicate.delivery/yhqm/yvUFoNEFVXbFB5Zknvred5rpa7wBTwiq8nvVFfBUqUplPjYTA/out-0.webp",
    "https://replicate.delivery/yhqm/JghfRLqD5tyuTyaF3YHdpe7x4g7fSBtYeU2nVPwJyfes5zI2E/out-1.webp",
    "https://replicate.delivery/yhqm/Pg6Mojmq0pq4O5cV0etkS77oDjm3BxBduY0DbfdJwnVmPjYTA/out-2.webp",
    "https://replicate.delivery/yhqm/VVRSl7SszBraPdHfDYtC6x7qEh3Refgk9Esd6IAeNeI08ZEbC/out-3.webp"
  ],
  "started_at": "2024-09-01T15:01:17.922276Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/kwbm8dp171rm60chnrdbg4p32c",
    "cancel": "https://api.replicate.com/v1/predictions/kwbm8dp171rm60chnrdbg4p32c/cancel"
  },
  "version": "e5582a4cac8eb6f5016386303b71e9a43dd9f26939c74b7fbb62343af9594653"
}

Generated in

40.5 seconds

Tweak it ShareReport

Using seed: 64929
Prompt: A cinematic abstract painting of a self-assured woman with a messy mid-length haircut. She is wearing a T-shirt and baggy pants, sitting in a hanging chair with her legs crossed. A large, fluffy cat is sitting on her legs. The artist uses warm and cool colors, such as oranges, blacks, and whites, to create a dynamic and emotive atmosphere. The bold, expressive brushstrokes bring the scene to life, while the muted background with hints of blues and yellows contrasts with the vibrant hues of the central figures. By Sasan. shot on TOKSTYL camera.
txt2img mode
Using dev model
free=9374762504192
Downloading weights
2024-09-01T15:01:17Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmp801mu_te/weights url=https://replicate.delivery/yhqm/BRTUKRMXKZb4LJmgxf2ePi6EkxLiJM66ovfqKj2twc1XZFxmA/trained_model.tar
2024-09-01T15:01:19Z | INFO  | [ Complete ] dest=/tmp/tmp801mu_te/weights size="172 MB" total_elapsed=1.539s url=https://replicate.delivery/yhqm/BRTUKRMXKZb4LJmgxf2ePi6EkxLiJM66ovfqKj2twc1XZFxmA/trained_model.tar
Downloaded weights in 1.57s
Loaded LoRAs in 10.65s
The following part of your input was truncated because CLIP can only handle sequences up to 77 tokens: ['atmosphere. the bold, expressive brushstrokes bring the scene to life, while the muted background with hints of blues and yellows contrasts with the vibrant hues of the central figures. by sasan. shot on tokstyl camera.', 'atmosphere. the bold, expressive brushstrokes bring the scene to life, while the muted background with hints of blues and yellows contrasts with the vibrant hues of the central figures. by sasan. shot on tokstyl camera.', 'atmosphere. the bold, expressive brushstrokes bring the scene to life, while the muted background with hints of blues and yellows contrasts with the vibrant hues of the central figures. by sasan. shot on tokstyl camera.', 'atmosphere. the bold, expressive brushstrokes bring the scene to life, while the muted background with hints of blues and yellows contrasts with the vibrant hues of the central figures. by sasan. shot on tokstyl camera.']
  0%|          | 0/28 [00:00<?, ?it/s]
  4%|▎         | 1/28 [00:01<00:27,  1.01s/it]
  7%|▋         | 2/28 [00:01<00:22,  1.13it/s]
 11%|█         | 3/28 [00:02<00:23,  1.06it/s]
 14%|█▍        | 4/28 [00:03<00:23,  1.03it/s]
 18%|█▊        | 5/28 [00:04<00:22,  1.02it/s]
 21%|██▏       | 6/28 [00:05<00:21,  1.01it/s]
 25%|██▌       | 7/28 [00:06<00:20,  1.00it/s]
 29%|██▊       | 8/28 [00:07<00:20,  1.00s/it]
 32%|███▏      | 9/28 [00:08<00:19,  1.00s/it]
 36%|███▌      | 10/28 [00:09<00:18,  1.01s/it]
 39%|███▉      | 11/28 [00:10<00:17,  1.01s/it]
 43%|████▎     | 12/28 [00:11<00:16,  1.01s/it]
 46%|████▋     | 13/28 [00:12<00:15,  1.01s/it]
 50%|█████     | 14/28 [00:13<00:14,  1.01s/it]
 54%|█████▎    | 15/28 [00:14<00:13,  1.01s/it]
 57%|█████▋    | 16/28 [00:15<00:12,  1.01s/it]
 61%|██████    | 17/28 [00:16<00:11,  1.01s/it]
 64%|██████▍   | 18/28 [00:17<00:10,  1.01s/it]
 68%|██████▊   | 19/28 [00:19<00:09,  1.01s/it]
 71%|███████▏  | 20/28 [00:20<00:08,  1.01s/it]
 75%|███████▌  | 21/28 [00:21<00:07,  1.01s/it]
 79%|███████▊  | 22/28 [00:22<00:06,  1.01s/it]
 82%|████████▏ | 23/28 [00:23<00:05,  1.01s/it]
 86%|████████▌ | 24/28 [00:24<00:04,  1.01s/it]
 89%|████████▉ | 25/28 [00:25<00:03,  1.01s/it]
 93%|█████████▎| 26/28 [00:26<00:02,  1.01s/it]
 96%|█████████▋| 27/28 [00:27<00:01,  1.01s/it]
100%|██████████| 28/28 [00:28<00:00,  1.01s/it]
100%|██████████| 28/28 [00:28<00:00,  1.00s/it]

Examples

View more examples

Run time and cost

This model costs approximately $0.037 to run on Replicate, or 27 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 H100 GPU hardware. Predictions typically complete within 25 seconds.

Readme

This model doesn't have a readme.