datacte/proteus-v0.2 | Run with an API on Replicate

datacte / proteus-v0.2

Proteus v0.2 shows subtle yet significant improvements over Version 0.1. It demonstrates enhanced prompt understanding that surpasses MJ6, while also approaching its stylistic capabilities.

Warm

Public
10.4M 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

cinematic film still of Kodak Motion Picture Film: (Sharp Detailed Image) An Oscar winning movie for Best Cinematography a woman in a kimono standing on a subway train in Japan Kodak Motion Picture Film Style, shallow depth of field, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainycinematic film still of Kodak Motion Picture Film: (Sharp Detailed Image) An Oscar winning movie for Best Cinematography a woman in a kimono standing on a subway train in Japan Kodak Motion Picture Film Style, shallow depth of field, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy

Input prompt

Default: "black fluffy gorgeous dangerous cat animal creature, large orange eyes, big fluffy ears, piercing gaze, full moon, dark ambiance, best quality, extremely detailed"

negative_prompt

string

Shift + Return to add a new line

Negative Input prompt

Default: "worst quality, low quality"

image

file

Input image for img2img or inpaint mode

mask

file

Input mask for inpaint mode. Black areas will be preserved, white areas will be inpainted.

width

integer

Width of output image

Default: 1024

height

integer

Height of output image

Default: 1024

num_outputs

integer

(minimum: 1, maximum: 4)

Number of images to output.

Default: 1

scheduler

string

scheduler

Default: "KarrasDPM"

num_inference_steps

integer

(minimum: 1, maximum: 100)

Number of denoising steps. 20 to 35 steps for more detail, 20 steps for faster results.

Default: 20

guidance_scale

number

(minimum: 1, maximum: 50)

Scale for classifier-free guidance. Recommended 7-8

Default: 7.5

prompt_strength

number

(minimum: 0, maximum: 1)

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

Default: 0.8

seed

integer

Random seed. Leave blank to randomize the seed

apply_watermark

boolean

Applies a watermark to enable determining if an image is generated in downstream applications. If you have other provisions for generating or deploying images safely, you can use this to disable watermarking.

Default: true

disable_safety_checker

boolean

Disable safety checker for generated images. This feature is only available through the API. See https://replicate.com/docs/how-does-replicate-work#safety

Default: false

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

npx create-replicate --model=datacte/proteus-v0.2

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 datacte/proteus-v0.2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "datacte/proteus-v0.2:06775cd262843edbde5abab958abdbb65a0a6b58ca301c9fd78fa55c775fc019",
  {
    input: {
      width: 1024,
      height: 1024,
      prompt: "cinematic film still of Kodak Motion Picture Film: (Sharp Detailed Image) An Oscar winning movie for Best Cinematography a woman in a kimono standing on a subway train in Japan Kodak Motion Picture Film Style, shallow depth of field, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy",
      scheduler: "KarrasDPM",
      num_outputs: 1,
      guidance_scale: 7.5,
      apply_watermark: true,
      negative_prompt: "worst quality, low quality",
      prompt_strength: 0.8,
      num_inference_steps: 20
    }
  }
);

// 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 datacte/proteus-v0.2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "datacte/proteus-v0.2:06775cd262843edbde5abab958abdbb65a0a6b58ca301c9fd78fa55c775fc019",
    input={
        "width": 1024,
        "height": 1024,
        "prompt": "cinematic film still of Kodak Motion Picture Film: (Sharp Detailed Image) An Oscar winning movie for Best Cinematography a woman in a kimono standing on a subway train in Japan Kodak Motion Picture Film Style, shallow depth of field, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy",
        "scheduler": "KarrasDPM",
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "apply_watermark": True,
        "negative_prompt": "worst quality, low quality",
        "prompt_strength": 0.8,
        "num_inference_steps": 20
    }
)

# To access the file URL:
print(output[0].url())
#=> "http://example.com"

# To write the file to disk:
with open("my-image.png", "wb") as file:
    file.write(output[0].read())

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 datacte/proteus-v0.2 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": "datacte/proteus-v0.2:06775cd262843edbde5abab958abdbb65a0a6b58ca301c9fd78fa55c775fc019",
    "input": {
      "width": 1024,
      "height": 1024,
      "prompt": "cinematic film still of Kodak Motion Picture Film: (Sharp Detailed Image) An Oscar winning movie for Best Cinematography a woman in a kimono standing on a subway train in Japan Kodak Motion Picture Film Style, shallow depth of field, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy",
      "scheduler": "KarrasDPM",
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "apply_watermark": true,
      "negative_prompt": "worst quality, low quality",
      "prompt_strength": 0.8,
      "num_inference_steps": 20
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2024-01-24T19:04:51.055695Z",
  "created_at": "2024-01-24T19:04:45.609539Z",
  "data_removed": false,
  "error": null,
  "id": "ba4g7ptbfappfgry54h4pozt7m",
  "input": {
    "width": 1024,
    "height": 1024,
    "prompt": "cinematic film still of Kodak Motion Picture Film: (Sharp Detailed Image) An Oscar winning movie for Best Cinematography a woman in a kimono standing on a subway train in Japan Kodak Motion Picture Film Style, shallow depth of field, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy",
    "scheduler": "KarrasDPM",
    "num_outputs": 1,
    "guidance_scale": 7.5,
    "apply_watermark": true,
    "prompt_strength": 0.8,
    "num_inference_steps": 20
  },
  "logs": "Using seed: 2304021969\nPrompt: cinematic film still of Kodak Motion Picture Film: (Sharp Detailed Image) An Oscar winning movie for Best Cinematography a woman in a kimono standing on a subway train in Japan Kodak Motion Picture Film Style, shallow depth of field, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy\ntxt2img mode\n  0%|          | 0/20 [00:00<?, ?it/s]\n  5%|▌         | 1/20 [00:00<00:03,  5.04it/s]\n 15%|█▌        | 3/20 [00:00<00:02,  6.22it/s]\n 20%|██        | 4/20 [00:00<00:02,  5.74it/s]\n 25%|██▌       | 5/20 [00:00<00:02,  5.47it/s]\n 30%|███       | 6/20 [00:01<00:02,  5.31it/s]\n 35%|███▌      | 7/20 [00:01<00:02,  5.21it/s]\n 40%|████      | 8/20 [00:01<00:02,  5.14it/s]\n 45%|████▌     | 9/20 [00:01<00:02,  5.09it/s]\n 50%|█████     | 10/20 [00:01<00:01,  5.06it/s]\n 55%|█████▌    | 11/20 [00:02<00:01,  5.03it/s]\n 60%|██████    | 12/20 [00:02<00:01,  5.02it/s]\n 65%|██████▌   | 13/20 [00:02<00:01,  5.00it/s]\n 70%|███████   | 14/20 [00:02<00:01,  5.00it/s]\n 75%|███████▌  | 15/20 [00:02<00:01,  4.99it/s]\n 80%|████████  | 16/20 [00:03<00:00,  4.99it/s]\n 85%|████████▌ | 17/20 [00:03<00:00,  4.98it/s]\n 90%|█████████ | 18/20 [00:03<00:00,  4.98it/s]\n 95%|█████████▌| 19/20 [00:03<00:00,  4.98it/s]\n100%|██████████| 20/20 [00:03<00:00,  4.97it/s]\n100%|██████████| 20/20 [00:03<00:00,  5.12it/s]",
  "metrics": {
    "predict_time": 5.437921,
    "total_time": 5.446156
  },
  "output": [
    "https://replicate.delivery/pbxt/1nrcrEszpsb0Kpv0qNBJrtQjoefjHJ3xSh3whVOJcklSFxPSA/out-0.png"
  ],
  "started_at": "2024-01-24T19:04:45.617774Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/ba4g7ptbfappfgry54h4pozt7m",
    "cancel": "https://api.replicate.com/v1/predictions/ba4g7ptbfappfgry54h4pozt7m/cancel"
  },
  "version": "06775cd262843edbde5abab958abdbb65a0a6b58ca301c9fd78fa55c775fc019"
}

Generated in

5.4 seconds

Tweak itReport View full prediction

Examples

View more examples

Run time and cost

This model costs approximately $0.020 to run on Replicate, or 50 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 21 seconds. The predict time for this model varies significantly based on the inputs.

Readme

Cog implementation of dataautogpt3/ProteusV0.2

ProteusV0.2

merged with RealCartoonXL to fix issues with inability to understand tags related to anime or cartoon styles at just a weight of 0.5% out of 100% using custom scripts with slerp like methods.

Version 0.2 shows subtle yet significant improvements over Version 0.1. It demonstrates enhanced prompt understanding that surpasses MJ6, while also approaching its stylistic capabilities.

Proteus

Proteus serves as a sophisticated enhancement over OpenDalleV1.1, leveraging its core functionalities to deliver superior outcomes. Key areas of advancement include heightened responsiveness to prompts and augmented creative capacities. To achieve this, it was fine-tuned using approximately 220,000 GPTV captioned images from copyright-free stock images (with some anime included), which were then normalized. Additionally, DPO (Direct Preference Optimization) was employed through a collection of 10,000 carefully selected high-quality, AI-generated image pairs.

In pursuit of optimal performance, numerous LORA (Low-Rank Adaptation) models are trained independently before being selectively incorporated into the principal model via dynamic application methods. These techniques involve targeting particular segments within the model while avoiding interference with other areas during the learning phase. Consequently, Proteus exhibits marked improvements in portraying intricate facial characteristics and lifelike skin textures, all while sustaining commendable proficiency across various aesthetic domains, notably surrealism, anime, and cartoon-style visualizations.

Settings for ProteusV0.2

Use these settings for the best results with ProteusV0.2:

CFG Scale: Use a CFG scale of 8 to 7

Steps: 20 to 60 steps for more detail, 20 steps for faster results.

Sampler: DPM++ 2M SDE

Scheduler: Karras

Resolution: 1280x1280 or 1024x1024

please also consider using these keep words to improve your prompts: best quality, HD, ~~aesthetic~~.

if you are having trouble coming up with prompts you can use this GPT I put together to help you refine the prompt. https://chat.openai.com/g/g-RziQNoydR-diffusion-master