jhorovitz/inversions:d1d9fc7a – Run with an API on Replicate

Version

You're looking at a specific version of this model. Jump to the model overview.

jhorovitz /inversions:d1d9fc7a

Playground API

Input

prompt

*string

Shift + Return to add a new line

Prompt for generated image

aspect_ratio

string

Aspect ratio for the generated image

Default: "1:1"

image

file

Input image for image to image mode. The aspect ratio of your output will match this image

prompt_strength

number

(minimum: 0, maximum: 1)

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

Default: 0.95

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. Recommended range is 28-50

Default: 28

guidance

number

(minimum: 0, maximum: 10)

Guidance for generated image

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

go_fast

boolean

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

Default: true

megapixels

string

Approximate number of megapixels for generated image

Default: "1"

img2img_mode

string

Algorithm to use for img2img. Default FluxImg2ImgPipeline, RF Inversion, DDIM inversion, or using the original image latents. All options but img2img use the eta based sampling strategy detailed in RF Inversion.

Default: "rf_inversion"

eta

number

(minimum: 0, maximum: 1)

Controls strength of influence from the original image in RF inversion sampling. Typical values are 0.7-1.0

Default: 0.9

start_step

integer

(minimum: 0, maximum: 28)

Controls start step for RF inversion sampling. Typical values are 0-3.

Default: 0

end_step

integer

(minimum: 0, maximum: 28)

Controls start step for RF inversion sampling. Typical values are 5-8.

Default: 6

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

npx create-replicate --model=jhorovitz/inversions

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

const output = await replicate.run(
  "jhorovitz/inversions:d1d9fc7a70eaad39f2b388a8ce8ad701bf5ba78cdd45f78995b4acb17f19bec4",
  {
    input: {
      eta: 0.9,
      go_fast: true,
      end_step: 6,
      guidance: 3,
      megapixels: "1",
      start_step: 0,
      num_outputs: 1,
      aspect_ratio: "1:1",
      img2img_mode: "rf_inversion",
      output_format: "webp",
      output_quality: 80,
      prompt_strength: 0.95,
      num_inference_steps: 28
    }
  }
);
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 jhorovitz/inversions using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "jhorovitz/inversions:d1d9fc7a70eaad39f2b388a8ce8ad701bf5ba78cdd45f78995b4acb17f19bec4",
    input={
        "eta": 0.9,
        "go_fast": True,
        "end_step": 6,
        "guidance": 3,
        "megapixels": "1",
        "start_step": 0,
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "img2img_mode": "rf_inversion",
        "output_format": "webp",
        "output_quality": 80,
        "prompt_strength": 0.95,
        "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 jhorovitz/inversions 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": "d1d9fc7a70eaad39f2b388a8ce8ad701bf5ba78cdd45f78995b4acb17f19bec4",
    "input": {
      "eta": 0.9,
      "go_fast": true,
      "end_step": 6,
      "guidance": 3,
      "megapixels": "1",
      "start_step": 0,
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "img2img_mode": "rf_inversion",
      "output_format": "webp",
      "output_quality": 80,
      "prompt_strength": 0.95,
      "num_inference_steps": 28
    }
  }' \
  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/jhorovitz/inversions@sha256:d1d9fc7a70eaad39f2b388a8ce8ad701bf5ba78cdd45f78995b4acb17f19bec4 \
  -i 'eta=0.9' \
  -i 'go_fast=true' \
  -i 'end_step=6' \
  -i 'guidance=3' \
  -i 'megapixels="1"' \
  -i 'start_step=0' \
  -i 'num_outputs=1' \
  -i 'aspect_ratio="1:1"' \
  -i 'img2img_mode="rf_inversion"' \
  -i 'output_format="webp"' \
  -i 'output_quality=80' \
  -i 'prompt_strength=0.95' \
  -i 'num_inference_steps=28'

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/jhorovitz/inversions@sha256:d1d9fc7a70eaad39f2b388a8ce8ad701bf5ba78cdd45f78995b4acb17f19bec4
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "eta": 0.9,
      "go_fast": true,
      "end_step": 6,
      "guidance": 3,
      "megapixels": "1",
      "start_step": 0,
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "img2img_mode": "rf_inversion",
      "output_format": "webp",
      "output_quality": 80,
      "prompt_strength": 0.95,
      "num_inference_steps": 28
    }
  }' \
  http://localhost:5000/predictions

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

Output

No output yet! Press "Submit" to start a prediction.