edenartlab/eden-sd-pipelines:3e56e23e – Run with an API on Replicate

Version

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

edenartlab /eden-sd-pipelines:3e56e23e

Playground API

Input

mode

string

Mode

Default: "generate"

stream

boolean

yield individual results if True

Default: false

stream_every

integer

(minimum: 1, maximum: 25)

for mode generate, how many steps per update to stream (steam must be set to True)

Default: 1

width

integer

(minimum: 64, maximum: 1600)

Width

Default: 512

height

integer

(minimum: 64, maximum: 1600)

Height

Default: 512

sampler

string

Which sampler to use

Default: "euler"

steps

integer

(minimum: 0, maximum: 200)

Diffusion steps

Default: 60

scale

number

(minimum: 0, maximum: 32)

Text conditioning scale

Default: 8

upscale_f

integer

Upscaling resolution

Default: 1

init_image_data

string

Shift + Return to add a new line

Load initial image from file, url, or base64 string

init_image_strength

number

(minimum: 0, maximum: 1)

Strength of initial image

Default: 0

init_image_inpaint_mode

string

Inpainting method for pre-processing init_image when it's masked

Default: "cv2_telea"

mask_image_data

string

Shift + Return to add a new line

Load mask image from file, url, or base64 string

mask_invert

boolean

Invert mask

Default: false

text_input

*string

Shift + Return to add a new line

Text input (mode==generate)

uc_text

string

Shift + Return to add a new line

poorly drawn face, ugly, tiling, out of frame, extra limbs, disfigured, deformed body, blurry, blurred, watermark, text, grainy, signature, cut off, draftpoorly drawn face, ugly, tiling, out of frame, extra limbs, disfigured, deformed body, blurry, blurred, watermark, text, grainy, signature, cut off, draft

Negative text input (mode==all)

Default: "poorly drawn face, ugly, tiling, out of frame, extra limbs, disfigured, deformed body, blurry, blurred, watermark, text, grainy, signature, cut off, draft"

seed

integer

(minimum: 0, maximum: 10000000000)

random seed (mode==generate)

Default: 13

n_samples

integer

(minimum: 1, maximum: 4)

batch size (mode==generate)

Default: 1

n_frames

integer

(minimum: 0, maximum: 100)

Total number of frames (mode==interpolate/animate)

Default: 50

interpolation_texts

string

Shift + Return to add a new line

Interpolation texts (mode==interpolate)

interpolation_seeds

string

Shift + Return to add a new line

Seeds for interpolated texts (mode==interpolate)

interpolation_init_images

string

Shift + Return to add a new line

Interpolation init images, file paths or urls (mode==interpolate)

interpolation_init_images_use_img2txt

boolean

Use clip_search to get prompts for the init images, if false use manual interpolation_texts (mode==interpolate)

Default: false

interpolation_init_images_top_k

integer

(minimum: 1, maximum: 10)

Top K for interpolation_init_images prompts (mode==interpolate)

Default: 2

interpolation_init_images_power

number

(minimum: 0, maximum: 8)

Power for interpolation_init_images prompts (mode==interpolate)

Default: 2.5

interpolation_init_images_min_strength

number

(minimum: 0, maximum: 1)

Minimum init image strength for interpolation_init_images prompts (mode==interpolate)

Default: 0.2

scale_modulation

number

(minimum: 0, maximum: 10)

Scale modulation amplitude for interpolation (mode==interpolate)

Default: 0

loop

boolean

Loops (mode==interpolate)

Default: true

smooth

boolean

Smooth (mode==interpolate)

Default: false

n_film

integer

(minimum: 0, maximum: 2)

Number of times to smooth final frames with FILM (default is 0) (mode==interpolate or animate)

Default: 0

fps

integer

(minimum: 1, maximum: 60)

Frames per second (mode==interpolate or animate)

Default: 12

animation_mode

string

Interpolation texts (mode==interpolate)

Default: "2D"

init_video

file

Initial video file (mode==animate)

extract_nth_frame

integer

(minimum: 1, maximum: 10)

Extract each frame of init_video (mode==animate)

Default: 1

turbo_steps

integer

(minimum: 1, maximum: 8)

Turbo steps (mode==animate)

Default: 3

previous_frame_strength

number

(minimum: 0, maximum: 1)

Strength of previous frame (mode==animate)

Default: 0.65

previous_frame_noise

number

(minimum: 0, maximum: 0.2)

How much to noise previous frame (mode==animate)

Default: 0.02

color_coherence

string

Color coherence strategy (mode==animate)

Default: "Match Frame 0 LAB"

contrast

number

(minimum: 0, maximum: 2)

Contrast (mode==animation)

Default: 1

angle

number

(minimum: -2, maximum: 2)

Rotation angle (animation_mode==2D)

Default: 0

zoom

number

(minimum: 0.91, maximum: 1.12)

Zoom (animation_mode==2D)

Default: 1

translation_x

number

(minimum: -5, maximum: 5)

Translation X (animation_mode==3D)

Default: 0

translation_y

number

(minimum: -5, maximum: 5)

Translation U (animation_mode==3D)

Default: 0

translation_z

number

(minimum: -5, maximum: 5)

Translation Z (animation_mode==3D)

Default: 0

rotation_x

number

(minimum: -1, maximum: 1)

Rotation X (animation_mode==3D)

Default: 0

rotation_y

number

(minimum: -1, maximum: 1)

Rotation U (animation_mode==3D)

Default: 0

rotation_z

number

(minimum: -1, maximum: 1)

Rotation Z (animation_mode==3D)

Default: 0

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

npx create-replicate --model=edenartlab/eden-sd-pipelines

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 edenartlab/eden-sd-pipelines using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "edenartlab/eden-sd-pipelines:3e56e23e427a313ebdf4fd9fc1610f333ce0ce99e359a0df3c44942c47e9f91c",
  {
    input: {
      fps: 12,
      loop: true,
      mode: "generate",
      seed: 13,
      zoom: 1,
      angle: 0,
      scale: 8,
      steps: 60,
      width: 512,
      height: 512,
      n_film: 0,
      smooth: false,
      stream: false,
      sampler: "euler",
      uc_text: "poorly drawn face, ugly, tiling, out of frame, extra limbs, disfigured, deformed body, blurry, blurred, watermark, text, grainy, signature, cut off, draft",
      contrast: 1,
      n_frames: 50,
      n_samples: 1,
      upscale_f: 1,
      rotation_x: 0,
      rotation_y: 0,
      rotation_z: 0,
      mask_invert: false,
      turbo_steps: 3,
      stream_every: 1,
      translation_x: 0,
      translation_y: 0,
      translation_z: 0,
      animation_mode: "2D",
      color_coherence: "Match Frame 0 LAB",
      scale_modulation: 0,
      extract_nth_frame: 1,
      init_image_strength: 0,
      previous_frame_noise: 0.02,
      init_image_inpaint_mode: "cv2_telea",
      previous_frame_strength: 0.65,
      interpolation_init_images_power: 2.5,
      interpolation_init_images_top_k: 2,
      interpolation_init_images_use_img2txt: false,
      interpolation_init_images_min_strength: 0.2
    }
  }
);

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 edenartlab/eden-sd-pipelines using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "edenartlab/eden-sd-pipelines:3e56e23e427a313ebdf4fd9fc1610f333ce0ce99e359a0df3c44942c47e9f91c",
    input={
        "fps": 12,
        "loop": True,
        "mode": "generate",
        "seed": 13,
        "zoom": 1,
        "angle": 0,
        "scale": 8,
        "steps": 60,
        "width": 512,
        "height": 512,
        "n_film": 0,
        "smooth": False,
        "stream": False,
        "sampler": "euler",
        "uc_text": "poorly drawn face, ugly, tiling, out of frame, extra limbs, disfigured, deformed body, blurry, blurred, watermark, text, grainy, signature, cut off, draft",
        "contrast": 1,
        "n_frames": 50,
        "n_samples": 1,
        "upscale_f": 1,
        "rotation_x": 0,
        "rotation_y": 0,
        "rotation_z": 0,
        "mask_invert": False,
        "turbo_steps": 3,
        "stream_every": 1,
        "translation_x": 0,
        "translation_y": 0,
        "translation_z": 0,
        "animation_mode": "2D",
        "color_coherence": "Match Frame 0 LAB",
        "scale_modulation": 0,
        "extract_nth_frame": 1,
        "init_image_strength": 0,
        "previous_frame_noise": 0.02,
        "init_image_inpaint_mode": "cv2_telea",
        "previous_frame_strength": 0.65,
        "interpolation_init_images_power": 2.5,
        "interpolation_init_images_top_k": 2,
        "interpolation_init_images_use_img2txt": False,
        "interpolation_init_images_min_strength": 0.2
    }
)

# The edenartlab/eden-sd-pipelines model can stream output as it's running.
# The predict method returns an iterator, and you can iterate over that output.
for item in output:
    # https://replicate.com/edenartlab/eden-sd-pipelines/api#output-schema
    print(item)

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 edenartlab/eden-sd-pipelines 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": "3e56e23e427a313ebdf4fd9fc1610f333ce0ce99e359a0df3c44942c47e9f91c",
    "input": {
      "fps": 12,
      "loop": true,
      "mode": "generate",
      "seed": 13,
      "zoom": 1,
      "angle": 0,
      "scale": 8,
      "steps": 60,
      "width": 512,
      "height": 512,
      "n_film": 0,
      "smooth": false,
      "stream": false,
      "sampler": "euler",
      "uc_text": "poorly drawn face, ugly, tiling, out of frame, extra limbs, disfigured, deformed body, blurry, blurred, watermark, text, grainy, signature, cut off, draft",
      "contrast": 1,
      "n_frames": 50,
      "n_samples": 1,
      "upscale_f": 1,
      "rotation_x": 0,
      "rotation_y": 0,
      "rotation_z": 0,
      "mask_invert": false,
      "turbo_steps": 3,
      "stream_every": 1,
      "translation_x": 0,
      "translation_y": 0,
      "translation_z": 0,
      "animation_mode": "2D",
      "color_coherence": "Match Frame 0 LAB",
      "scale_modulation": 0,
      "extract_nth_frame": 1,
      "init_image_strength": 0,
      "previous_frame_noise": 0.02,
      "init_image_inpaint_mode": "cv2_telea",
      "previous_frame_strength": 0.65,
      "interpolation_init_images_power": 2.5,
      "interpolation_init_images_top_k": 2,
      "interpolation_init_images_use_img2txt": false,
      "interpolation_init_images_min_strength": 0.2
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

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