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

edenartlab / eden-sd-pipelines

Cold

Public
114.9K runs
A100 (80GB)

Run with an API

Playground API Examples README Versions

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: 256, maximum: 2048)

Width

Default: 768

height

integer

(minimum: 256, maximum: 2048)

Height

Default: 768

checkpoint

string

Which Stable Diffusion checkpoint to use

Default: "eden:eden-v1"

lora

string

Shift + Return to add a new line

(optional) URL of Lora finetuning

lora_scale

number

(minimum: 0, maximum: 1.2)

Lora scale (how much of the Lora finetuning to apply)

Default: 0.8

sampler

string

Which sampler to use

Default: "euler"

steps

integer

(minimum: 10, maximum: 100)

Diffusion steps

Default: 60

guidance_scale

number

(minimum: 0, maximum: 30)

Strength of text conditioning guidance

Default: 7.5

upscale_f

number

(minimum: 1, maximum: 2)

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

text_input

*string

Shift + Return to add a new line

Text input (mode==generate)

uc_text

string

Shift + Return to add a new line

watermark, text, nude, naked, nsfw, poorly drawn face, ugly, tiling, out of frame, blurry, blurred, grainy, signature, cut off, draftwatermark, text, nude, naked, nsfw, poorly drawn face, ugly, tiling, out of frame, blurry, blurred, grainy, signature, cut off, draft

Negative text input (mode==all)

Default: "watermark, text, nude, naked, nsfw, poorly drawn face, ugly, tiling, out of frame, blurry, blurred, 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: 3, maximum: 1000)

Total number of frames (mode==interpolate)

Default: 60

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_power

number

(minimum: 0.5, maximum: 5)

Power for interpolation_init_images prompts (mode==interpolate)

Default: 3

interpolation_init_images_min_strength

number

(minimum: 0, maximum: 0.75)

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

Default: 0.25

interpolation_init_images_max_strength

number

(minimum: 0.5, maximum: 1)

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

Default: 0.95

scale_modulation

number

(minimum: 0, maximum: 0.25)

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)

Default: 0

fps

integer

(minimum: 1, maximum: 60)

Frames per second (mode==interpolate)

Default: 12

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:79befe687d0930473e5528b59673890c694250b615e8405bc8f245f906ae8042",
  {
    input: {
      fps: 12,
      loop: true,
      mode: "generate",
      seed: 13,
      steps: 60,
      width: 768,
      height: 768,
      n_film: 0,
      smooth: false,
      stream: false,
      sampler: "euler",
      uc_text: "watermark, text, nude, naked, nsfw, poorly drawn face, ugly, tiling, out of frame, blurry, blurred, grainy, signature, cut off, draft",
      n_frames: 60,
      n_samples: 1,
      upscale_f: 1,
      checkpoint: "eden:eden-v1",
      lora_scale: 0.8,
      stream_every: 1,
      guidance_scale: 7.5,
      scale_modulation: 0,
      init_image_strength: 0,
      interpolation_init_images_power: 3,
      interpolation_init_images_max_strength: 0.95,
      interpolation_init_images_min_strength: 0.25
    }
  }
);

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:79befe687d0930473e5528b59673890c694250b615e8405bc8f245f906ae8042",
    input={
        "fps": 12,
        "loop": True,
        "mode": "generate",
        "seed": 13,
        "steps": 60,
        "width": 768,
        "height": 768,
        "n_film": 0,
        "smooth": False,
        "stream": False,
        "sampler": "euler",
        "uc_text": "watermark, text, nude, naked, nsfw, poorly drawn face, ugly, tiling, out of frame, blurry, blurred, grainy, signature, cut off, draft",
        "n_frames": 60,
        "n_samples": 1,
        "upscale_f": 1,
        "checkpoint": "eden:eden-v1",
        "lora_scale": 0.8,
        "stream_every": 1,
        "guidance_scale": 7.5,
        "scale_modulation": 0,
        "init_image_strength": 0,
        "interpolation_init_images_power": 3,
        "interpolation_init_images_max_strength": 0.95,
        "interpolation_init_images_min_strength": 0.25
    }
)

# 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": "79befe687d0930473e5528b59673890c694250b615e8405bc8f245f906ae8042",
    "input": {
      "fps": 12,
      "loop": true,
      "mode": "generate",
      "seed": 13,
      "steps": 60,
      "width": 768,
      "height": 768,
      "n_film": 0,
      "smooth": false,
      "stream": false,
      "sampler": "euler",
      "uc_text": "watermark, text, nude, naked, nsfw, poorly drawn face, ugly, tiling, out of frame, blurry, blurred, grainy, signature, cut off, draft",
      "n_frames": 60,
      "n_samples": 1,
      "upscale_f": 1,
      "checkpoint": "eden:eden-v1",
      "lora_scale": 0.8,
      "stream_every": 1,
      "guidance_scale": 7.5,
      "scale_modulation": 0,
      "init_image_strength": 0,
      "interpolation_init_images_power": 3,
      "interpolation_init_images_max_strength": 0.95,
      "interpolation_init_images_min_strength": 0.25
    }
  }' \
  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.

Run time and cost

This model costs approximately $0.016 to run on Replicate, or 62 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 A100 (80GB) GPU hardware. Predictions typically complete within 12 seconds.

Readme

…

Model description

…

Intended use

…

Ethical considerations

…

Caveats and recommendations

…