edenartlab/eden-sd-pipelines:2fb1270a – 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:2fb1270a

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: 2048)

Width

Default: 512

height

integer

(minimum: 64, maximum: 2048)

Height

Default: 512

checkpoint

string

Which Stable Diffusion checkpoint to use

Default: "dreamlike-art/dreamlike-photoreal-2.0"

lora

string

Shift + Return to add a new line

(optional) URL of Lora finetuning

lora_scale

number

(minimum: 0, maximum: 1)

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

Default: 0.8

sampler

string

Which sampler to use

Default: "euler"

steps

integer

(minimum: 0, maximum: 200)

Diffusion steps

Default: 60

guidance_scale

number

(minimum: 0, maximum: 32)

Strength of text conditioning guidance

Default: 10

upscale_f

integer

(minimum: 1, maximum: 4)

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

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)

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_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)

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:2fb1270a2ecc7d061f6e659f1dab472e44248d242c1a1f52557df05a843a9550",
  {
    input: {
      fps: 12,
      loop: true,
      mode: "generate",
      seed: 13,
      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",
      n_frames: 50,
      n_samples: 1,
      upscale_f: 1,
      checkpoint: "dreamlike-art/dreamlike-photoreal-2.0",
      lora_scale: 0.8,
      stream_every: 1,
      guidance_scale: 10,
      scale_modulation: 0,
      init_image_strength: 0,
      interpolation_init_images_power: 2.5,
      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:2fb1270a2ecc7d061f6e659f1dab472e44248d242c1a1f52557df05a843a9550",
    input={
        "fps": 12,
        "loop": True,
        "mode": "generate",
        "seed": 13,
        "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",
        "n_frames": 50,
        "n_samples": 1,
        "upscale_f": 1,
        "checkpoint": "dreamlike-art/dreamlike-photoreal-2.0",
        "lora_scale": 0.8,
        "stream_every": 1,
        "guidance_scale": 10,
        "scale_modulation": 0,
        "init_image_strength": 0,
        "interpolation_init_images_power": 2.5,
        "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": "2fb1270a2ecc7d061f6e659f1dab472e44248d242c1a1f52557df05a843a9550",
    "input": {
      "fps": 12,
      "loop": true,
      "mode": "generate",
      "seed": 13,
      "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",
      "n_frames": 50,
      "n_samples": 1,
      "upscale_f": 1,
      "checkpoint": "dreamlike-art/dreamlike-photoreal-2.0",
      "lora_scale": 0.8,
      "stream_every": 1,
      "guidance_scale": 10,
      "scale_modulation": 0,
      "init_image_strength": 0,
      "interpolation_init_images_power": 2.5,
      "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.

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/abraham-ai/eden-sd-pipelines@sha256:2fb1270a2ecc7d061f6e659f1dab472e44248d242c1a1f52557df05a843a9550 \
  -i 'fps=12' \
  -i 'loop=true' \
  -i 'mode="generate"' \
  -i 'seed=13' \
  -i 'steps=60' \
  -i 'width=512' \
  -i 'height=512' \
  -i 'n_film=0' \
  -i 'smooth=false' \
  -i 'stream=false' \
  -i 'sampler="euler"' \
  -i 'uc_text="poorly drawn face, ugly, tiling, out of frame, extra limbs, disfigured, deformed body, blurry, blurred, watermark, text, grainy, signature, cut off, draft"' \
  -i 'n_frames=50' \
  -i 'n_samples=1' \
  -i 'upscale_f=1' \
  -i 'checkpoint="dreamlike-art/dreamlike-photoreal-2.0"' \
  -i 'lora_scale=0.8' \
  -i 'stream_every=1' \
  -i 'guidance_scale=10' \
  -i 'scale_modulation=0' \
  -i 'init_image_strength=0' \
  -i 'interpolation_init_images_power=2.5' \
  -i 'interpolation_init_images_min_strength=0.2'

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/abraham-ai/eden-sd-pipelines@sha256:2fb1270a2ecc7d061f6e659f1dab472e44248d242c1a1f52557df05a843a9550
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "fps": 12,
      "loop": true,
      "mode": "generate",
      "seed": 13,
      "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",
      "n_frames": 50,
      "n_samples": 1,
      "upscale_f": 1,
      "checkpoint": "dreamlike-art/dreamlike-photoreal-2.0",
      "lora_scale": 0.8,
      "stream_every": 1,
      "guidance_scale": 10,
      "scale_modulation": 0,
      "init_image_strength": 0,
      "interpolation_init_images_power": 2.5,
      "interpolation_init_images_min_strength": 0.2
    }
  }' \
  http://localhost:5000/predictions

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

Output

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