Prediction

cjwbw/blipdiffusion:501be8d57d86d63f9b9a06f8ea6d7a051ec7a7a7fc7b71d63764c8fb49a4fcfc

Model

cjwbw/blipdiffusion:501be8d5

ID

ob7mjq3bkttx5vdh5pkn6rhnwe

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

2.6s

Created

over 1 year ago

Input

width: 512
height: 512
prompt: eating ramen
guidance_scale: 7.5
negative_prompt: over-exposure, under-exposure, saturated, duplicate, out of frame, lowres, cropped, worst quality, low quality, jpeg artifacts, morbid, mutilated, ugly, bad anatomy, bad proportions, deformed, blurry
reference_image
num_inference_steps: 25
source_subject_category: dog
target_subject_category: dog

{
  "width": 512,
  "height": 512,
  "prompt": "eating ramen",
  "guidance_scale": 7.5,
  "negative_prompt": "over-exposure, under-exposure, saturated, duplicate, out of frame, lowres, cropped, worst quality, low quality, jpeg artifacts, morbid, mutilated, ugly, bad anatomy, bad proportions, deformed, blurry",
  "reference_image": "https://replicate.delivery/pbxt/KNZcJhVZuWiMWYReUDO2J0Up9CrBN7NmubFg2ZHADbJ5tP9c/dog.png",
  "num_inference_steps": 25,
  "source_subject_category": "dog",
  "target_subject_category": "dog"
}

Install Replicate’s Node.js client library:

npm install replicate

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

const output = await replicate.run(
  "cjwbw/blipdiffusion:501be8d57d86d63f9b9a06f8ea6d7a051ec7a7a7fc7b71d63764c8fb49a4fcfc",
  {
    input: {
      width: 512,
      height: 512,
      prompt: "eating ramen",
      guidance_scale: 7.5,
      negative_prompt: "over-exposure, under-exposure, saturated, duplicate, out of frame, lowres, cropped, worst quality, low quality, jpeg artifacts, morbid, mutilated, ugly, bad anatomy, bad proportions, deformed, blurry",
      reference_image: "https://replicate.delivery/pbxt/KNZcJhVZuWiMWYReUDO2J0Up9CrBN7NmubFg2ZHADbJ5tP9c/dog.png",
      num_inference_steps: 25,
      source_subject_category: "dog",
      target_subject_category: "dog"
    }
  }
);

// To access the file URL:
console.log(output.url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", 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

Import the client:

import replicate

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

output = replicate.run(
    "cjwbw/blipdiffusion:501be8d57d86d63f9b9a06f8ea6d7a051ec7a7a7fc7b71d63764c8fb49a4fcfc",
    input={
        "width": 512,
        "height": 512,
        "prompt": "eating ramen",
        "guidance_scale": 7.5,
        "negative_prompt": "over-exposure, under-exposure, saturated, duplicate, out of frame, lowres, cropped, worst quality, low quality, jpeg artifacts, morbid, mutilated, ugly, bad anatomy, bad proportions, deformed, blurry",
        "reference_image": "https://replicate.delivery/pbxt/KNZcJhVZuWiMWYReUDO2J0Up9CrBN7NmubFg2ZHADbJ5tP9c/dog.png",
        "num_inference_steps": 25,
        "source_subject_category": "dog",
        "target_subject_category": "dog"
    }
)

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

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

To learn more, take a look at the guide on getting started with Python.

Run cjwbw/blipdiffusion 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": "cjwbw/blipdiffusion:501be8d57d86d63f9b9a06f8ea6d7a051ec7a7a7fc7b71d63764c8fb49a4fcfc",
    "input": {
      "width": 512,
      "height": 512,
      "prompt": "eating ramen",
      "guidance_scale": 7.5,
      "negative_prompt": "over-exposure, under-exposure, saturated, duplicate, out of frame, lowres, cropped, worst quality, low quality, jpeg artifacts, morbid, mutilated, ugly, bad anatomy, bad proportions, deformed, blurry",
      "reference_image": "https://replicate.delivery/pbxt/KNZcJhVZuWiMWYReUDO2J0Up9CrBN7NmubFg2ZHADbJ5tP9c/dog.png",
      "num_inference_steps": 25,
      "source_subject_category": "dog",
      "target_subject_category": "dog"
    }
  }' \
  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/chenxwh/blipdiffusion@sha256:501be8d57d86d63f9b9a06f8ea6d7a051ec7a7a7fc7b71d63764c8fb49a4fcfc \
  -i 'width=512' \
  -i 'height=512' \
  -i 'prompt="eating ramen"' \
  -i 'guidance_scale=7.5' \
  -i 'negative_prompt="over-exposure, under-exposure, saturated, duplicate, out of frame, lowres, cropped, worst quality, low quality, jpeg artifacts, morbid, mutilated, ugly, bad anatomy, bad proportions, deformed, blurry"' \
  -i 'reference_image="https://replicate.delivery/pbxt/KNZcJhVZuWiMWYReUDO2J0Up9CrBN7NmubFg2ZHADbJ5tP9c/dog.png"' \
  -i 'num_inference_steps=25' \
  -i 'source_subject_category="dog"' \
  -i 'target_subject_category="dog"'

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/chenxwh/blipdiffusion@sha256:501be8d57d86d63f9b9a06f8ea6d7a051ec7a7a7fc7b71d63764c8fb49a4fcfc
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "width": 512,
      "height": 512,
      "prompt": "eating ramen",
      "guidance_scale": 7.5,
      "negative_prompt": "over-exposure, under-exposure, saturated, duplicate, out of frame, lowres, cropped, worst quality, low quality, jpeg artifacts, morbid, mutilated, ugly, bad anatomy, bad proportions, deformed, blurry",
      "reference_image": "https://replicate.delivery/pbxt/KNZcJhVZuWiMWYReUDO2J0Up9CrBN7NmubFg2ZHADbJ5tP9c/dog.png",
      "num_inference_steps": 25,
      "source_subject_category": "dog",
      "target_subject_category": "dog"
    }
  }' \
  http://localhost:5000/predictions

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

Output

Generated in

2.6 seconds

Tweak it Iterate in playground Share Report

Prediction

cjwbw/blipdiffusion:81a70441392af1288983861c01b09317acfc5eb5ba1343e86a2578487b26620f

Model

cjwbw/blipdiffusion:81a70441

ID

3daa7ydbsyu7averijiuedlpqq

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

79.3s

Created

over 1 year ago

Input

prompt: swimming underwater
guidance_scale: 7.5
negative_prompt: over-exposure, under-exposure, saturated, duplicate, out of frame, lowres, cropped, worst quality, low quality, jpeg artifacts, morbid, mutilated, ugly, bad anatomy, bad proportions, deformed, blurry
reference_image
num_inference_steps: 50
source_subject_category: dog
target_subject_category: dog

{
  "prompt": "swimming underwater",
  "guidance_scale": 7.5,
  "negative_prompt": "over-exposure, under-exposure, saturated, duplicate, out of frame, lowres, cropped, worst quality, low quality, jpeg artifacts, morbid, mutilated, ugly, bad anatomy, bad proportions, deformed, blurry",
  "reference_image": "https://replicate.delivery/pbxt/KNZcJhVZuWiMWYReUDO2J0Up9CrBN7NmubFg2ZHADbJ5tP9c/dog.png",
  "num_inference_steps": 50,
  "source_subject_category": "dog",
  "target_subject_category": "dog"
}

Install Replicate’s Node.js client library:

npm install replicate

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

const output = await replicate.run(
  "cjwbw/blipdiffusion:81a70441392af1288983861c01b09317acfc5eb5ba1343e86a2578487b26620f",
  {
    input: {
      prompt: "swimming underwater",
      guidance_scale: 7.5,
      negative_prompt: "over-exposure, under-exposure, saturated, duplicate, out of frame, lowres, cropped, worst quality, low quality, jpeg artifacts, morbid, mutilated, ugly, bad anatomy, bad proportions, deformed, blurry",
      reference_image: "https://replicate.delivery/pbxt/KNZcJhVZuWiMWYReUDO2J0Up9CrBN7NmubFg2ZHADbJ5tP9c/dog.png",
      num_inference_steps: 50,
      source_subject_category: "dog",
      target_subject_category: "dog"
    }
  }
);

// To access the file URL:
console.log(output.url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", 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

Import the client:

import replicate

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

output = replicate.run(
    "cjwbw/blipdiffusion:81a70441392af1288983861c01b09317acfc5eb5ba1343e86a2578487b26620f",
    input={
        "prompt": "swimming underwater",
        "guidance_scale": 7.5,
        "negative_prompt": "over-exposure, under-exposure, saturated, duplicate, out of frame, lowres, cropped, worst quality, low quality, jpeg artifacts, morbid, mutilated, ugly, bad anatomy, bad proportions, deformed, blurry",
        "reference_image": "https://replicate.delivery/pbxt/KNZcJhVZuWiMWYReUDO2J0Up9CrBN7NmubFg2ZHADbJ5tP9c/dog.png",
        "num_inference_steps": 50,
        "source_subject_category": "dog",
        "target_subject_category": "dog"
    }
)

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

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

To learn more, take a look at the guide on getting started with Python.

Run cjwbw/blipdiffusion 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": "cjwbw/blipdiffusion:81a70441392af1288983861c01b09317acfc5eb5ba1343e86a2578487b26620f",
    "input": {
      "prompt": "swimming underwater",
      "guidance_scale": 7.5,
      "negative_prompt": "over-exposure, under-exposure, saturated, duplicate, out of frame, lowres, cropped, worst quality, low quality, jpeg artifacts, morbid, mutilated, ugly, bad anatomy, bad proportions, deformed, blurry",
      "reference_image": "https://replicate.delivery/pbxt/KNZcJhVZuWiMWYReUDO2J0Up9CrBN7NmubFg2ZHADbJ5tP9c/dog.png",
      "num_inference_steps": 50,
      "source_subject_category": "dog",
      "target_subject_category": "dog"
    }
  }' \
  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/chenxwh/blipdiffusion@sha256:81a70441392af1288983861c01b09317acfc5eb5ba1343e86a2578487b26620f \
  -i 'prompt="swimming underwater"' \
  -i 'guidance_scale=7.5' \
  -i 'negative_prompt="over-exposure, under-exposure, saturated, duplicate, out of frame, lowres, cropped, worst quality, low quality, jpeg artifacts, morbid, mutilated, ugly, bad anatomy, bad proportions, deformed, blurry"' \
  -i 'reference_image="https://replicate.delivery/pbxt/KNZcJhVZuWiMWYReUDO2J0Up9CrBN7NmubFg2ZHADbJ5tP9c/dog.png"' \
  -i 'num_inference_steps=50' \
  -i 'source_subject_category="dog"' \
  -i 'target_subject_category="dog"'

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/chenxwh/blipdiffusion@sha256:81a70441392af1288983861c01b09317acfc5eb5ba1343e86a2578487b26620f
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "prompt": "swimming underwater",
      "guidance_scale": 7.5,
      "negative_prompt": "over-exposure, under-exposure, saturated, duplicate, out of frame, lowres, cropped, worst quality, low quality, jpeg artifacts, morbid, mutilated, ugly, bad anatomy, bad proportions, deformed, blurry",
      "reference_image": "https://replicate.delivery/pbxt/KNZcJhVZuWiMWYReUDO2J0Up9CrBN7NmubFg2ZHADbJ5tP9c/dog.png",
      "num_inference_steps": 50,
      "source_subject_category": "dog",
      "target_subject_category": "dog"
    }
  }' \
  http://localhost:5000/predictions

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

Output

{
  "completed_at": "2024-02-10T15:17:47.934133Z",
  "created_at": "2024-02-10T15:16:28.691482Z",
  "data_removed": false,
  "error": null,
  "id": "3daa7ydbsyu7averijiuedlpqq",
  "input": {
    "prompt": "swimming underwater",
    "guidance_scale": 7.5,
    "negative_prompt": "over-exposure, under-exposure, saturated, duplicate, out of frame, lowres, cropped, worst quality, low quality, jpeg artifacts, morbid, mutilated, ugly, bad anatomy, bad proportions, deformed, blurry",
    "reference_image": "https://replicate.delivery/pbxt/KNZcJhVZuWiMWYReUDO2J0Up9CrBN7NmubFg2ZHADbJ5tP9c/dog.png",
    "num_inference_steps": 50,
    "source_subject_category": "dog",
    "target_subject_category": "dog"
  },
  "logs": "Using seed: 49496\n  0%|          | 0/51 [00:00<?, ?it/s]\n  2%|▏         | 1/51 [00:00<00:06,  7.87it/s]\n  8%|▊         | 4/51 [00:00<00:02, 19.08it/s]\n 14%|█▎        | 7/51 [00:00<00:02, 21.93it/s]\n 20%|█▉        | 10/51 [00:00<00:01, 23.13it/s]\n 25%|██▌       | 13/51 [00:00<00:01, 23.93it/s]\n 31%|███▏      | 16/51 [00:00<00:01, 24.24it/s]\n 37%|███▋      | 19/51 [00:00<00:01, 24.38it/s]\n 43%|████▎     | 22/51 [00:00<00:01, 24.68it/s]\n 49%|████▉     | 25/51 [00:01<00:01, 24.74it/s]\n 55%|█████▍    | 28/51 [00:01<00:00, 24.76it/s]\n 61%|██████    | 31/51 [00:01<00:00, 24.79it/s]\n 67%|██████▋   | 34/51 [00:01<00:00, 24.87it/s]\n 73%|███████▎  | 37/51 [00:01<00:00, 24.92it/s]\n 78%|███████▊  | 40/51 [00:01<00:00, 24.96it/s]\n 84%|████████▍ | 43/51 [00:01<00:00, 24.89it/s]\n 90%|█████████ | 46/51 [00:01<00:00, 24.98it/s]\n 96%|█████████▌| 49/51 [00:02<00:00, 24.98it/s]\n100%|██████████| 51/51 [00:02<00:00, 24.12it/s]",
  "metrics": {
    "predict_time": 3.877075,
    "total_time": 79.242651
  },
  "output": "https://replicate.delivery/pbxt/veCAqO2Ne3jEYUdfBwATq5G2J4dbpwyq0TF0kYLaC6g0soqkA/out.png",
  "started_at": "2024-02-10T15:17:44.057058Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/3daa7ydbsyu7averijiuedlpqq",
    "cancel": "https://api.replicate.com/v1/predictions/3daa7ydbsyu7averijiuedlpqq/cancel"
  },
  "version": "81a70441392af1288983861c01b09317acfc5eb5ba1343e86a2578487b26620f"
}

Generated in

3.9 seconds

Tweak it Iterate in playground Share Report

Prediction

cjwbw/blipdiffusion:501be8d57d86d63f9b9a06f8ea6d7a051ec7a7a7fc7b71d63764c8fb49a4fcfc

Model

cjwbw/blipdiffusion:501be8d5

ID

kyvlgylb5jbdi3khmmjotened4

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

1m 39s

Created

over 1 year ago

Input

width: 512
height: 512
prompt: painting by Van Gogh
guidance_scale: 7.5
negative_prompt: over-exposure, under-exposure, saturated, duplicate, out of frame, lowres, cropped, worst quality, low quality, jpeg artifacts, morbid, mutilated, ugly, bad anatomy, bad proportions, deformed, blurry
reference_image
num_inference_steps: 25
source_subject_category: dog
target_subject_category: dog

{
  "width": 512,
  "height": 512,
  "prompt": "painting by Van Gogh",
  "guidance_scale": 7.5,
  "negative_prompt": "over-exposure, under-exposure, saturated, duplicate, out of frame, lowres, cropped, worst quality, low quality, jpeg artifacts, morbid, mutilated, ugly, bad anatomy, bad proportions, deformed, blurry",
  "reference_image": "https://replicate.delivery/pbxt/KNZcJhVZuWiMWYReUDO2J0Up9CrBN7NmubFg2ZHADbJ5tP9c/dog.png",
  "num_inference_steps": 25,
  "source_subject_category": "dog",
  "target_subject_category": "dog"
}

Install Replicate’s Node.js client library:

npm install replicate

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

const output = await replicate.run(
  "cjwbw/blipdiffusion:501be8d57d86d63f9b9a06f8ea6d7a051ec7a7a7fc7b71d63764c8fb49a4fcfc",
  {
    input: {
      width: 512,
      height: 512,
      prompt: "painting by Van Gogh",
      guidance_scale: 7.5,
      negative_prompt: "over-exposure, under-exposure, saturated, duplicate, out of frame, lowres, cropped, worst quality, low quality, jpeg artifacts, morbid, mutilated, ugly, bad anatomy, bad proportions, deformed, blurry",
      reference_image: "https://replicate.delivery/pbxt/KNZcJhVZuWiMWYReUDO2J0Up9CrBN7NmubFg2ZHADbJ5tP9c/dog.png",
      num_inference_steps: 25,
      source_subject_category: "dog",
      target_subject_category: "dog"
    }
  }
);

// To access the file URL:
console.log(output.url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", 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

Import the client:

import replicate

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

output = replicate.run(
    "cjwbw/blipdiffusion:501be8d57d86d63f9b9a06f8ea6d7a051ec7a7a7fc7b71d63764c8fb49a4fcfc",
    input={
        "width": 512,
        "height": 512,
        "prompt": "painting by Van Gogh",
        "guidance_scale": 7.5,
        "negative_prompt": "over-exposure, under-exposure, saturated, duplicate, out of frame, lowres, cropped, worst quality, low quality, jpeg artifacts, morbid, mutilated, ugly, bad anatomy, bad proportions, deformed, blurry",
        "reference_image": "https://replicate.delivery/pbxt/KNZcJhVZuWiMWYReUDO2J0Up9CrBN7NmubFg2ZHADbJ5tP9c/dog.png",
        "num_inference_steps": 25,
        "source_subject_category": "dog",
        "target_subject_category": "dog"
    }
)

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

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

To learn more, take a look at the guide on getting started with Python.

Run cjwbw/blipdiffusion 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": "cjwbw/blipdiffusion:501be8d57d86d63f9b9a06f8ea6d7a051ec7a7a7fc7b71d63764c8fb49a4fcfc",
    "input": {
      "width": 512,
      "height": 512,
      "prompt": "painting by Van Gogh",
      "guidance_scale": 7.5,
      "negative_prompt": "over-exposure, under-exposure, saturated, duplicate, out of frame, lowres, cropped, worst quality, low quality, jpeg artifacts, morbid, mutilated, ugly, bad anatomy, bad proportions, deformed, blurry",
      "reference_image": "https://replicate.delivery/pbxt/KNZcJhVZuWiMWYReUDO2J0Up9CrBN7NmubFg2ZHADbJ5tP9c/dog.png",
      "num_inference_steps": 25,
      "source_subject_category": "dog",
      "target_subject_category": "dog"
    }
  }' \
  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/chenxwh/blipdiffusion@sha256:501be8d57d86d63f9b9a06f8ea6d7a051ec7a7a7fc7b71d63764c8fb49a4fcfc \
  -i 'width=512' \
  -i 'height=512' \
  -i 'prompt="painting by Van Gogh"' \
  -i 'guidance_scale=7.5' \
  -i 'negative_prompt="over-exposure, under-exposure, saturated, duplicate, out of frame, lowres, cropped, worst quality, low quality, jpeg artifacts, morbid, mutilated, ugly, bad anatomy, bad proportions, deformed, blurry"' \
  -i 'reference_image="https://replicate.delivery/pbxt/KNZcJhVZuWiMWYReUDO2J0Up9CrBN7NmubFg2ZHADbJ5tP9c/dog.png"' \
  -i 'num_inference_steps=25' \
  -i 'source_subject_category="dog"' \
  -i 'target_subject_category="dog"'

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/chenxwh/blipdiffusion@sha256:501be8d57d86d63f9b9a06f8ea6d7a051ec7a7a7fc7b71d63764c8fb49a4fcfc
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "width": 512,
      "height": 512,
      "prompt": "painting by Van Gogh",
      "guidance_scale": 7.5,
      "negative_prompt": "over-exposure, under-exposure, saturated, duplicate, out of frame, lowres, cropped, worst quality, low quality, jpeg artifacts, morbid, mutilated, ugly, bad anatomy, bad proportions, deformed, blurry",
      "reference_image": "https://replicate.delivery/pbxt/KNZcJhVZuWiMWYReUDO2J0Up9CrBN7NmubFg2ZHADbJ5tP9c/dog.png",
      "num_inference_steps": 25,
      "source_subject_category": "dog",
      "target_subject_category": "dog"
    }
  }' \
  http://localhost:5000/predictions

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

Output

Generated in

3.3 seconds

Tweak it Iterate in playground Share Report

Prediction

Input

Output

Prediction

Input

Output

Prediction

Input

Output

Logs (ob7mjq3bkttx5vdh5pkn6rhnwe)

Logs (3daa7ydbsyu7averijiuedlpqq)

Logs (kyvlgylb5jbdi3khmmjotened4)