emaph / in-and-outpaint-union

Combines inpainting and outpainting for image editing.

Cold

Public
245 runs
L40S

Run with an API

Playground API Examples README Versions

Input

prompt

string

Shift + Return to add a new line

a man wearing a pink shirt, in the middle of a foggy new york, skyscrapers on the sidea man wearing a pink shirt, in the middle of a foggy new york, skyscrapers on the side

Default: ""

negative_prompt

string

Shift + Return to add a new line

Things you do not want to see in your image

Default: ""

image

file

Preview

The image to inpaint

mask

file

Preview

The image with the masked area to inpaint

left

integer

Outpaint left

Default: 150

right

integer

Outpaint right

Default: 150

top

integer

Outpaint top

Default: 150

bottom

integer

Outpaint bottom

Default: 150

steps

integer

(minimum: 1, maximum: 50)

Number of inference steps

Default: 20

cfg

number

(minimum: 0, maximum: 20)

Guidance scale

Default: 4

output_format

string

Format of the output images

Default: "webp"

output_quality

integer

(minimum: 0, maximum: 100)

Quality of the output images, from 0 to 100. 100 is best quality, 0 is lowest quality.

Default: 80

seed

integer

Set a seed for reproducibility. Random by default.

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

npx create-replicate --model=emaph/in-and-outpaint-union

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 emaph/in-and-outpaint-union using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "emaph/in-and-outpaint-union:3a23360cf7a5675e7f812b477f8c6b0e02266ddc23dbebb3acfa9abd46042f69",
  {
    input: {
      cfg: 4,
      top: 150,
      left: 300,
      mask: "https://replicate.delivery/pbxt/LLgbikVFw1CPcptesJFntZIbdDTdJgT96TgSkmInPPiAwQAp/clipspace-mask-36011.png",
      image: "https://replicate.delivery/pbxt/LLgbi97wIWxt0nUNa0wu9lZbSb0UjRnkX7Xijy6NNmZaTEdL/inoutin.png",
      right: 300,
      steps: 20,
      bottom: 150,
      prompt: "a man wearing a pink shirt, in the middle of a foggy new york, skyscrapers on the side",
      output_format: "webp",
      output_quality: 80,
      negative_prompt: "text, watermark"
    }
  }
);
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 emaph/in-and-outpaint-union using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "emaph/in-and-outpaint-union:3a23360cf7a5675e7f812b477f8c6b0e02266ddc23dbebb3acfa9abd46042f69",
    input={
        "cfg": 4,
        "top": 150,
        "left": 300,
        "mask": "https://replicate.delivery/pbxt/LLgbikVFw1CPcptesJFntZIbdDTdJgT96TgSkmInPPiAwQAp/clipspace-mask-36011.png",
        "image": "https://replicate.delivery/pbxt/LLgbi97wIWxt0nUNa0wu9lZbSb0UjRnkX7Xijy6NNmZaTEdL/inoutin.png",
        "right": 300,
        "steps": 20,
        "bottom": 150,
        "prompt": "a man wearing a pink shirt, in the middle of a foggy new york, skyscrapers on the side",
        "output_format": "webp",
        "output_quality": 80,
        "negative_prompt": "text, watermark"
    }
)
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 emaph/in-and-outpaint-union 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": "3a23360cf7a5675e7f812b477f8c6b0e02266ddc23dbebb3acfa9abd46042f69",
    "input": {
      "cfg": 4,
      "top": 150,
      "left": 300,
      "mask": "https://replicate.delivery/pbxt/LLgbikVFw1CPcptesJFntZIbdDTdJgT96TgSkmInPPiAwQAp/clipspace-mask-36011.png",
      "image": "https://replicate.delivery/pbxt/LLgbi97wIWxt0nUNa0wu9lZbSb0UjRnkX7Xijy6NNmZaTEdL/inoutin.png",
      "right": 300,
      "steps": 20,
      "bottom": 150,
      "prompt": "a man wearing a pink shirt, in the middle of a foggy new york, skyscrapers on the side",
      "output_format": "webp",
      "output_quality": 80,
      "negative_prompt": "text, watermark"
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Install Cog

brew install cog

If you don’t have Homebrew, there are other installation options available.

Pull and run emaph/in-and-outpaint-union using Cog (this will download the full model and run it in your local environment):

cog predict r8.im/emaph/in-and-outpaint-union@sha256:3a23360cf7a5675e7f812b477f8c6b0e02266ddc23dbebb3acfa9abd46042f69 \
  -i 'cfg=4' \
  -i 'top=150' \
  -i 'left=300' \
  -i 'mask="https://replicate.delivery/pbxt/LLgbikVFw1CPcptesJFntZIbdDTdJgT96TgSkmInPPiAwQAp/clipspace-mask-36011.png"' \
  -i 'image="https://replicate.delivery/pbxt/LLgbi97wIWxt0nUNa0wu9lZbSb0UjRnkX7Xijy6NNmZaTEdL/inoutin.png"' \
  -i 'right=300' \
  -i 'steps=20' \
  -i 'bottom=150' \
  -i 'prompt="a man wearing a pink shirt, in the middle of a foggy new york, skyscrapers on the side"' \
  -i 'output_format="webp"' \
  -i 'output_quality=80' \
  -i 'negative_prompt="text, watermark"'

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

Pull and run emaph/in-and-outpaint-union using Docker (this will download the full model and run it in your local environment):

docker run -d -p 5000:5000 --gpus=all r8.im/emaph/in-and-outpaint-union@sha256:3a23360cf7a5675e7f812b477f8c6b0e02266ddc23dbebb3acfa9abd46042f69
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "cfg": 4,
      "top": 150,
      "left": 300,
      "mask": "https://replicate.delivery/pbxt/LLgbikVFw1CPcptesJFntZIbdDTdJgT96TgSkmInPPiAwQAp/clipspace-mask-36011.png",
      "image": "https://replicate.delivery/pbxt/LLgbi97wIWxt0nUNa0wu9lZbSb0UjRnkX7Xijy6NNmZaTEdL/inoutin.png",
      "right": 300,
      "steps": 20,
      "bottom": 150,
      "prompt": "a man wearing a pink shirt, in the middle of a foggy new york, skyscrapers on the side",
      "output_format": "webp",
      "output_quality": 80,
      "negative_prompt": "text, watermark"
    }
  }' \
  http://localhost:5000/predictions

Output

{
  "completed_at": "2024-07-28T20:39:55.149341Z",
  "created_at": "2024-07-28T20:36:55.790000Z",
  "data_removed": false,
  "error": null,
  "id": "739bc641dsrgj0cgzc7s09k8ar",
  "input": {
    "cfg": 4,
    "top": 150,
    "left": 300,
    "mask": "https://replicate.delivery/pbxt/LLgbikVFw1CPcptesJFntZIbdDTdJgT96TgSkmInPPiAwQAp/clipspace-mask-36011.png",
    "image": "https://replicate.delivery/pbxt/LLgbi97wIWxt0nUNa0wu9lZbSb0UjRnkX7Xijy6NNmZaTEdL/inoutin.png",
    "right": 300,
    "steps": 20,
    "bottom": 150,
    "prompt": "a man wearing a pink shirt, in the middle of a foggy new york, skyscrapers on the side",
    "output_format": "webp",
    "output_quality": 80,
    "negative_prompt": "text, watermark"
  },
  "logs": "Random seed set to: 286931823\nChecking inputs\n✅ /tmp/inputs/image.png\n✅ /tmp/inputs/mask.png\n====================================\nChecking weights\n✅ diffusion_pytorch_model_promax.safetensors exists in ComfyUI/models/controlnet\n✅ juggernautXL_v8Rundiffusion.safetensors exists in ComfyUI/models/checkpoints\n====================================\nRunning workflow\ngot prompt\nExecuting node 4, title: Load Checkpoint, class type: CheckpointLoaderSimple\nmodel_type EPS\nUsing pytorch attention in VAE\nUsing pytorch attention in VAE\nloaded straight to GPU\nRequested to load SDXL\nLoading 1 new model\nExecuting node 6, title: Positive, class type: CLIPTextEncode\nRequested to load SDXLClipModel\nLoading 1 new model\nExecuting node 7, title: Negetive, class type: CLIPTextEncode\nExecuting node 16, title: Load ControlNet Model, class type: ControlNetLoader\nExecuting node 17, title: SetUnionControlNetType, class type: SetUnionControlNetType\nExecuting node 11, title: Load Image, class type: LoadImage\nExecuting node 71, title: Load Image Mask, class type: LoadImage\nExecuting node 50, title: InvertMask, class type: InvertMask\nExecuting node 48, title: Convert Mask to Image, class type: MaskToImage\nExecuting node 54, title: ImageCompositeMasked, class type: ImageCompositeMasked\nExecuting node 75, title: Pad Image for Outpainting, class type: ImagePadForOutpaint\nExecuting node 78, title: InvertMask, class type: InvertMask\nExecuting node 77, title: Convert Mask to Image, class type: MaskToImage\nExecuting node 79, title: ImageCompositeMasked, class type: ImageCompositeMasked\nExecuting node 15, title: Apply ControlNet (Advanced), class type: ControlNetApplyAdvanced\nExecuting node 51, title: VAE Encode, class type: VAEEncode\nRequested to load AutoencoderKL\nLoading 1 new model\nRequested to load ControlNet\nLoading 1 new model\nExecuting node 3, title: KSampler, class type: KSampler\n  0%|          | 0/20 [00:00<?, ?it/s]\n  5%|▌         | 1/20 [00:00<00:12,  1.57it/s]\n 10%|█         | 2/20 [00:01<00:10,  1.68it/s]\n 15%|█▌        | 3/20 [00:01<00:09,  1.72it/s]\n 20%|██        | 4/20 [00:02<00:09,  1.74it/s]\n 25%|██▌       | 5/20 [00:02<00:08,  1.75it/s]\n 30%|███       | 6/20 [00:03<00:07,  1.75it/s]\n 35%|███▌      | 7/20 [00:04<00:07,  1.76it/s]\n 40%|████      | 8/20 [00:04<00:06,  1.76it/s]\n 45%|████▌     | 9/20 [00:05<00:06,  1.76it/s]\n 50%|█████     | 10/20 [00:05<00:05,  1.76it/s]\n 55%|█████▌    | 11/20 [00:06<00:05,  1.76it/s]\n 60%|██████    | 12/20 [00:06<00:04,  1.76it/s]\n 65%|██████▌   | 13/20 [00:07<00:03,  1.77it/s]\n 70%|███████   | 14/20 [00:07<00:03,  1.77it/s]\n 75%|███████▌  | 15/20 [00:08<00:02,  1.77it/s]\n 80%|████████  | 16/20 [00:09<00:02,  1.58it/s]\n 85%|████████▌ | 17/20 [00:09<00:01,  1.62it/s]\n 90%|█████████ | 18/20 [00:10<00:01,  1.46it/s]\n 95%|█████████▌| 19/20 [00:11<00:00,  1.41it/s]\n100%|██████████| 20/20 [00:12<00:00,  1.50it/s]\n100%|██████████| 20/20 [00:12<00:00,  1.65it/s]\nExecuting node 8, title: VAE Decode, class type: VAEDecode\nExecuting node 74, title: Save Image, class type: SaveImage\nPrompt executed in 16.87 seconds\noutputs:  {'74': {'images': [{'filename': 'edited_00001_.png', 'subfolder': '', 'type': 'output'}]}}\n====================================\nedited_00001_.png",
  "metrics": {
    "predict_time": 20.844022075,
    "total_time": 179.359341
  },
  "output": [
    "https://replicate.delivery/pbxt/1UGdvhFDzDZKNl6pb4Jbzaq98cRvACBesCLlH24TLIIN9imJA/edited_00001_.webp"
  ],
  "started_at": "2024-07-28T20:39:34.305319Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/739bc641dsrgj0cgzc7s09k8ar",
    "cancel": "https://api.replicate.com/v1/predictions/739bc641dsrgj0cgzc7s09k8ar/cancel"
  },
  "version": "3a23360cf7a5675e7f812b477f8c6b0e02266ddc23dbebb3acfa9abd46042f69"
}

Generated in

20.9 seconds

Tweak it ShareReport

Random seed set to: 286931823
Checking inputs
✅ /tmp/inputs/image.png
✅ /tmp/inputs/mask.png
====================================
Checking weights
✅ diffusion_pytorch_model_promax.safetensors exists in ComfyUI/models/controlnet
✅ juggernautXL_v8Rundiffusion.safetensors exists in ComfyUI/models/checkpoints
====================================
Running workflow
got prompt
Executing node 4, title: Load Checkpoint, class type: CheckpointLoaderSimple
model_type EPS
Using pytorch attention in VAE
Using pytorch attention in VAE
loaded straight to GPU
Requested to load SDXL
Loading 1 new model
Executing node 6, title: Positive, class type: CLIPTextEncode
Requested to load SDXLClipModel
Loading 1 new model
Executing node 7, title: Negetive, class type: CLIPTextEncode
Executing node 16, title: Load ControlNet Model, class type: ControlNetLoader
Executing node 17, title: SetUnionControlNetType, class type: SetUnionControlNetType
Executing node 11, title: Load Image, class type: LoadImage
Executing node 71, title: Load Image Mask, class type: LoadImage
Executing node 50, title: InvertMask, class type: InvertMask
Executing node 48, title: Convert Mask to Image, class type: MaskToImage
Executing node 54, title: ImageCompositeMasked, class type: ImageCompositeMasked
Executing node 75, title: Pad Image for Outpainting, class type: ImagePadForOutpaint
Executing node 78, title: InvertMask, class type: InvertMask
Executing node 77, title: Convert Mask to Image, class type: MaskToImage
Executing node 79, title: ImageCompositeMasked, class type: ImageCompositeMasked
Executing node 15, title: Apply ControlNet (Advanced), class type: ControlNetApplyAdvanced
Executing node 51, title: VAE Encode, class type: VAEEncode
Requested to load AutoencoderKL
Loading 1 new model
Requested to load ControlNet
Loading 1 new model
Executing node 3, title: KSampler, class type: KSampler
  0%|          | 0/20 [00:00<?, ?it/s]
  5%|▌         | 1/20 [00:00<00:12,  1.57it/s]
 10%|█         | 2/20 [00:01<00:10,  1.68it/s]
 15%|█▌        | 3/20 [00:01<00:09,  1.72it/s]
 20%|██        | 4/20 [00:02<00:09,  1.74it/s]
 25%|██▌       | 5/20 [00:02<00:08,  1.75it/s]
 30%|███       | 6/20 [00:03<00:07,  1.75it/s]
 35%|███▌      | 7/20 [00:04<00:07,  1.76it/s]
 40%|████      | 8/20 [00:04<00:06,  1.76it/s]
 45%|████▌     | 9/20 [00:05<00:06,  1.76it/s]
 50%|█████     | 10/20 [00:05<00:05,  1.76it/s]
 55%|█████▌    | 11/20 [00:06<00:05,  1.76it/s]
 60%|██████    | 12/20 [00:06<00:04,  1.76it/s]
 65%|██████▌   | 13/20 [00:07<00:03,  1.77it/s]
 70%|███████   | 14/20 [00:07<00:03,  1.77it/s]
 75%|███████▌  | 15/20 [00:08<00:02,  1.77it/s]
 80%|████████  | 16/20 [00:09<00:02,  1.58it/s]
 85%|████████▌ | 17/20 [00:09<00:01,  1.62it/s]
 90%|█████████ | 18/20 [00:10<00:01,  1.46it/s]
 95%|█████████▌| 19/20 [00:11<00:00,  1.41it/s]
100%|██████████| 20/20 [00:12<00:00,  1.50it/s]
100%|██████████| 20/20 [00:12<00:00,  1.65it/s]
Executing node 8, title: VAE Decode, class type: VAEDecode
Executing node 74, title: Save Image, class type: SaveImage
Prompt executed in 16.87 seconds
outputs:  {'74': {'images': [{'filename': 'edited_00001_.png', 'subfolder': '', 'type': 'output'}]}}
====================================
edited_00001_.png

Examples

View more examples

Run time and cost

This model runs on Nvidia L40S GPU hardware. We don't yet have enough runs of this model to provide performance information.

Readme

Combines inpainting and outpainting with controlnet++ union for sdxl.

ControlNet++: All-in-one ControlNet for image generations and editing!

ProMax Model has released!! 12 control + 5 advanced editing, just try it!!!

Advantages about the model

Use bucket training like novelai, can generate high resolutions images of any aspect ratio
Use large amount of high quality data(over 10000000 images), the dataset covers a diversity of situation
Use re-captioned prompt like DALLE.3, use CogVLM to generate detailed description, good prompt following ability
Use many useful tricks during training. Including but not limited to date augmentation, mutiple loss, multi resolution
Use almost the same parameter compared with original ControlNet. No obvious increase in network parameter or computation.
Support 10+ control conditions, no obvious performance drop on any single condition compared with training independently
Support multi condition generation, condition fusion is learned during training. No need to set hyperparameter or design prompts.
Compatible with other opensource SDXL models, such as BluePencilXL, CounterfeitXL. Compatible with other Lora models.

Inference scripts and more details can found: https://github.com/xinsir6/ControlNetPlus/tree/main

emaph / in-and-outpaint-union

Input

Output

Examples

Run time and cost

Readme

ControlNet++: All-in-one ControlNet for image generations and editing!

ProMax Model has released!! 12 control + 5 advanced editing, just try it!!!

Advantages about the model

Image Inpainting

Image Outpainting

Logs (739bc641dsrgj0cgzc7s09k8ar)