cedoysch/flux-fill-redux-try-on – Run with an API on Replicate

cedoysch / flux-fill-redux-try-on

Virtual fitting of clothes

Cold

Public
113 runs
L40S

Run with an API

Playground API Examples README Versions

Input

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

npx create-replicate --model=cedoysch/flux-fill-redux-try-on

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 cedoysch/flux-fill-redux-try-on using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "cedoysch/flux-fill-redux-try-on:cf5cb07a25e726fe2fac166a8c5ab52ddccd48657741670fb09d9954d4d8446f",
  {
    input: {
      cloth_type: "upper",
      cloth_image: "https://replicate.delivery/pbxt/MjVInxdHWaHcHcbQcmiEyf7vm9gMwo59uItGH3vYAaK1G1ir/example_jacket.png",
      person_image: "https://replicate.delivery/pbxt/MjVIo8ENgFG5SBbMep5WKSJFakH3AxBX9YDzROldiNVK53VK/model%201.jpg",
      output_format: "png",
      output_quality: 100
    }
  }
);
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 cedoysch/flux-fill-redux-try-on using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "cedoysch/flux-fill-redux-try-on:cf5cb07a25e726fe2fac166a8c5ab52ddccd48657741670fb09d9954d4d8446f",
    input={
        "cloth_type": "upper",
        "cloth_image": "https://replicate.delivery/pbxt/MjVInxdHWaHcHcbQcmiEyf7vm9gMwo59uItGH3vYAaK1G1ir/example_jacket.png",
        "person_image": "https://replicate.delivery/pbxt/MjVIo8ENgFG5SBbMep5WKSJFakH3AxBX9YDzROldiNVK53VK/model%201.jpg",
        "output_format": "png",
        "output_quality": 100
    }
)
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 cedoysch/flux-fill-redux-try-on 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": "cf5cb07a25e726fe2fac166a8c5ab52ddccd48657741670fb09d9954d4d8446f",
    "input": {
      "cloth_type": "upper",
      "cloth_image": "https://replicate.delivery/pbxt/MjVInxdHWaHcHcbQcmiEyf7vm9gMwo59uItGH3vYAaK1G1ir/example_jacket.png",
      "person_image": "https://replicate.delivery/pbxt/MjVIo8ENgFG5SBbMep5WKSJFakH3AxBX9YDzROldiNVK53VK/model%201.jpg",
      "output_format": "png",
      "output_quality": 100
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2025-03-27T15:16:12.783042Z",
  "created_at": "2025-03-27T15:05:13.798000Z",
  "data_removed": false,
  "error": null,
  "id": "p2set2eb8srme0cnv0hbbxxkcm",
  "input": {
    "cloth_type": "upper",
    "cloth_image": "https://replicate.delivery/pbxt/MjVInxdHWaHcHcbQcmiEyf7vm9gMwo59uItGH3vYAaK1G1ir/example_jacket.png",
    "person_image": "https://replicate.delivery/pbxt/MjVIo8ENgFG5SBbMep5WKSJFakH3AxBX9YDzROldiNVK53VK/model%201.jpg",
    "output_format": "png",
    "output_quality": 100
  },
  "logs": "Random seed set to: 2376496366\nChecking inputs\n✅ /tmp/inputs/person_image.jpg\n✅ /tmp/inputs/cloth_image.png\n====================================\nChecking weights\n✅ t5xxl_fp16.safetensors exists in ComfyUI/models/text_encoders\n✅ flux1-redux-dev.safetensors exists in ComfyUI/models/style_models\n✅ ViT-L-14-TEXT-detail-improved-hiT-GmP-HF.safetensors exists in ComfyUI/models/text_encoders\n✅ ae.safetensors exists in ComfyUI/models/vae\n✅ flux1-fill-dev.safetensors exists in ComfyUI/models/diffusion_models\n⚠️  RMBG-1.4/model.pth is for non-commercial use only. Unless you have obtained a commercial license.\nDetails: https://github.com/replicate/cog-comfyui/blob/main/weights_licenses.md\n✅ RMBG-1.4/model.pth exists in ComfyUI/custom_nodes/ComfyUI-BRIA_AI-RMBG/\n✅ sigclip_vision_patch14_384.safetensors exists in ComfyUI/models/clip_vision\n====================================\nRunning workflow\n[ComfyUI] got prompt\nExecuting node 17, title: Person, class type: LoadImage\nExecuting node 399, title: Resize Image, class type: ImageResizeKJ\nExecuting node 369, title: Auto Mask Generation, class type: AutoMasker\nExecuting node 371, title: Masked Target, class type: PreviewImage\nExecuting node 370, title: Binary Mask, class type: PreviewImage\nExecuting node 231, title: Scale Image to Total Pixels, class type: ImageScaleToTotalPixels\nExecuting node 235, title: ImageSize, class type: easy imageSize\nExecuting node 264, title: Image Concatenate, class type: ImageConcanate\nExecuting node 267, title: Preview Image, class type: PreviewImage\nExecuting node 184, title: ImageSize, class type: easy imageSize\nExecuting node 354, title: Image Concatenate, class type: ImageConcanate\nExecuting node 358, title: Convert Image to Mask, class type: ImageToMask\nExecuting node 397, title: 🔧 Mask Blur, class type: MaskBlur+\nExecuting node 259, title: InpaintModelConditioning, class type: InpaintModelConditioning\nExecuting node 263, title: KSampler, class type: KSampler\n[ComfyUI]\n[ComfyUI] 0%|          | 0/12 [00:00<?, ?it/s]\n[ComfyUI] 8%|▊         | 1/12 [00:01<00:12,  1.16s/it]\n[ComfyUI] 17%|█▋        | 2/12 [00:03<00:16,  1.61s/it]\n[ComfyUI] 25%|██▌       | 3/12 [00:05<00:15,  1.76s/it]\n[ComfyUI] 33%|███▎      | 4/12 [00:06<00:14,  1.83s/it]\n[ComfyUI] 42%|████▏     | 5/12 [00:08<00:13,  1.86s/it]\n[ComfyUI] 50%|█████     | 6/12 [00:10<00:11,  1.89s/it]\n[ComfyUI] 58%|█████▊    | 7/12 [00:12<00:09,  1.90s/it]\n[ComfyUI] 67%|██████▋   | 8/12 [00:14<00:07,  1.91s/it]\n[ComfyUI] 75%|███████▌  | 9/12 [00:16<00:05,  1.92s/it]\n[ComfyUI] 83%|████████▎ | 10/12 [00:18<00:03,  1.93s/it]\n[ComfyUI] 92%|█████████▏| 11/12 [00:20<00:01,  1.93s/it]\n[ComfyUI] 100%|██████████| 12/12 [00:22<00:00,  1.93s/it]\nExecuting node 262, title: VAE Decode, class type: VAEDecode\nExecuting node 272, title: Preview Image, class type: PreviewImage\nExecuting node 191, title: Image Overlay, class type: Image Overlay\nExecuting node 273, title: Preview Image, class type: PreviewImage\nExecuting node 237, title: ImageSize, class type: easy imageSize\nExecuting node 238, title: 🔧 Simple Math, class type: SimpleMath+\nExecuting node 234, title: 🔧 Image Crop, class type: ImageCrop+\nExecuting node 333, title: Image Comparer (rgthree), class type: Image Comparer (rgthree)\nExecuting node 307, title: Save Image, class type: SaveImage\n[ComfyUI] 100%|██████████| 12/12 [00:22<00:00,  1.87s/it]\n[ComfyUI] Prompt executed in 26.56 seconds\noutputs:  {'267': {'images': [{'filename': 'ComfyUI_temp_cbdba_00001_.png', 'subfolder': '', 'type': 'temp'}]}, '307': {'images': [{'filename': 'ComfyUI_00001_.png', 'subfolder': '', 'type': 'output'}]}, '140': {'text': ['W', 'i', 'd', 't', 'h', ':', ' ', '1', '0', '2', '4', ' ', ',', ' ', 'H', 'e', 'i', 'g', 'h', 't', ':', ' ', '1', '0', '2', '4']}, '144': {'images': [{'filename': 'ComfyUI_temp_mpsux_00001_.png', 'subfolder': '', 'type': 'temp'}]}, '272': {'images': [{'filename': 'ComfyUI_temp_psdlx_00001_.png', 'subfolder': '', 'type': 'temp'}]}, '266': {'images': [{'filename': 'ComfyUI_temp_hjmip_00001_.png', 'subfolder': '', 'type': 'temp'}]}, '236': {'text': ['W', 'i', 'd', 't', 'h', ':', ' ', '1', '3', '3', '5', ' ', ',', ' ', 'H', 'e', 'i', 'g', 'h', 't', ':', ' ', '1', '3', '3', '5']}, '371': {'images': [{'filename': 'ComfyUI_temp_eaecq_00001_.png', 'subfolder': '', 'type': 'temp'}]}, '237': {'text': ['W', 'i', 'd', 't', 'h', ':', ' ', '2', '3', '2', '8', ' ', ',', ' ', 'H', 'e', 'i', 'g', 'h', 't', ':', ' ', '1', '3', '2', '8']}, '273': {'images': [{'filename': 'ComfyUI_temp_zgyrd_00001_.png', 'subfolder': '', 'type': 'temp'}]}, '271': {'images': [{'filename': 'ComfyUI_temp_dkmud_00001_.png', 'subfolder': '', 'type': 'temp'}]}, '391': {'text': ['A brown jacket with a fur collar on a white background.']}, '333': {'a_images': [{'filename': 'rgthree.compare._temp_updpu_00001_.png', 'subfolder': '', 'type': 'temp'}], 'b_images': [{'filename': 'rgthree.compare._temp_updpu_00002_.png', 'subfolder': '', 'type': 'temp'}]}, '370': {'images': [{'filename': 'ComfyUI_temp_iqrbr_00001_.png', 'subfolder': '', 'type': 'temp'}]}, '235': {'text': ['W', 'i', 'd', 't', 'h', ':', ' ', '1', '1', '5', '6', ' ', ',', ' ', 'H', 'e', 'i', 'g', 'h', 't', ':', ' ', '1', '5', '4', '2']}, '184': {'text': ['W', 'i', 'd', 't', 'h', ':', ' ', '2', '3', '3', '5', ' ', ',', ' ', 'H', 'e', 'i', 'g', 'h', 't', ':', ' ', '1', '3', '3', '5']}}\n====================================\nComfyUI_00001_.png",
  "metrics": {
    "predict_time": 27.267200649,
    "total_time": 658.985042
  },
  "output": [
    "https://replicate.delivery/xezq/3QaH2HRr6yZ7ApQaxtFB8TTSwgcabuxneXnk0nEF9rae2xcUA/ComfyUI_00001_.png"
  ],
  "started_at": "2025-03-27T15:15:45.515841Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-edntq4joqg7gxyinjpyihtnrttahr5mwbh3yo4quwmxtbhs25jsq",
    "get": "https://api.replicate.com/v1/predictions/p2set2eb8srme0cnv0hbbxxkcm",
    "cancel": "https://api.replicate.com/v1/predictions/p2set2eb8srme0cnv0hbbxxkcm/cancel"
  },
  "version": "cf5cb07a25e726fe2fac166a8c5ab52ddccd48657741670fb09d9954d4d8446f"
}

Generated in

27.3 seconds

Tweak it ShareReport

Random seed set to: 2376496366
Checking inputs
✅ /tmp/inputs/person_image.jpg
✅ /tmp/inputs/cloth_image.png
====================================
Checking weights
✅ t5xxl_fp16.safetensors exists in ComfyUI/models/text_encoders
✅ flux1-redux-dev.safetensors exists in ComfyUI/models/style_models
✅ ViT-L-14-TEXT-detail-improved-hiT-GmP-HF.safetensors exists in ComfyUI/models/text_encoders
✅ ae.safetensors exists in ComfyUI/models/vae
✅ flux1-fill-dev.safetensors exists in ComfyUI/models/diffusion_models
⚠️  RMBG-1.4/model.pth is for non-commercial use only. Unless you have obtained a commercial license.
Details: https://github.com/replicate/cog-comfyui/blob/main/weights_licenses.md
✅ RMBG-1.4/model.pth exists in ComfyUI/custom_nodes/ComfyUI-BRIA_AI-RMBG/
✅ sigclip_vision_patch14_384.safetensors exists in ComfyUI/models/clip_vision
====================================
Running workflow
[ComfyUI] got prompt
Executing node 17, title: Person, class type: LoadImage
Executing node 399, title: Resize Image, class type: ImageResizeKJ
Executing node 369, title: Auto Mask Generation, class type: AutoMasker
Executing node 371, title: Masked Target, class type: PreviewImage
Executing node 370, title: Binary Mask, class type: PreviewImage
Executing node 231, title: Scale Image to Total Pixels, class type: ImageScaleToTotalPixels
Executing node 235, title: ImageSize, class type: easy imageSize
Executing node 264, title: Image Concatenate, class type: ImageConcanate
Executing node 267, title: Preview Image, class type: PreviewImage
Executing node 184, title: ImageSize, class type: easy imageSize
Executing node 354, title: Image Concatenate, class type: ImageConcanate
Executing node 358, title: Convert Image to Mask, class type: ImageToMask
Executing node 397, title: 🔧 Mask Blur, class type: MaskBlur+
Executing node 259, title: InpaintModelConditioning, class type: InpaintModelConditioning
Executing node 263, title: KSampler, class type: KSampler
[ComfyUI]
[ComfyUI] 0%|          | 0/12 [00:00<?, ?it/s]
[ComfyUI] 8%|▊         | 1/12 [00:01<00:12,  1.16s/it]
[ComfyUI] 17%|█▋        | 2/12 [00:03<00:16,  1.61s/it]
[ComfyUI] 25%|██▌       | 3/12 [00:05<00:15,  1.76s/it]
[ComfyUI] 33%|███▎      | 4/12 [00:06<00:14,  1.83s/it]
[ComfyUI] 42%|████▏     | 5/12 [00:08<00:13,  1.86s/it]
[ComfyUI] 50%|█████     | 6/12 [00:10<00:11,  1.89s/it]
[ComfyUI] 58%|█████▊    | 7/12 [00:12<00:09,  1.90s/it]
[ComfyUI] 67%|██████▋   | 8/12 [00:14<00:07,  1.91s/it]
[ComfyUI] 75%|███████▌  | 9/12 [00:16<00:05,  1.92s/it]
[ComfyUI] 83%|████████▎ | 10/12 [00:18<00:03,  1.93s/it]
[ComfyUI] 92%|█████████▏| 11/12 [00:20<00:01,  1.93s/it]
[ComfyUI] 100%|██████████| 12/12 [00:22<00:00,  1.93s/it]
Executing node 262, title: VAE Decode, class type: VAEDecode
Executing node 272, title: Preview Image, class type: PreviewImage
Executing node 191, title: Image Overlay, class type: Image Overlay
Executing node 273, title: Preview Image, class type: PreviewImage
Executing node 237, title: ImageSize, class type: easy imageSize
Executing node 238, title: 🔧 Simple Math, class type: SimpleMath+
Executing node 234, title: 🔧 Image Crop, class type: ImageCrop+
Executing node 333, title: Image Comparer (rgthree), class type: Image Comparer (rgthree)
Executing node 307, title: Save Image, class type: SaveImage
[ComfyUI] 100%|██████████| 12/12 [00:22<00:00,  1.87s/it]
[ComfyUI] Prompt executed in 26.56 seconds
outputs:  {'267': {'images': [{'filename': 'ComfyUI_temp_cbdba_00001_.png', 'subfolder': '', 'type': 'temp'}]}, '307': {'images': [{'filename': 'ComfyUI_00001_.png', 'subfolder': '', 'type': 'output'}]}, '140': {'text': ['W', 'i', 'd', 't', 'h', ':', ' ', '1', '0', '2', '4', ' ', ',', ' ', 'H', 'e', 'i', 'g', 'h', 't', ':', ' ', '1', '0', '2', '4']}, '144': {'images': [{'filename': 'ComfyUI_temp_mpsux_00001_.png', 'subfolder': '', 'type': 'temp'}]}, '272': {'images': [{'filename': 'ComfyUI_temp_psdlx_00001_.png', 'subfolder': '', 'type': 'temp'}]}, '266': {'images': [{'filename': 'ComfyUI_temp_hjmip_00001_.png', 'subfolder': '', 'type': 'temp'}]}, '236': {'text': ['W', 'i', 'd', 't', 'h', ':', ' ', '1', '3', '3', '5', ' ', ',', ' ', 'H', 'e', 'i', 'g', 'h', 't', ':', ' ', '1', '3', '3', '5']}, '371': {'images': [{'filename': 'ComfyUI_temp_eaecq_00001_.png', 'subfolder': '', 'type': 'temp'}]}, '237': {'text': ['W', 'i', 'd', 't', 'h', ':', ' ', '2', '3', '2', '8', ' ', ',', ' ', 'H', 'e', 'i', 'g', 'h', 't', ':', ' ', '1', '3', '2', '8']}, '273': {'images': [{'filename': 'ComfyUI_temp_zgyrd_00001_.png', 'subfolder': '', 'type': 'temp'}]}, '271': {'images': [{'filename': 'ComfyUI_temp_dkmud_00001_.png', 'subfolder': '', 'type': 'temp'}]}, '391': {'text': ['A brown jacket with a fur collar on a white background.']}, '333': {'a_images': [{'filename': 'rgthree.compare._temp_updpu_00001_.png', 'subfolder': '', 'type': 'temp'}], 'b_images': [{'filename': 'rgthree.compare._temp_updpu_00002_.png', 'subfolder': '', 'type': 'temp'}]}, '370': {'images': [{'filename': 'ComfyUI_temp_iqrbr_00001_.png', 'subfolder': '', 'type': 'temp'}]}, '235': {'text': ['W', 'i', 'd', 't', 'h', ':', ' ', '1', '1', '5', '6', ' ', ',', ' ', 'H', 'e', 'i', 'g', 'h', 't', ':', ' ', '1', '5', '4', '2']}, '184': {'text': ['W', 'i', 'd', 't', 'h', ':', ' ', '2', '3', '3', '5', ' ', ',', ' ', 'H', 'e', 'i', 'g', 'h', 't', ':', ' ', '1', '3', '3', '5']}}
====================================
ComfyUI_00001_.png

Examples

View more examples

Run time and cost

This model costs approximately $0.20 to run on Replicate, or 5 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 L40S GPU hardware. Predictions typically complete within 4 minutes. The predict time for this model varies significantly based on the inputs.

Readme

This model allows users to visualize how the selected clothes will look in the image of a person. The model accepts a photo of a person, an image of clothing, and the type of clothing (upper, lower, or overall – a one-piece outfit). Based on the set parameters, processing takes place using the ComfyUI workflow, which includes image loading and scaling, mask generation, and clothing overlay on the photo.

Input data:

person_image: A photo of the person on whom the clothes will be “applied”.

cloth_image: An image of the selected clothing. Important: for a correct fitting, the image of the clothes must be 1024×1024 pixels in size.

clot_type: The type of clothing where:

upper — outerwear (T-shirt, jacket, etc.),

lower — undergarments (trousers, skirt, etc.),

overall — clothes for the whole body (complex image).

Output data:

A generated image in which clothes are superimposed on a photo of a person. The final image has a size of 1024×768 pixels.