xlabs-ai/flux-dev-realism – Run with an API on Replicate

xlabs-ai / flux-dev-realism

FLUX.1-dev with XLabs-AI’s realism lora

Warm

Public
841.6K runs
A100 (80GB)
Paper
License

Run with an API

Playground API Examples README Versions

Input

prompt

string

Shift + Return to add a new line

A charismatic speaker is captured mid-speech. He has short, tousled brown hair that's slightly messy on top. He has a round circle face, clean shaven, adorned with rounded rectangular-framed glasses with dark rims, is animated as he gestures with his left hand. He is holding a black microphone in his right hand, speaking passionately.

The man is wearing a light grey sweater over a white t-shirt. He's also wearing a simple black lanyard hanging around his neck. The lanyard badge has the text "Replicate".

Behind him, there is a blurred background with a white banner containing logos and text (including replicate), a professional conference setting.A charismatic speaker is captured mid-speech. He has short, tousled brown hair that's slightly messy on top. He has a round circle face, clean shaven, adorned with rounded rectangular-framed glasses with dark rims, is animated as he gestures with his left hand. He is holding a black microphone in his right hand, speaking passionately.

The man is wearing a light grey sweater over a white t-shirt. He's also wearing a simple black lanyard hanging around his neck. The lanyard badge has the text "Replicate".

Behind him, there is a blurred background with a white banner containing logos and text (including replicate), a professional conference setting.

Default: ""

aspect_ratio

string

Aspect ratio for the generated image

Default: "1:1"

num_outputs

integer

(minimum: 1, maximum: 4)

Number of outputs to generate

Default: 1

num_inference_steps

integer

(minimum: 1, maximum: 50)

Number of denoising steps. Recommended range is 28-50

Default: 30

guidance

number

(minimum: 0, maximum: 10)

Guidance for generated image

Default: 3.5

lora_strength

number

(minimum: 0, maximum: 2)

Strength of flux-realism lora, 0 is disabled

Default: 0.8

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=xlabs-ai/flux-dev-realism

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 xlabs-ai/flux-dev-realism using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "xlabs-ai/flux-dev-realism:39b3434f194f87a900d1bc2b6d4b983e90f0dde1d5022c27b52c143d670758fa",
  {
    input: {
      prompt: "A charismatic speaker is captured mid-speech. He has short, tousled brown hair that's slightly messy on top. He has a round circle face, clean shaven, adorned with rounded rectangular-framed glasses with dark rims, is animated as he gestures with his left hand. He is holding a black microphone in his right hand, speaking passionately.\n\nThe man is wearing a light grey sweater over a white t-shirt. He's also wearing a simple black lanyard hanging around his neck. The lanyard badge has the text \"Replicate\".\n\nBehind him, there is a blurred background with a white banner containing logos and text (including replicate), a professional conference setting.",
      guidance: 3.5,
      num_outputs: 1,
      aspect_ratio: "4:5",
      lora_strength: 0.8,
      output_format: "webp",
      output_quality: 100,
      num_inference_steps: 30
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

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 xlabs-ai/flux-dev-realism using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "xlabs-ai/flux-dev-realism:39b3434f194f87a900d1bc2b6d4b983e90f0dde1d5022c27b52c143d670758fa",
    input={
        "prompt": "A charismatic speaker is captured mid-speech. He has short, tousled brown hair that's slightly messy on top. He has a round circle face, clean shaven, adorned with rounded rectangular-framed glasses with dark rims, is animated as he gestures with his left hand. He is holding a black microphone in his right hand, speaking passionately.\n\nThe man is wearing a light grey sweater over a white t-shirt. He's also wearing a simple black lanyard hanging around his neck. The lanyard badge has the text \"Replicate\".\n\nBehind him, there is a blurred background with a white banner containing logos and text (including replicate), a professional conference setting.",
        "guidance": 3.5,
        "num_outputs": 1,
        "aspect_ratio": "4:5",
        "lora_strength": 0.8,
        "output_format": "webp",
        "output_quality": 100,
        "num_inference_steps": 30
    }
)
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 xlabs-ai/flux-dev-realism 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": "39b3434f194f87a900d1bc2b6d4b983e90f0dde1d5022c27b52c143d670758fa",
    "input": {
      "prompt": "A charismatic speaker is captured mid-speech. He has short, tousled brown hair that\'s slightly messy on top. He has a round circle face, clean shaven, adorned with rounded rectangular-framed glasses with dark rims, is animated as he gestures with his left hand. He is holding a black microphone in his right hand, speaking passionately.\\n\\nThe man is wearing a light grey sweater over a white t-shirt. He\'s also wearing a simple black lanyard hanging around his neck. The lanyard badge has the text \\"Replicate\\".\\n\\nBehind him, there is a blurred background with a white banner containing logos and text (including replicate), a professional conference setting.",
      "guidance": 3.5,
      "num_outputs": 1,
      "aspect_ratio": "4:5",
      "lora_strength": 0.8,
      "output_format": "webp",
      "output_quality": 100,
      "num_inference_steps": 30
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2024-08-10T21:03:47.643409Z",
  "created_at": "2024-08-10T21:03:33.897000Z",
  "data_removed": false,
  "error": null,
  "id": "zj1sazmg15rj00ch7rd994r67m",
  "input": {
    "prompt": "A charismatic speaker is captured mid-speech. He has short, tousled brown hair that's slightly messy on top. He has a round circle face, clean shaven, adorned with rounded rectangular-framed glasses with dark rims, is animated as he gestures with his left hand. He is holding a black microphone in his right hand, speaking passionately.\n\nThe man is wearing a light grey sweater over a white t-shirt. He's also wearing a simple black lanyard hanging around his neck. The lanyard badge has the text \"Replicate\".\n\nBehind him, there is a blurred background with a white banner containing logos and text (including replicate), a professional conference setting.",
    "guidance": 3.5,
    "num_outputs": 1,
    "aspect_ratio": "4:5",
    "lora_strength": 0.8,
    "output_format": "webp",
    "output_quality": 100,
    "num_inference_steps": 30
  },
  "logs": "Random seed set to: 1191887297\nRunning workflow\ngot prompt\nExecuting node 25, title: RandomNoise, class type: RandomNoise\nExecuting node 6, title: CLIP Text Encode (Prompt), class type: CLIPTextEncode\nExecuting node 60, title: FluxGuidance, class type: FluxGuidance\nExecuting node 22, title: BasicGuider, class type: BasicGuider\nExecuting node 13, title: SamplerCustomAdvanced, class type: SamplerCustomAdvanced\n  0%|          | 0/30 [00:00<?, ?it/s]\n  3%|▎         | 1/30 [00:00<00:06,  4.27it/s]\n  7%|▋         | 2/30 [00:00<00:09,  2.93it/s]\n 10%|█         | 3/30 [00:01<00:10,  2.66it/s]\n 13%|█▎        | 4/30 [00:01<00:10,  2.55it/s]\n 17%|█▋        | 5/30 [00:01<00:10,  2.49it/s]\n 20%|██        | 6/30 [00:02<00:09,  2.46it/s]\n 23%|██▎       | 7/30 [00:02<00:09,  2.44it/s]\n 27%|██▋       | 8/30 [00:03<00:09,  2.42it/s]\n 30%|███       | 9/30 [00:03<00:08,  2.41it/s]\n 33%|███▎      | 10/30 [00:03<00:08,  2.41it/s]\n 37%|███▋      | 11/30 [00:04<00:07,  2.40it/s]\n 40%|████      | 12/30 [00:04<00:07,  2.40it/s]\n 43%|████▎     | 13/30 [00:05<00:07,  2.40it/s]\n 47%|████▋     | 14/30 [00:05<00:06,  2.40it/s]\n 50%|█████     | 15/30 [00:06<00:06,  2.40it/s]\n 53%|█████▎    | 16/30 [00:06<00:05,  2.39it/s]\n 57%|█████▋    | 17/30 [00:06<00:05,  2.39it/s]\n 60%|██████    | 18/30 [00:07<00:05,  2.39it/s]\n 63%|██████▎   | 19/30 [00:07<00:04,  2.39it/s]\n 67%|██████▋   | 20/30 [00:08<00:04,  2.39it/s]\n 70%|███████   | 21/30 [00:08<00:03,  2.39it/s]\n 73%|███████▎  | 22/30 [00:09<00:03,  2.39it/s]\n 77%|███████▋  | 23/30 [00:09<00:02,  2.39it/s]\n 80%|████████  | 24/30 [00:09<00:02,  2.39it/s]\n 83%|████████▎ | 25/30 [00:10<00:02,  2.39it/s]\n 87%|████████▋ | 26/30 [00:10<00:01,  2.39it/s]\n 90%|█████████ | 27/30 [00:11<00:01,  2.39it/s]\n 93%|█████████▎| 28/30 [00:11<00:00,  2.39it/s]\n 97%|█████████▋| 29/30 [00:11<00:00,  2.39it/s]\n100%|██████████| 30/30 [00:12<00:00,  2.39it/s]\n100%|██████████| 30/30 [00:12<00:00,  2.43it/s]\nExecuting node 8, title: VAE Decode, class type: VAEDecode\nExecuting node 9, title: Save Image, class type: SaveImage\nPrompt executed in 13.19 seconds\noutputs:  {'9': {'images': [{'filename': 'R8_FLUX_DEV_REALISM_00001_.png', 'subfolder': '', 'type': 'output'}]}}\n====================================\nR8_FLUX_DEV_REALISM_00001_.png",
  "metrics": {
    "predict_time": 13.736403549,
    "total_time": 13.746409
  },
  "output": [
    "https://replicate.delivery/yhqm/RRqzNwnofelJuUCkhiicKoHWcVr9ye2Ln3fnjQEZRNnM7hFNB/R8_FLUX_DEV_REALISM_00001_.webp"
  ],
  "started_at": "2024-08-10T21:03:33.907006Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/zj1sazmg15rj00ch7rd994r67m",
    "cancel": "https://api.replicate.com/v1/predictions/zj1sazmg15rj00ch7rd994r67m/cancel"
  },
  "version": "39b3434f194f87a900d1bc2b6d4b983e90f0dde1d5022c27b52c143d670758fa"
}

Generated in

13.7 seconds

Tweak it ShareReport

Random seed set to: 1191887297
Running workflow
got prompt
Executing node 25, title: RandomNoise, class type: RandomNoise
Executing node 6, title: CLIP Text Encode (Prompt), class type: CLIPTextEncode
Executing node 60, title: FluxGuidance, class type: FluxGuidance
Executing node 22, title: BasicGuider, class type: BasicGuider
Executing node 13, title: SamplerCustomAdvanced, class type: SamplerCustomAdvanced
  0%|          | 0/30 [00:00<?, ?it/s]
  3%|▎         | 1/30 [00:00<00:06,  4.27it/s]
  7%|▋         | 2/30 [00:00<00:09,  2.93it/s]
 10%|█         | 3/30 [00:01<00:10,  2.66it/s]
 13%|█▎        | 4/30 [00:01<00:10,  2.55it/s]
 17%|█▋        | 5/30 [00:01<00:10,  2.49it/s]
 20%|██        | 6/30 [00:02<00:09,  2.46it/s]
 23%|██▎       | 7/30 [00:02<00:09,  2.44it/s]
 27%|██▋       | 8/30 [00:03<00:09,  2.42it/s]
 30%|███       | 9/30 [00:03<00:08,  2.41it/s]
 33%|███▎      | 10/30 [00:03<00:08,  2.41it/s]
 37%|███▋      | 11/30 [00:04<00:07,  2.40it/s]
 40%|████      | 12/30 [00:04<00:07,  2.40it/s]
 43%|████▎     | 13/30 [00:05<00:07,  2.40it/s]
 47%|████▋     | 14/30 [00:05<00:06,  2.40it/s]
 50%|█████     | 15/30 [00:06<00:06,  2.40it/s]
 53%|█████▎    | 16/30 [00:06<00:05,  2.39it/s]
 57%|█████▋    | 17/30 [00:06<00:05,  2.39it/s]
 60%|██████    | 18/30 [00:07<00:05,  2.39it/s]
 63%|██████▎   | 19/30 [00:07<00:04,  2.39it/s]
 67%|██████▋   | 20/30 [00:08<00:04,  2.39it/s]
 70%|███████   | 21/30 [00:08<00:03,  2.39it/s]
 73%|███████▎  | 22/30 [00:09<00:03,  2.39it/s]
 77%|███████▋  | 23/30 [00:09<00:02,  2.39it/s]
 80%|████████  | 24/30 [00:09<00:02,  2.39it/s]
 83%|████████▎ | 25/30 [00:10<00:02,  2.39it/s]
 87%|████████▋ | 26/30 [00:10<00:01,  2.39it/s]
 90%|█████████ | 27/30 [00:11<00:01,  2.39it/s]
 93%|█████████▎| 28/30 [00:11<00:00,  2.39it/s]
 97%|█████████▋| 29/30 [00:11<00:00,  2.39it/s]
100%|██████████| 30/30 [00:12<00:00,  2.39it/s]
100%|██████████| 30/30 [00:12<00:00,  2.43it/s]
Executing node 8, title: VAE Decode, class type: VAEDecode
Executing node 9, title: Save Image, class type: SaveImage
Prompt executed in 13.19 seconds
outputs:  {'9': {'images': [{'filename': 'R8_FLUX_DEV_REALISM_00001_.png', 'subfolder': '', 'type': 'output'}]}}
====================================
R8_FLUX_DEV_REALISM_00001_.png

Examples

View more examples

Run time and cost

This model costs approximately $0.033 to run on Replicate, or 30 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 24 seconds. The predict time for this model varies significantly based on the inputs.

Readme

This model doesn't have a readme.