fire/flux | Run with an API on Replicate

The image generation model tailored for local development and personal use

Cold

Public

117 runs

L40S

License

GitHub

Playground API Examples README Versions

Input

prompt

*string

Shift + Return to add a new line

The front view is a young woman with realistic adult proportions, featuring long legs, a slender waist, and balanced shoulders. She has short, slightly messy brown hair and expressive brown eyes. The medium bust is dressed in simple, armless garments with a clean and flowing silhouette. She is standing with her arms outstretched to the sides, palms facing downwards, and her legs slightly apart with a slight bend in her knees.  Her hands and legs are equally outstretched to the sides, her palms facing downwards, and her knees apart, barefoot apart.  She is wearing simple, flat shoes. Rendered in a clean anime style with soft shading, focusing on smooth shapes, proper proportions, and balanced anatomy. The background is beige, with soft lighting emphasizing her features and overall form. This is a front view. There are multiple consistent views.The front view is a young woman with realistic adult proportions, featuring long legs, a slender waist, and balanced shoulders. She has short, slightly messy brown hair and expressive brown eyes. The medium bust is dressed in simple, armless garments with a clean and flowing silhouette. She is standing with her arms outstretched to the sides, palms facing downwards, and her legs slightly apart with a slight bend in her knees.  Her hands and legs are equally outstretched to the sides, her palms facing downwards, and her knees apart, barefoot apart.  She is wearing simple, flat shoes. Rendered in a clean anime style with soft shading, focusing on smooth shapes, proper proportions, and balanced anatomy. The background is beige, with soft lighting emphasizing her features and overall form. This is a front view. There are multiple consistent views.

Prompt for generated image

aspect_ratio

string

Aspect ratio for the generated image

Default: "2:1"

num_outputs

integer

(minimum: 1, maximum: 4)

Number of outputs to generate

Default: 1

output_format

string

Format of the output images

Default: "png"

megapixels

string

Approximate number of megapixels for generated image

Default: "1"

Including num_inference_steps and 4 more...

num_inference_steps

integer

(minimum: 1, maximum: 8)

Number of denoising steps. 4 is recommended, and lower number of steps produce lower quality outputs, faster.

Default: 4

seed

integer

Random seed. Set for reproducible generation

Default: 0

output_quality

integer

(minimum: 0, maximum: 100)

Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs

Default: 80

disable_safety_checker

boolean

Disable safety checker for generated images.

Default: false

go_fast

boolean

Run faster predictions with model optimized for speed (currently fp8 quantized); disable to run in original bf16

Default: true

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

npx create-replicate --model=fire/flux

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";
import fs from "node:fs";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

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

const output = await replicate.run(
  "fire/flux:da7b098b70c3e52d56a04c2b7f3632eb63dfb0f26941a0934bf223157a7c5245",
  {
    input: {
      seed: 0,
      prompt: "The front view is a young woman with realistic adult proportions, featuring long legs, a slender waist, and balanced shoulders. She has short, slightly messy brown hair and expressive brown eyes. The medium bust is dressed in simple, armless garments with a clean and flowing silhouette. She is standing with her arms outstretched to the sides, palms facing downwards, and her legs slightly apart with a slight bend in her knees.  Her hands and legs are equally outstretched to the sides, her palms facing downwards, and her knees apart, barefoot apart.  She is wearing simple, flat shoes. Rendered in a clean anime style with soft shading, focusing on smooth shapes, proper proportions, and balanced anatomy. The background is beige, with soft lighting emphasizing her features and overall form. This is a front view. There are multiple consistent views.",
      go_fast: true,
      megapixels: "1",
      num_outputs: 4,
      aspect_ratio: "1:1",
      output_format: "webp",
      output_quality: 80,
      num_inference_steps: 8
    }
  }
);

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

output = replicate.run(
    "fire/flux:da7b098b70c3e52d56a04c2b7f3632eb63dfb0f26941a0934bf223157a7c5245",
    input={
        "seed": 0,
        "prompt": "The front view is a young woman with realistic adult proportions, featuring long legs, a slender waist, and balanced shoulders. She has short, slightly messy brown hair and expressive brown eyes. The medium bust is dressed in simple, armless garments with a clean and flowing silhouette. She is standing with her arms outstretched to the sides, palms facing downwards, and her legs slightly apart with a slight bend in her knees.  Her hands and legs are equally outstretched to the sides, her palms facing downwards, and her knees apart, barefoot apart.  She is wearing simple, flat shoes. Rendered in a clean anime style with soft shading, focusing on smooth shapes, proper proportions, and balanced anatomy. The background is beige, with soft lighting emphasizing her features and overall form. This is a front view. There are multiple consistent views.",
        "go_fast": True,
        "megapixels": "1",
        "num_outputs": 4,
        "aspect_ratio": "1:1",
        "output_format": "webp",
        "output_quality": 80,
        "num_inference_steps": 8
    }
)

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

# To write the file to disk:
with open("my-image.png", "wb") as file:
    file.write(output[0].read())

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 fire/flux 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": "fire/flux:da7b098b70c3e52d56a04c2b7f3632eb63dfb0f26941a0934bf223157a7c5245",
    "input": {
      "seed": 0,
      "prompt": "The front view is a young woman with realistic adult proportions, featuring long legs, a slender waist, and balanced shoulders. She has short, slightly messy brown hair and expressive brown eyes. The medium bust is dressed in simple, armless garments with a clean and flowing silhouette. She is standing with her arms outstretched to the sides, palms facing downwards, and her legs slightly apart with a slight bend in her knees.  Her hands and legs are equally outstretched to the sides, her palms facing downwards, and her knees apart, barefoot apart.  She is wearing simple, flat shoes. Rendered in a clean anime style with soft shading, focusing on smooth shapes, proper proportions, and balanced anatomy. The background is beige, with soft lighting emphasizing her features and overall form. This is a front view. There are multiple consistent views.",
      "go_fast": true,
      "megapixels": "1",
      "num_outputs": 4,
      "aspect_ratio": "1:1",
      "output_format": "webp",
      "output_quality": 80,
      "num_inference_steps": 8
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2024-12-25T12:23:32.914761Z",
  "created_at": "2024-12-25T12:15:36.085000Z",
  "data_removed": false,
  "error": null,
  "id": "963vbnvejnrj00ckzpzbwwsder",
  "input": {
    "prompt": "The front view is a young woman with realistic adult proportions, featuring long legs, a slender waist, and balanced shoulders. She has short, slightly messy brown hair and expressive brown eyes. The medium bust is dressed in simple, armless garments with a clean and flowing silhouette. She is standing with her arms outstretched to the sides, palms facing downwards, and her legs slightly apart with a slight bend in her knees.  Her hands and legs are equally outstretched to the sides, her palms facing downwards, and her knees apart, barefoot apart.  She is wearing simple, flat shoes. Rendered in a clean anime style with soft shading, focusing on smooth shapes, proper proportions, and balanced anatomy. The background is beige, with soft lighting emphasizing her features and overall form. This is a front view. There are multiple consistent views.",
    "go_fast": true,
    "megapixels": "1",
    "num_outputs": 4,
    "aspect_ratio": "1:1",
    "output_format": "webp",
    "output_quality": 80,
    "num_inference_steps": 8
  },
  "logs": "running quantized prediction\nUsing seed: 1137156351\n  0%|          | 0/8 [00:00<?, ?it/s]\n 25%|██▌       | 2/8 [00:00<00:01,  3.11it/s]\n 38%|███▊      | 3/8 [00:01<00:02,  2.30it/s]\n 50%|█████     | 4/8 [00:01<00:01,  2.02it/s]\n 62%|██████▎   | 5/8 [00:02<00:01,  1.89it/s]\n 75%|███████▌  | 6/8 [00:03<00:01,  1.82it/s]\n 88%|████████▊ | 7/8 [00:03<00:00,  1.77it/s]\n100%|██████████| 8/8 [00:04<00:00,  1.75it/s]\n100%|██████████| 8/8 [00:04<00:00,  1.90it/s]\n  0%|          | 0/8 [00:00<?, ?it/s]\n 12%|█▎        | 1/8 [00:00<00:04,  1.69it/s]\n 25%|██▌       | 2/8 [00:01<00:03,  1.69it/s]\n 38%|███▊      | 3/8 [00:01<00:02,  1.69it/s]\n 50%|█████     | 4/8 [00:02<00:02,  1.69it/s]\n 62%|██████▎   | 5/8 [00:02<00:01,  1.69it/s]\n 75%|███████▌  | 6/8 [00:03<00:01,  1.69it/s]\n 88%|████████▊ | 7/8 [00:04<00:00,  1.69it/s]\n100%|██████████| 8/8 [00:04<00:00,  1.69it/s]\n100%|██████████| 8/8 [00:04<00:00,  1.69it/s]\n  0%|          | 0/8 [00:00<?, ?it/s]\n 12%|█▎        | 1/8 [00:00<00:04,  1.69it/s]\n 25%|██▌       | 2/8 [00:01<00:03,  1.69it/s]\n 38%|███▊      | 3/8 [00:01<00:02,  1.69it/s]\n 50%|█████     | 4/8 [00:02<00:02,  1.68it/s]\n 62%|██████▎   | 5/8 [00:02<00:01,  1.68it/s]\n 75%|███████▌  | 6/8 [00:03<00:01,  1.68it/s]\n 88%|████████▊ | 7/8 [00:04<00:00,  1.68it/s]\n100%|██████████| 8/8 [00:04<00:00,  1.69it/s]\n100%|██████████| 8/8 [00:04<00:00,  1.68it/s]\n  0%|          | 0/8 [00:00<?, ?it/s]\n 12%|█▎        | 1/8 [00:00<00:04,  1.69it/s]\n 25%|██▌       | 2/8 [00:01<00:03,  1.69it/s]\n 38%|███▊      | 3/8 [00:01<00:02,  1.69it/s]\n 50%|█████     | 4/8 [00:02<00:02,  1.68it/s]\n 62%|██████▎   | 5/8 [00:02<00:01,  1.68it/s]\n 75%|███████▌  | 6/8 [00:03<00:01,  1.68it/s]\n 88%|████████▊ | 7/8 [00:04<00:00,  1.68it/s]\n100%|██████████| 8/8 [00:04<00:00,  1.68it/s]\n100%|██████████| 8/8 [00:04<00:00,  1.68it/s]\nTotal safe images: 4 out of 4",
  "metrics": {
    "predict_time": 68.710243511,
    "total_time": 476.829761
  },
  "output": [
    "https://replicate.delivery/yhqm/OvOs4jnjTmaZFlkBrpUqf2iekF0m0HVyDfF4CBslaeuR0q5PB/out-0.webp",
    "https://replicate.delivery/yhqm/OLOltZLUG9pgD5QA4GSiRosGnWYLPQvphoQ3oUJTxkMRrmfJA/out-1.webp",
    "https://replicate.delivery/yhqm/JXceGuvtUpR9JSdW2DkDPumdKva8e8ALKp8fWcCjCjHJa18nA/out-2.webp",
    "https://replicate.delivery/yhqm/10FaFbFjJ4YeYCafC22fbWQKsJI1H2CIonHjUIExdXwIa18nA/out-3.webp"
  ],
  "started_at": "2024-12-25T12:22:24.204517Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/qoxq-4zspuhaxakonhvn4e5il2ovumrn4hemgmni26mlvp5i5bvsjncba",
    "get": "https://api.replicate.com/v1/predictions/963vbnvejnrj00ckzpzbwwsder",
    "cancel": "https://api.replicate.com/v1/predictions/963vbnvejnrj00ckzpzbwwsder/cancel"
  },
  "version": "de30fa90bbfddd50f18ce1a1cf3a427d93711eceab613ec398fab202a3d6303a"
}

Generated in

68.7 seconds

Tweak it Iterate in playground ShareReport View full prediction

running quantized prediction
Using seed: 1137156351
  0%|          | 0/8 [00:00<?, ?it/s]
 25%|██▌       | 2/8 [00:00<00:01,  3.11it/s]
 38%|███▊      | 3/8 [00:01<00:02,  2.30it/s]
 50%|█████     | 4/8 [00:01<00:01,  2.02it/s]
 62%|██████▎   | 5/8 [00:02<00:01,  1.89it/s]
 75%|███████▌  | 6/8 [00:03<00:01,  1.82it/s]
 88%|████████▊ | 7/8 [00:03<00:00,  1.77it/s]
100%|██████████| 8/8 [00:04<00:00,  1.75it/s]
100%|██████████| 8/8 [00:04<00:00,  1.90it/s]
  0%|          | 0/8 [00:00<?, ?it/s]
 12%|█▎        | 1/8 [00:00<00:04,  1.69it/s]
 25%|██▌       | 2/8 [00:01<00:03,  1.69it/s]
 38%|███▊      | 3/8 [00:01<00:02,  1.69it/s]
 50%|█████     | 4/8 [00:02<00:02,  1.69it/s]
 62%|██████▎   | 5/8 [00:02<00:01,  1.69it/s]
 75%|███████▌  | 6/8 [00:03<00:01,  1.69it/s]
 88%|████████▊ | 7/8 [00:04<00:00,  1.69it/s]
100%|██████████| 8/8 [00:04<00:00,  1.69it/s]
100%|██████████| 8/8 [00:04<00:00,  1.69it/s]
  0%|          | 0/8 [00:00<?, ?it/s]
 12%|█▎        | 1/8 [00:00<00:04,  1.69it/s]
 25%|██▌       | 2/8 [00:01<00:03,  1.69it/s]
 38%|███▊      | 3/8 [00:01<00:02,  1.69it/s]
 50%|█████     | 4/8 [00:02<00:02,  1.68it/s]
 62%|██████▎   | 5/8 [00:02<00:01,  1.68it/s]
 75%|███████▌  | 6/8 [00:03<00:01,  1.68it/s]
 88%|████████▊ | 7/8 [00:04<00:00,  1.68it/s]
100%|██████████| 8/8 [00:04<00:00,  1.69it/s]
100%|██████████| 8/8 [00:04<00:00,  1.68it/s]
  0%|          | 0/8 [00:00<?, ?it/s]
 12%|█▎        | 1/8 [00:00<00:04,  1.69it/s]
 25%|██▌       | 2/8 [00:01<00:03,  1.69it/s]
 38%|███▊      | 3/8 [00:01<00:02,  1.69it/s]
 50%|█████     | 4/8 [00:02<00:02,  1.68it/s]
 62%|██████▎   | 5/8 [00:02<00:01,  1.68it/s]
 75%|███████▌  | 6/8 [00:03<00:01,  1.68it/s]
 88%|████████▊ | 7/8 [00:04<00:00,  1.68it/s]
100%|██████████| 8/8 [00:04<00:00,  1.68it/s]
100%|██████████| 8/8 [00:04<00:00,  1.68it/s]
Total safe images: 4 out of 4

This output was created using a different version of the model, fire/flux:de30fa90.

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

This model doesn't have a readme.