Prediction

bytedance/hyper-flux-8step:16084e97

Model

bytedance/hyper-flux-8step:81946b1e

ID

zr6w3kzn81rm60cjb6j9sqh5pc

Status

Succeeded

Source

Web

Hardware

H100

Total duration

4.4s

Created

6 months ago

Input

prompt: a dog smiling and looking directly at the camera, wearing a white t-shirt with the word "HYPER" printed on it.
num_outputs: 1
aspect_ratio: 1:1
output_format: webp
guidance_scale: 3.5
output_quality: 80
num_inference_steps: 8

{
  "prompt": "a dog smiling and looking directly at the camera, wearing a white t-shirt with the word \"HYPER\" printed on it.",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 3.5,
  "output_quality": 80,
  "num_inference_steps": 8
}

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 bytedance/hyper-flux-8step using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "bytedance/hyper-flux-8step:16084e9731223a4367228928a6cb393b21736da2a0ca6a5a492ce311f0a97143",
  {
    input: {
      prompt: "a dog smiling and looking directly at the camera, wearing a white t-shirt with the word \"HYPER\" printed on it.",
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "webp",
      guidance_scale: 3.5,
      output_quality: 80,
      num_inference_steps: 8
    }
  }
);
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 bytedance/hyper-flux-8step using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "bytedance/hyper-flux-8step:16084e9731223a4367228928a6cb393b21736da2a0ca6a5a492ce311f0a97143",
    input={
        "prompt": "a dog smiling and looking directly at the camera, wearing a white t-shirt with the word \"HYPER\" printed on it.",
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "webp",
        "guidance_scale": 3.5,
        "output_quality": 80,
        "num_inference_steps": 8
    }
)
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 bytedance/hyper-flux-8step 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": "16084e9731223a4367228928a6cb393b21736da2a0ca6a5a492ce311f0a97143",
    "input": {
      "prompt": "a dog smiling and looking directly at the camera, wearing a white t-shirt with the word \\"HYPER\\" printed on it.",
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "webp",
      "guidance_scale": 3.5,
      "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

Generated in

2.1 seconds

Tweak it ShareReport

Prediction

bytedance/hyper-flux-8step:16084e97

Model

bytedance/hyper-flux-8step:81946b1e

ID

rpngbjmc8srm00cjb6jsy9gkfm

Status

Succeeded

Source

Web

Hardware

H100

Total duration

2.1s

Created

6 months ago

Input

prompt: a digital portrait of a woman with a pensive expression, her hair styled in a messy bun adorned with splashes of color
num_outputs: 1
aspect_ratio: 1:1
output_format: webp
guidance_scale: 3.5
output_quality: 80
num_inference_steps: 8

{
  "prompt": "a digital portrait of a woman with a pensive expression, her hair styled in a messy bun adorned with splashes of color",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 3.5,
  "output_quality": 80,
  "num_inference_steps": 8
}

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 bytedance/hyper-flux-8step using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "bytedance/hyper-flux-8step:16084e9731223a4367228928a6cb393b21736da2a0ca6a5a492ce311f0a97143",
  {
    input: {
      prompt: "a digital portrait of a woman with a pensive expression, her hair styled in a messy bun adorned with splashes of color",
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "webp",
      guidance_scale: 3.5,
      output_quality: 80,
      num_inference_steps: 8
    }
  }
);
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 bytedance/hyper-flux-8step using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "bytedance/hyper-flux-8step:16084e9731223a4367228928a6cb393b21736da2a0ca6a5a492ce311f0a97143",
    input={
        "prompt": "a digital portrait of a woman with a pensive expression, her hair styled in a messy bun adorned with splashes of color",
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "webp",
        "guidance_scale": 3.5,
        "output_quality": 80,
        "num_inference_steps": 8
    }
)
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 bytedance/hyper-flux-8step 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": "16084e9731223a4367228928a6cb393b21736da2a0ca6a5a492ce311f0a97143",
    "input": {
      "prompt": "a digital portrait of a woman with a pensive expression, her hair styled in a messy bun adorned with splashes of color",
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "webp",
      "guidance_scale": 3.5,
      "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

Generated in

2.1 seconds

Tweak it ShareReport

Prediction

bytedance/hyper-flux-8step:16084e97

Model

bytedance/hyper-flux-8step:81946b1e

ID

yvy74vgxx9rm00cjb6k97ttp08

Status

Succeeded

Source

Web

Hardware

H100

Total duration

2.1s

Created

6 months ago

Input

prompt: a heart-shaped glass object, filled with green plants, rests on a mossy surface, surrounded by rocks and other greenery, with sunlight filtering through the foliage.
num_outputs: 1
aspect_ratio: 1:1
output_format: webp
guidance_scale: 3.5
output_quality: 80
num_inference_steps: 8

{
  "prompt": "a heart-shaped glass object, filled with green plants, rests on a mossy surface, surrounded by rocks and other greenery, with sunlight filtering through the foliage.",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 3.5,
  "output_quality": 80,
  "num_inference_steps": 8
}

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 bytedance/hyper-flux-8step using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "bytedance/hyper-flux-8step:16084e9731223a4367228928a6cb393b21736da2a0ca6a5a492ce311f0a97143",
  {
    input: {
      prompt: "a heart-shaped glass object, filled with green plants, rests on a mossy surface, surrounded by rocks and other greenery, with sunlight filtering through the foliage.",
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "webp",
      guidance_scale: 3.5,
      output_quality: 80,
      num_inference_steps: 8
    }
  }
);
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 bytedance/hyper-flux-8step using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "bytedance/hyper-flux-8step:16084e9731223a4367228928a6cb393b21736da2a0ca6a5a492ce311f0a97143",
    input={
        "prompt": "a heart-shaped glass object, filled with green plants, rests on a mossy surface, surrounded by rocks and other greenery, with sunlight filtering through the foliage.",
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "webp",
        "guidance_scale": 3.5,
        "output_quality": 80,
        "num_inference_steps": 8
    }
)
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 bytedance/hyper-flux-8step 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": "16084e9731223a4367228928a6cb393b21736da2a0ca6a5a492ce311f0a97143",
    "input": {
      "prompt": "a heart-shaped glass object, filled with green plants, rests on a mossy surface, surrounded by rocks and other greenery, with sunlight filtering through the foliage.",
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "webp",
      "guidance_scale": 3.5,
      "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

Generated in

2.1 seconds

Tweak it ShareReport

Prediction

bytedance/hyper-flux-8step:16084e97

Model

bytedance/hyper-flux-8step:81946b1e

ID

vefqapk55srm60cjb6k8y3r0zw

Status

Succeeded

Source

Web

Hardware

H100

Total duration

2.1s

Created

6 months ago

Input

prompt: womens street skateboarding final in Paris Olympics 2024
num_outputs: 1
aspect_ratio: 1:1
output_format: webp
guidance_scale: 3.5
output_quality: 80
num_inference_steps: 8

{
  "prompt": "womens street skateboarding final in Paris Olympics 2024",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 3.5,
  "output_quality": 80,
  "num_inference_steps": 8
}

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 bytedance/hyper-flux-8step using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "bytedance/hyper-flux-8step:16084e9731223a4367228928a6cb393b21736da2a0ca6a5a492ce311f0a97143",
  {
    input: {
      prompt: "womens street skateboarding final in Paris Olympics 2024",
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "webp",
      guidance_scale: 3.5,
      output_quality: 80,
      num_inference_steps: 8
    }
  }
);
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 bytedance/hyper-flux-8step using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "bytedance/hyper-flux-8step:16084e9731223a4367228928a6cb393b21736da2a0ca6a5a492ce311f0a97143",
    input={
        "prompt": "womens street skateboarding final in Paris Olympics 2024",
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "webp",
        "guidance_scale": 3.5,
        "output_quality": 80,
        "num_inference_steps": 8
    }
)
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 bytedance/hyper-flux-8step 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": "16084e9731223a4367228928a6cb393b21736da2a0ca6a5a492ce311f0a97143",
    "input": {
      "prompt": "womens street skateboarding final in Paris Olympics 2024",
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "webp",
      "guidance_scale": 3.5,
      "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

Generated in

2.1 seconds

Tweak it ShareReport

Prediction

bytedance/hyper-flux-8step:16084e97

Model

bytedance/hyper-flux-8step:81946b1e

ID

fqqze80rt1rm20cjb6ks63h404

Status

Succeeded

Source

Web

Hardware

H100

Total duration

20.5s

Created

6 months ago

Input

prompt: a deer in a suit with antlers standing amidst a forest of orange leaves, with a light source shining from above
num_outputs: 1
aspect_ratio: 1:1
output_format: webp
guidance_scale: 3.5
output_quality: 80
num_inference_steps: 8

{
  "prompt": "a deer in a suit with antlers standing amidst a forest of orange leaves, with a light source shining from above",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 3.5,
  "output_quality": 80,
  "num_inference_steps": 8
}

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 bytedance/hyper-flux-8step using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "bytedance/hyper-flux-8step:16084e9731223a4367228928a6cb393b21736da2a0ca6a5a492ce311f0a97143",
  {
    input: {
      prompt: "a deer in a suit with antlers standing amidst a forest of orange leaves, with a light source shining from above",
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "webp",
      guidance_scale: 3.5,
      output_quality: 80,
      num_inference_steps: 8
    }
  }
);
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 bytedance/hyper-flux-8step using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "bytedance/hyper-flux-8step:16084e9731223a4367228928a6cb393b21736da2a0ca6a5a492ce311f0a97143",
    input={
        "prompt": "a deer in a suit with antlers standing amidst a forest of orange leaves, with a light source shining from above",
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "webp",
        "guidance_scale": 3.5,
        "output_quality": 80,
        "num_inference_steps": 8
    }
)
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 bytedance/hyper-flux-8step 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": "16084e9731223a4367228928a6cb393b21736da2a0ca6a5a492ce311f0a97143",
    "input": {
      "prompt": "a deer in a suit with antlers standing amidst a forest of orange leaves, with a light source shining from above",
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "webp",
      "guidance_scale": 3.5,
      "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

Generated in

2.1 seconds

Tweak it ShareReport

Prediction

bytedance/hyper-flux-8step:16084e97

Model

bytedance/hyper-flux-8step:81946b1e

ID

rptjtzd08drm60cjb6ktb3msc8

Status

Succeeded

Source

Web

Hardware

H100

Total duration

2.1s

Created

6 months ago

Input

prompt: a blue paradise bird in the jungle
num_outputs: 1
aspect_ratio: 1:1
output_format: webp
guidance_scale: 3.5
output_quality: 80
num_inference_steps: 8

{
  "prompt": "a blue paradise bird in the jungle",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 3.5,
  "output_quality": 80,
  "num_inference_steps": 8
}

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 bytedance/hyper-flux-8step using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "bytedance/hyper-flux-8step:16084e9731223a4367228928a6cb393b21736da2a0ca6a5a492ce311f0a97143",
  {
    input: {
      prompt: "a blue paradise bird in the jungle",
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "webp",
      guidance_scale: 3.5,
      output_quality: 80,
      num_inference_steps: 8
    }
  }
);
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 bytedance/hyper-flux-8step using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "bytedance/hyper-flux-8step:16084e9731223a4367228928a6cb393b21736da2a0ca6a5a492ce311f0a97143",
    input={
        "prompt": "a blue paradise bird in the jungle",
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "webp",
        "guidance_scale": 3.5,
        "output_quality": 80,
        "num_inference_steps": 8
    }
)
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 bytedance/hyper-flux-8step 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": "16084e9731223a4367228928a6cb393b21736da2a0ca6a5a492ce311f0a97143",
    "input": {
      "prompt": "a blue paradise bird in the jungle",
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "webp",
      "guidance_scale": 3.5,
      "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

Generated in

2.1 seconds

Tweak it ShareReport

Prediction

bytedance/hyper-flux-8step:16084e97

Model

bytedance/hyper-flux-8step:81946b1e

ID

edec76qacdrm00cjb6ksar0vhr

Status

Succeeded

Source

Web

Hardware

H100

Total duration

2.1s

Created

6 months ago

Input

prompt: a serene landscape with mountains and a lake at sunset
num_outputs: 1
aspect_ratio: 1:1
output_format: webp
guidance_scale: 3.5
output_quality: 80
num_inference_steps: 8

{
  "prompt": "a serene landscape with mountains and a lake at sunset",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 3.5,
  "output_quality": 80,
  "num_inference_steps": 8
}

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 bytedance/hyper-flux-8step using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "bytedance/hyper-flux-8step:16084e9731223a4367228928a6cb393b21736da2a0ca6a5a492ce311f0a97143",
  {
    input: {
      prompt: "a serene landscape with mountains and a lake at sunset",
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "webp",
      guidance_scale: 3.5,
      output_quality: 80,
      num_inference_steps: 8
    }
  }
);
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 bytedance/hyper-flux-8step using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "bytedance/hyper-flux-8step:16084e9731223a4367228928a6cb393b21736da2a0ca6a5a492ce311f0a97143",
    input={
        "prompt": "a serene landscape with mountains and a lake at sunset",
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "webp",
        "guidance_scale": 3.5,
        "output_quality": 80,
        "num_inference_steps": 8
    }
)
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 bytedance/hyper-flux-8step 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": "16084e9731223a4367228928a6cb393b21736da2a0ca6a5a492ce311f0a97143",
    "input": {
      "prompt": "a serene landscape with mountains and a lake at sunset",
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "webp",
      "guidance_scale": 3.5,
      "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

Generated in

2.1 seconds

Tweak it ShareReport

Prediction

bytedance/hyper-flux-8step:16084e97

Model

bytedance/hyper-flux-8step:81946b1e

ID

za5h3nga11rm60cjb6q9r3w10r

Status

Succeeded

Source

Web

Hardware

H100

Total duration

4.7s

Created

6 months ago

Input

prompt: A chocolate cookie
num_outputs: 1
aspect_ratio: 1:1
output_format: webp
guidance_scale: 3.5
output_quality: 80
num_inference_steps: 8

{
  "prompt": "A chocolate cookie",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 3.5,
  "output_quality": 80,
  "num_inference_steps": 8
}

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 bytedance/hyper-flux-8step using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "bytedance/hyper-flux-8step:16084e9731223a4367228928a6cb393b21736da2a0ca6a5a492ce311f0a97143",
  {
    input: {
      prompt: "A chocolate cookie",
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "webp",
      guidance_scale: 3.5,
      output_quality: 80,
      num_inference_steps: 8
    }
  }
);
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 bytedance/hyper-flux-8step using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "bytedance/hyper-flux-8step:16084e9731223a4367228928a6cb393b21736da2a0ca6a5a492ce311f0a97143",
    input={
        "prompt": "A chocolate cookie",
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "webp",
        "guidance_scale": 3.5,
        "output_quality": 80,
        "num_inference_steps": 8
    }
)
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 bytedance/hyper-flux-8step 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": "16084e9731223a4367228928a6cb393b21736da2a0ca6a5a492ce311f0a97143",
    "input": {
      "prompt": "A chocolate cookie",
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "webp",
      "guidance_scale": 3.5,
      "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

Generated in

2.1 seconds

Tweak it ShareReport

bytedance / hyper-flux-8step

Prediction

Input

Output

Prediction

Input

Output

Prediction

Input

Output

Prediction

Input

Output

Prediction

Input

Output

Prediction

Input

Output

Prediction

Input

Output

Prediction

Input

Output

Logs (zr6w3kzn81rm60cjb6j9sqh5pc)

Logs (rpngbjmc8srm00cjb6jsy9gkfm)

Logs (yvy74vgxx9rm00cjb6k97ttp08)

Logs (vefqapk55srm60cjb6k8y3r0zw)

Logs (fqqze80rt1rm20cjb6ks63h404)

Logs (rptjtzd08drm60cjb6ktb3msc8)

Logs (edec76qacdrm00cjb6ksar0vhr)

Logs (za5h3nga11rm60cjb6q9r3w10r)