zhangp365/flux_loras | Run with an API on Replicate

Public

99 runs

A100 (80GB)

Run with an API

Pricing

Playground API Examples README Versions

Input

prompt

string

Shift + Return to add a new line

Ghibli Studio style, Charming hand-drawn anime-style illustrationGhibli Studio style, Charming hand-drawn anime-style illustration

Enter a text prompt to guide image generation.

Default: ""

height

integer

(minimum: 0, maximum: 1600)

The height will decide by the first spatial image. no need to set it.

Default: 0

width

integer

(minimum: 0, maximum: 1600)

The width will decide by the first spatial image. no need to set it.

Default: 0

seed

integer

Set a random seed for generation (-1 for random).

Default: 42

use_zero_init

boolean

Use CFG zero star.

Default: true

zero_steps

integer

(minimum: 0)

Zero init steps.

Default: 1

image

*file

reference image.

control_type

string

Control type (now only support two types, pose and mine_craft).

Default: "Ghibli"

control_weight

number

Control weights (must correspond to the control type).

Default: 1

extra_image

file

extra reference image.

extra_control_type

string

Extra control type (now only support two types, pose and mine_craft).

extra_control_weight

number

Extra control weights (must correspond to the extra control type).

Default: 1

output_format

string

Choose the format of the output images.

Default: "png"

output_quality

integer

(minimum: 1, maximum: 100)

Set the quality of the output image for jpg and webp (1-100).

Default: 90

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

npx create-replicate --model=zhangp365/flux_loras

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 zhangp365/flux_loras using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "zhangp365/flux_loras:5f2171037f55d162ec5501c12ed560b5a46409ff667ba9438fbc82a325241749",
  {
    input: {
      seed: 42,
      width: 0,
      height: 0,
      prompt: "Ghibli Studio style, Charming hand-drawn anime-style illustration",
      zero_steps: 1,
      control_type: "Ghibli",
      output_format: "png",
      use_zero_init: true,
      control_weight: 1.2,
      output_quality: 90,
      extra_control_type: "pose",
      extra_control_weight: 0.65
    }
  }
);

// 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 zhangp365/flux_loras using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "zhangp365/flux_loras:5f2171037f55d162ec5501c12ed560b5a46409ff667ba9438fbc82a325241749",
    input={
        "seed": 42,
        "width": 0,
        "height": 0,
        "prompt": "Ghibli Studio style, Charming hand-drawn anime-style illustration",
        "zero_steps": 1,
        "control_type": "Ghibli",
        "output_format": "png",
        "use_zero_init": True,
        "control_weight": 1.2,
        "output_quality": 90,
        "extra_control_type": "pose",
        "extra_control_weight": 0.65
    }
)

# 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 zhangp365/flux_loras 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": "zhangp365/flux_loras:5f2171037f55d162ec5501c12ed560b5a46409ff667ba9438fbc82a325241749",
    "input": {
      "seed": 42,
      "width": 0,
      "height": 0,
      "prompt": "Ghibli Studio style, Charming hand-drawn anime-style illustration",
      "zero_steps": 1,
      "control_type": "Ghibli",
      "output_format": "png",
      "use_zero_init": true,
      "control_weight": 1.2,
      "output_quality": 90,
      "extra_control_type": "pose",
      "extra_control_weight": 0.65
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2025-05-09T08:09:19.009473Z",
  "created_at": "2025-05-09T08:06:04.789000Z",
  "data_removed": false,
  "error": null,
  "id": "5gp0atm0ynrj40cppga8js7r3r",
  "input": {
    "seed": 42,
    "width": 0,
    "height": 0,
    "prompt": "Ghibli Studio style, Charming hand-drawn anime-style illustration",
    "zero_steps": 1,
    "spatial_img": "https://replicate.delivery/pbxt/MyLRTYOlEZDnYTq6QTLWQOkNhEo6HJf22SvMtiNPtRndo390/boy.png",
    "control_type": "Ghibli",
    "output_format": "png",
    "use_zero_init": true,
    "control_weight": 1.2,
    "output_quality": 90,
    "extra_spatial_img": "https://replicate.delivery/pbxt/MyLRSx6uGs94l0zLLAvnIenJwPbj2iFC95oKLbQce4XfAYQd/ComfyUI_00070_.jpg",
    "extra_control_type": "pose",
    "extra_control_weight": 0.65
  },
  "logs": "Loading .safetensors checkpoint from ./checkpoints/models/models/Ghibli.safetensors\nLoading .safetensors checkpoint from ./checkpoints/models/models/pose.safetensors\n2025-05-09 08:08:50,533 - INFO - 219 - Multi LoRA applied successfully.\n2025-05-09 08:08:50,533 - INFO - 231 - Using seed: 42\n2025-05-09 08:08:50,591 - INFO - 247 - Loaded spatial image from: /tmp/tmp5l5tmrj4boy.png\n2025-05-09 08:08:50,594 - INFO - 247 - Loaded spatial image from: /tmp/tmpd1yp3vstComfyUI_00070_.jpg\n2025-05-09 08:08:50,594 - INFO - 266 - Generating image with use_zero_init=True...\n<PIL.Image.Image image mode=RGB size=1024x1536 at 0x7BF00CAB5010>\n<PIL.Image.Image image mode=RGB size=512x768 at 0x7BEFE69FC890>\n  0%|          | 0/25 [00:00<?, ?it/s]\n  4%|▍         | 1/25 [00:01<00:25,  1.07s/it]\n  8%|▊         | 2/25 [00:01<00:20,  1.12it/s]\n 12%|█▏        | 3/25 [00:02<00:21,  1.05it/s]\n 16%|█▌        | 4/25 [00:03<00:20,  1.01it/s]\n 20%|██        | 5/25 [00:04<00:20,  1.00s/it]\n 24%|██▍       | 6/25 [00:05<00:19,  1.01s/it]\n 28%|██▊       | 7/25 [00:07<00:18,  1.02s/it]\n 32%|███▏      | 8/25 [00:08<00:17,  1.03s/it]\n 36%|███▌      | 9/25 [00:09<00:16,  1.03s/it]\n 40%|████      | 10/25 [00:10<00:15,  1.03s/it]\n 44%|████▍     | 11/25 [00:11<00:14,  1.03s/it]\n 48%|████▊     | 12/25 [00:12<00:13,  1.03s/it]\n 52%|█████▏    | 13/25 [00:13<00:12,  1.03s/it]\n 56%|█████▌    | 14/25 [00:14<00:11,  1.04s/it]\n 60%|██████    | 15/25 [00:15<00:10,  1.04s/it]\n 64%|██████▍   | 16/25 [00:16<00:09,  1.04s/it]\n 68%|██████▊   | 17/25 [00:17<00:08,  1.04s/it]\n 72%|███████▏  | 18/25 [00:18<00:07,  1.04s/it]\n 76%|███████▌  | 19/25 [00:19<00:06,  1.04s/it]\n 80%|████████  | 20/25 [00:20<00:05,  1.04s/it]\n 84%|████████▍ | 21/25 [00:21<00:04,  1.04s/it]\n 88%|████████▊ | 22/25 [00:22<00:03,  1.04s/it]\n 92%|█████████▏| 23/25 [00:23<00:02,  1.04s/it]\n 96%|█████████▌| 24/25 [00:24<00:01,  1.04s/it]\n100%|██████████| 25/25 [00:25<00:00,  1.04s/it]\n100%|██████████| 25/25 [00:25<00:00,  1.03s/it]\n2025-05-09 08:09:18,407 - INFO - 283 - Generated 'zeroinit' image in 27.81s\n2025-05-09 08:09:18,988 - INFO - 330 - Saved: output_seed42.png\n2025-05-09 08:09:18,988 - INFO - 331 - Saved output in 0.57s\n2025-05-09 08:09:18,988 - INFO - 340 - Total prediction time: 28.89 seconds",
  "metrics": {
    "predict_time": 29.248009889,
    "total_time": 194.220473
  },
  "output": [
    "https://replicate.delivery/yhqm/EDPo8wmfhIzBBqkHMeaoxdpvTym7VsecAioeknQfXnezLqtKF/output_seed42.png"
  ],
  "started_at": "2025-05-09T08:08:49.761463Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/qoxq-pzjrp5w36jqfqziclbjtccfylgfaz7wgqmbpbyuiazdjsmro3tnq",
    "get": "https://api.replicate.com/v1/predictions/5gp0atm0ynrj40cppga8js7r3r",
    "cancel": "https://api.replicate.com/v1/predictions/5gp0atm0ynrj40cppga8js7r3r/cancel"
  },
  "version": "040a409de8e9358addafd8346559501454ecf3af9fae9a6c695482273d9f292b"
}

Generated in

29.3 seconds

Tweak it Iterate in playground Share Report View full prediction

Loading .safetensors checkpoint from ./checkpoints/models/models/Ghibli.safetensors
Loading .safetensors checkpoint from ./checkpoints/models/models/pose.safetensors
2025-05-09 08:08:50,533 - INFO - 219 - Multi LoRA applied successfully.
2025-05-09 08:08:50,533 - INFO - 231 - Using seed: 42
2025-05-09 08:08:50,591 - INFO - 247 - Loaded spatial image from: /tmp/tmp5l5tmrj4boy.png
2025-05-09 08:08:50,594 - INFO - 247 - Loaded spatial image from: /tmp/tmpd1yp3vstComfyUI_00070_.jpg
2025-05-09 08:08:50,594 - INFO - 266 - Generating image with use_zero_init=True...
<PIL.Image.Image image mode=RGB size=1024x1536 at 0x7BF00CAB5010>
<PIL.Image.Image image mode=RGB size=512x768 at 0x7BEFE69FC890>
  0%|          | 0/25 [00:00<?, ?it/s]
  4%|▍         | 1/25 [00:01<00:25,  1.07s/it]
  8%|▊         | 2/25 [00:01<00:20,  1.12it/s]
 12%|█▏        | 3/25 [00:02<00:21,  1.05it/s]
 16%|█▌        | 4/25 [00:03<00:20,  1.01it/s]
 20%|██        | 5/25 [00:04<00:20,  1.00s/it]
 24%|██▍       | 6/25 [00:05<00:19,  1.01s/it]
 28%|██▊       | 7/25 [00:07<00:18,  1.02s/it]
 32%|███▏      | 8/25 [00:08<00:17,  1.03s/it]
 36%|███▌      | 9/25 [00:09<00:16,  1.03s/it]
 40%|████      | 10/25 [00:10<00:15,  1.03s/it]
 44%|████▍     | 11/25 [00:11<00:14,  1.03s/it]
 48%|████▊     | 12/25 [00:12<00:13,  1.03s/it]
 52%|█████▏    | 13/25 [00:13<00:12,  1.03s/it]
 56%|█████▌    | 14/25 [00:14<00:11,  1.04s/it]
 60%|██████    | 15/25 [00:15<00:10,  1.04s/it]
 64%|██████▍   | 16/25 [00:16<00:09,  1.04s/it]
 68%|██████▊   | 17/25 [00:17<00:08,  1.04s/it]
 72%|███████▏  | 18/25 [00:18<00:07,  1.04s/it]
 76%|███████▌  | 19/25 [00:19<00:06,  1.04s/it]
 80%|████████  | 20/25 [00:20<00:05,  1.04s/it]
 84%|████████▍ | 21/25 [00:21<00:04,  1.04s/it]
 88%|████████▊ | 22/25 [00:22<00:03,  1.04s/it]
 92%|█████████▏| 23/25 [00:23<00:02,  1.04s/it]
 96%|█████████▌| 24/25 [00:24<00:01,  1.04s/it]
100%|██████████| 25/25 [00:25<00:00,  1.04s/it]
100%|██████████| 25/25 [00:25<00:00,  1.03s/it]
2025-05-09 08:09:18,407 - INFO - 283 - Generated 'zeroinit' image in 27.81s
2025-05-09 08:09:18,988 - INFO - 330 - Saved: output_seed42.png
2025-05-09 08:09:18,988 - INFO - 331 - Saved output in 0.57s
2025-05-09 08:09:18,988 - INFO - 340 - Total prediction time: 28.89 seconds

This output was created using a different version of the model, zhangp365/flux_loras:040a409d.

Examples

View more examples

Run time and cost

This model runs on Nvidia A100 (80GB) GPU hardware. We don't yet have enough runs of this model to provide performance information.

Readme

This model doesn't have a readme.