dcamsdev/klm-lora-flux – Run with an API on Replicate

dcamsdev / klm-lora-flux

Creates realistic KLM flight attendants

Warm

Public
225 runs
H100

Run with an API

Playground API Examples README Versions

Input

prompt

*string

Shift + Return to add a new line

A female KLM flight attendant windsurfing in the sea, looking at camera and smiling, colorful setting, in style of a film scene, cinematinc lighting, koda, film styleA female KLM flight attendant windsurfing in the sea, looking at camera and smiling, colorful setting, in style of a film scene, cinematinc lighting, koda, film style

Prompt for generated image. If you include the `trigger_word` used in the training process you are more likely to activate the trained object, style, or concept in the resulting image.

image

file

Input image for image to image or inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored.

mask

file

Image mask for image inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored.

aspect_ratio

string

Aspect ratio for the generated image. If custom is selected, uses height and width below & will run in bf16 mode

Default: "1:1"

height

integer

(minimum: 256, maximum: 1440)

Height of generated image. Only works if `aspect_ratio` is set to custom. Will be rounded to nearest multiple of 16. Incompatible with fast generation

width

integer

(minimum: 256, maximum: 1440)

Width of generated image. Only works if `aspect_ratio` is set to custom. Will be rounded to nearest multiple of 16. Incompatible with fast generation

prompt_strength

number

(minimum: 0, maximum: 1)

Prompt strength when using img2img. 1.0 corresponds to full destruction of information in image

Default: 0.8

model

string

Which model to run inference with. The dev model performs best with around 28 inference steps but the schnell model only needs 4 steps.

Default: "dev"

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. More steps can give more detailed images, but take longer.

Default: 28

guidance_scale

number

(minimum: 0, maximum: 10)

Guidance scale for the diffusion process. Lower values can give more realistic images. Good values to try are 2, 2.5, 3 and 3.5

Default: 3

seed

integer

Random seed. Set for reproducible generation

output_format

string

Format of the output images

Default: "webp"

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: false

megapixels

string

Approximate number of megapixels for generated image

Default: "1"

lora_scale

number

(minimum: -1, maximum: 3)

Determines how strongly the main LoRA should be applied. Sane results between 0 and 1 for base inference. For go_fast we apply a 1.5x multiplier to this value; we've generally seen good performance when scaling the base value by that amount. You may still need to experiment to find the best value for your particular lora.

Default: 1

extra_lora

string

Shift + Return to add a new line

Load LoRA weights. Supports Replicate models in the format <owner>/<username> or <owner>/<username>/<version>, HuggingFace URLs in the format huggingface.co/<owner>/<model-name>, CivitAI URLs in the format civitai.com/models/<id>[/<model-name>], or arbitrary .safetensors URLs from the Internet. For example, 'fofr/flux-pixar-cars'

extra_lora_scale

number

(minimum: -1, maximum: 3)

Determines how strongly the extra LoRA should be applied. Sane results between 0 and 1 for base inference. For go_fast we apply a 1.5x multiplier to this value; we've generally seen good performance when scaling the base value by that amount. You may still need to experiment to find the best value for your particular lora.

Default: 1

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

npx create-replicate --model=dcamsdev/klm-lora-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";

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

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

const output = await replicate.run(
  "dcamsdev/klm-lora-flux:b44d8509a34daf2f6bb469c31bb3e4864fc2660dddd496a994f65da395c8f8e6",
  {
    input: {
      model: "dev",
      prompt: "A female KLM flight attendant windsurfing in the sea, looking at camera and smiling, colorful setting, in style of a film scene, cinematinc lighting, koda, film style",
      go_fast: false,
      lora_scale: 0.94,
      megapixels: "1",
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "webp",
      guidance_scale: 5.77,
      output_quality: 90,
      prompt_strength: 0.85,
      extra_lora_scale: 1,
      num_inference_steps: 28
    }
  }
);

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

output = replicate.run(
    "dcamsdev/klm-lora-flux:b44d8509a34daf2f6bb469c31bb3e4864fc2660dddd496a994f65da395c8f8e6",
    input={
        "model": "dev",
        "prompt": "A female KLM flight attendant windsurfing in the sea, looking at camera and smiling, colorful setting, in style of a film scene, cinematinc lighting, koda, film style",
        "go_fast": False,
        "lora_scale": 0.94,
        "megapixels": "1",
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "webp",
        "guidance_scale": 5.77,
        "output_quality": 90,
        "prompt_strength": 0.85,
        "extra_lora_scale": 1,
        "num_inference_steps": 28
    }
)
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 dcamsdev/klm-lora-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": "b44d8509a34daf2f6bb469c31bb3e4864fc2660dddd496a994f65da395c8f8e6",
    "input": {
      "model": "dev",
      "prompt": "A female KLM flight attendant windsurfing in the sea, looking at camera and smiling, colorful setting, in style of a film scene, cinematinc lighting, koda, film style",
      "go_fast": false,
      "lora_scale": 0.94,
      "megapixels": "1",
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "webp",
      "guidance_scale": 5.77,
      "output_quality": 90,
      "prompt_strength": 0.85,
      "extra_lora_scale": 1,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2024-09-05T16:55:46.789645Z",
  "created_at": "2024-09-05T16:55:28.624000Z",
  "data_removed": false,
  "error": null,
  "id": "1at83vy6e1rm20chrcead7qxnr",
  "input": {
    "model": "dev",
    "prompt": "A female KLM flight attendant windsurfing in the sea, looking at camera and smiling, colorful setting, in style of a film scene, cinematinc lighting, koda, film style",
    "lora_scale": 0.94,
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "webp",
    "guidance_scale": 5.77,
    "output_quality": 90,
    "prompt_strength": 0.85,
    "extra_lora_scale": 1,
    "num_inference_steps": 28
  },
  "logs": "Using seed: 37009\nPrompt: A female KLM flight attendant windsurfing in the sea, looking at camera and smiling, colorful setting, in style of a film scene, cinematinc lighting, koda, film style\n[!] txt2img mode\nUsing dev model\nfree=8459560759296\nDownloading weights\n2024-09-05T16:55:28Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmp1muvasxo/weights url=https://replicate.delivery/yhqm/p0FaD61vYVpmCtW4RqCbce1Dk7avKxfNLW6Sx8QwTKrRi3ZTA/trained_model.tar\n2024-09-05T16:55:30Z | INFO  | [ Complete ] dest=/tmp/tmp1muvasxo/weights size=\"172 MB\" total_elapsed=1.373s url=https://replicate.delivery/yhqm/p0FaD61vYVpmCtW4RqCbce1Dk7avKxfNLW6Sx8QwTKrRi3ZTA/trained_model.tar\nDownloaded weights in 1.40s\nLoaded LoRAs in 9.62s\n  0%|          | 0/28 [00:00<?, ?it/s]\n  4%|▎         | 1/28 [00:00<00:07,  3.40it/s]\n  7%|▋         | 2/28 [00:00<00:06,  3.78it/s]\n 11%|█         | 3/28 [00:00<00:06,  3.64it/s]\n 14%|█▍        | 4/28 [00:01<00:06,  3.58it/s]\n 18%|█▊        | 5/28 [00:01<00:06,  3.56it/s]\n 21%|██▏       | 6/28 [00:01<00:06,  3.53it/s]\n 25%|██▌       | 7/28 [00:01<00:05,  3.52it/s]\n 29%|██▊       | 8/28 [00:02<00:05,  3.52it/s]\n 32%|███▏      | 9/28 [00:02<00:05,  3.50it/s]\n 36%|███▌      | 10/28 [00:02<00:05,  3.50it/s]\n 39%|███▉      | 11/28 [00:03<00:04,  3.50it/s]\n 43%|████▎     | 12/28 [00:03<00:04,  3.49it/s]\n 46%|████▋     | 13/28 [00:03<00:04,  3.49it/s]\n 50%|█████     | 14/28 [00:03<00:04,  3.49it/s]\n 54%|█████▎    | 15/28 [00:04<00:03,  3.48it/s]\n 57%|█████▋    | 16/28 [00:04<00:03,  3.49it/s]\n 61%|██████    | 17/28 [00:04<00:03,  3.49it/s]\n 64%|██████▍   | 18/28 [00:05<00:02,  3.49it/s]\n 68%|██████▊   | 19/28 [00:05<00:02,  3.49it/s]\n 71%|███████▏  | 20/28 [00:05<00:02,  3.49it/s]\n 75%|███████▌  | 21/28 [00:05<00:02,  3.49it/s]\n 79%|███████▊  | 22/28 [00:06<00:01,  3.48it/s]\n 82%|████████▏ | 23/28 [00:06<00:01,  3.49it/s]\n 86%|████████▌ | 24/28 [00:06<00:01,  3.48it/s]\n 89%|████████▉ | 25/28 [00:07<00:00,  3.49it/s]\n 93%|█████████▎| 26/28 [00:07<00:00,  3.49it/s]\n 96%|█████████▋| 27/28 [00:07<00:00,  3.48it/s]\n100%|██████████| 28/28 [00:07<00:00,  3.49it/s]\n100%|██████████| 28/28 [00:07<00:00,  3.50it/s]",
  "metrics": {
    "predict_time": 18.155520949,
    "total_time": 18.165645
  },
  "output": [
    "https://replicate.delivery/yhqm/PFK6S8rOuAKMB91CXlvKMZ8zI3lAtCZtdKFAiR8651pkUesJA/out-0.webp"
  ],
  "started_at": "2024-09-05T16:55:28.634124Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/1at83vy6e1rm20chrcead7qxnr",
    "cancel": "https://api.replicate.com/v1/predictions/1at83vy6e1rm20chrcead7qxnr/cancel"
  },
  "version": "b44d8509a34daf2f6bb469c31bb3e4864fc2660dddd496a994f65da395c8f8e6"
}

Generated in

18.2 seconds

Tweak it ShareReport

Using seed: 37009
Prompt: A female KLM flight attendant windsurfing in the sea, looking at camera and smiling, colorful setting, in style of a film scene, cinematinc lighting, koda, film style
[!] txt2img mode
Using dev model
free=8459560759296
Downloading weights
2024-09-05T16:55:28Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmp1muvasxo/weights url=https://replicate.delivery/yhqm/p0FaD61vYVpmCtW4RqCbce1Dk7avKxfNLW6Sx8QwTKrRi3ZTA/trained_model.tar
2024-09-05T16:55:30Z | INFO  | [ Complete ] dest=/tmp/tmp1muvasxo/weights size="172 MB" total_elapsed=1.373s url=https://replicate.delivery/yhqm/p0FaD61vYVpmCtW4RqCbce1Dk7avKxfNLW6Sx8QwTKrRi3ZTA/trained_model.tar
Downloaded weights in 1.40s
Loaded LoRAs in 9.62s
  0%|          | 0/28 [00:00<?, ?it/s]
  4%|▎         | 1/28 [00:00<00:07,  3.40it/s]
  7%|▋         | 2/28 [00:00<00:06,  3.78it/s]
 11%|█         | 3/28 [00:00<00:06,  3.64it/s]
 14%|█▍        | 4/28 [00:01<00:06,  3.58it/s]
 18%|█▊        | 5/28 [00:01<00:06,  3.56it/s]
 21%|██▏       | 6/28 [00:01<00:06,  3.53it/s]
 25%|██▌       | 7/28 [00:01<00:05,  3.52it/s]
 29%|██▊       | 8/28 [00:02<00:05,  3.52it/s]
 32%|███▏      | 9/28 [00:02<00:05,  3.50it/s]
 36%|███▌      | 10/28 [00:02<00:05,  3.50it/s]
 39%|███▉      | 11/28 [00:03<00:04,  3.50it/s]
 43%|████▎     | 12/28 [00:03<00:04,  3.49it/s]
 46%|████▋     | 13/28 [00:03<00:04,  3.49it/s]
 50%|█████     | 14/28 [00:03<00:04,  3.49it/s]
 54%|█████▎    | 15/28 [00:04<00:03,  3.48it/s]
 57%|█████▋    | 16/28 [00:04<00:03,  3.49it/s]
 61%|██████    | 17/28 [00:04<00:03,  3.49it/s]
 64%|██████▍   | 18/28 [00:05<00:02,  3.49it/s]
 68%|██████▊   | 19/28 [00:05<00:02,  3.49it/s]
 71%|███████▏  | 20/28 [00:05<00:02,  3.49it/s]
 75%|███████▌  | 21/28 [00:05<00:02,  3.49it/s]
 79%|███████▊  | 22/28 [00:06<00:01,  3.48it/s]
 82%|████████▏ | 23/28 [00:06<00:01,  3.49it/s]
 86%|████████▌ | 24/28 [00:06<00:01,  3.48it/s]
 89%|████████▉ | 25/28 [00:07<00:00,  3.49it/s]
 93%|█████████▎| 26/28 [00:07<00:00,  3.49it/s]
 96%|█████████▋| 27/28 [00:07<00:00,  3.48it/s]
100%|██████████| 28/28 [00:07<00:00,  3.49it/s]
100%|██████████| 28/28 [00:07<00:00,  3.50it/s]

Examples

View more examples

Run time and cost

This model costs approximately $0.052 to run on Replicate, or 19 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 H100 GPU hardware. Predictions typically complete within 35 seconds. The predict time for this model varies significantly based on the inputs.

Readme

This model doesn't have a readme.