cloneofsimo / lora

LoRA Inference model with Stable Diffusion

Cold

Public
129.7K runs
A100 (80GB)
GitHub
Paper
License

Run with an API

Playground API Examples README Versions

Input

prompt

string

Shift + Return to add a new line

a photo of an astronaut riding a horse in the style of <1>a photo of an astronaut riding a horse in the style of <1>

Input prompt. Use <1>, <2>, <3>, etc., to specify LoRA concepts

Default: "a photo of <1> riding a horse on mars"

negative_prompt

string

Shift + Return to add a new line

Specify things to not see in the output

Default: ""

width

integer

Width of output image. Maximum size is 1024x768 or 768x1024 because of memory limits

Default: 512

height

integer

Height of output image. Maximum size is 1024x768 or 768x1024 because of memory limits

Default: 512

num_outputs

integer

(minimum: 1, maximum: 4)

Number of images to output.

Default: 1

num_inference_steps

integer

(minimum: 1, maximum: 500)

Number of denoising steps

Default: 50

guidance_scale

number

(minimum: 1, maximum: 20)

Scale for classifier-free guidance

Default: 7.5

image

file

(Img2Img) Inital image to generate variations of. If this is not none, Img2Img will be invoked.

prompt_strength

number

(Img2Img) Prompt strength when providing the image. 1.0 corresponds to full destruction of information in init image

Default: 0.8

scheduler

string

Choose a scheduler.

Default: "DPMSolverMultistep"

lora_urls

string

Shift + Return to add a new line

https://replicate.delivery/pbxt/c32Ba8UOS6bFDBwybc16WDREfzWCqeCRUzL3YtTgNrTIrqaQA/tmpan_f4msxcaravaggio.safetensorshttps://replicate.delivery/pbxt/c32Ba8UOS6bFDBwybc16WDREfzWCqeCRUzL3YtTgNrTIrqaQA/tmpan_f4msxcaravaggio.safetensors

List of urls for safetensors of lora models, seperated with | .

Default: ""

lora_scales

string

Shift + Return to add a new line

List of scales for safetensors of lora models, seperated with |

Default: "0.5"

seed

integer

Random seed. Leave blank to randomize the seed

adapter_condition_image

file

(T2I-adapter) Adapter Condition Image to gain extra control over generation. If this is not none, T2I adapter will be invoked. Width, Height of this image must match the above parameter, or dimension of the Img2Img image.

adapter_type

string

(T2I-adapter) Choose an adapter type for the additional condition.

Default: "sketch"

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

npx create-replicate --model=cloneofsimo/lora

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

const output = await replicate.run(
  "cloneofsimo/lora:fce477182f407ffd66b94b08e761424cabd13b82b518754b83080bc75ad32466",
  {
    input: {
      width: 512,
      height: 512,
      prompt: "a photo of an astronaut riding a horse in the style of <1>",
      lora_urls: "https://replicate.delivery/pbxt/c32Ba8UOS6bFDBwybc16WDREfzWCqeCRUzL3YtTgNrTIrqaQA/tmpan_f4msxcaravaggio.safetensors",
      scheduler: "DPMSolverMultistep",
      lora_scales: "0.6",
      num_outputs: 1,
      adapter_type: "sketch",
      guidance_scale: 7.5,
      negative_prompt: "frame",
      prompt_strength: 0.8,
      num_inference_steps: 50
    }
  }
);

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

output = replicate.run(
    "cloneofsimo/lora:fce477182f407ffd66b94b08e761424cabd13b82b518754b83080bc75ad32466",
    input={
        "width": 512,
        "height": 512,
        "prompt": "a photo of an astronaut riding a horse in the style of <1>",
        "lora_urls": "https://replicate.delivery/pbxt/c32Ba8UOS6bFDBwybc16WDREfzWCqeCRUzL3YtTgNrTIrqaQA/tmpan_f4msxcaravaggio.safetensors",
        "scheduler": "DPMSolverMultistep",
        "lora_scales": "0.6",
        "num_outputs": 1,
        "adapter_type": "sketch",
        "guidance_scale": 7.5,
        "negative_prompt": "frame",
        "prompt_strength": 0.8,
        "num_inference_steps": 50
    }
)
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 cloneofsimo/lora 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": "fce477182f407ffd66b94b08e761424cabd13b82b518754b83080bc75ad32466",
    "input": {
      "width": 512,
      "height": 512,
      "prompt": "a photo of an astronaut riding a horse in the style of <1>",
      "lora_urls": "https://replicate.delivery/pbxt/c32Ba8UOS6bFDBwybc16WDREfzWCqeCRUzL3YtTgNrTIrqaQA/tmpan_f4msxcaravaggio.safetensors",
      "scheduler": "DPMSolverMultistep",
      "lora_scales": "0.6",
      "num_outputs": 1,
      "adapter_type": "sketch",
      "guidance_scale": 7.5,
      "negative_prompt": "frame",
      "prompt_strength": 0.8,
      "num_inference_steps": 50
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2023-02-03T12:45:52.881913Z",
  "created_at": "2023-02-03T12:45:45.977984Z",
  "data_removed": false,
  "error": null,
  "id": "v7kbrzbsdjchxc3d37z5yheb6i",
  "input": {
    "width": 512,
    "height": 512,
    "prompt": "a photo of an astronaut riding a horse in the style of <1>",
    "lora_urls": "https://replicate.delivery/pbxt/c32Ba8UOS6bFDBwybc16WDREfzWCqeCRUzL3YtTgNrTIrqaQA/tmpan_f4msxcaravaggio.safetensors",
    "scheduler": "DPMSolverMultistep",
    "lora_scales": "0.6",
    "num_outputs": "1",
    "guidance_scale": 7.5,
    "negative_prompt": "frame",
    "num_inference_steps": 50
  },
  "logs": "Using seed: 12291\nThe requested LoRAs are loaded.\n  0%|          | 0/50 [00:00<?, ?it/s]\n  2%|▏         | 1/50 [00:00<00:06,  7.09it/s]\n  4%|▍         | 2/50 [00:00<00:06,  7.93it/s]\n  6%|▌         | 3/50 [00:00<00:05,  8.20it/s]\n  8%|▊         | 4/50 [00:00<00:05,  8.40it/s]\n 10%|█         | 5/50 [00:00<00:05,  8.50it/s]\n 12%|█▏        | 6/50 [00:00<00:05,  8.56it/s]\n 14%|█▍        | 7/50 [00:00<00:04,  8.61it/s]\n 16%|█▌        | 8/50 [00:00<00:04,  8.63it/s]\n 18%|█▊        | 9/50 [00:01<00:04,  8.64it/s]\n 20%|██        | 10/50 [00:01<00:04,  8.67it/s]\n 22%|██▏       | 11/50 [00:01<00:04,  8.68it/s]\n 24%|██▍       | 12/50 [00:01<00:04,  8.68it/s]\n 26%|██▌       | 13/50 [00:01<00:04,  8.69it/s]\n 28%|██▊       | 14/50 [00:01<00:04,  8.69it/s]\n 30%|███       | 15/50 [00:01<00:04,  8.69it/s]\n 32%|███▏      | 16/50 [00:01<00:03,  8.70it/s]\n 34%|███▍      | 17/50 [00:01<00:03,  8.70it/s]\n 36%|███▌      | 18/50 [00:02<00:03,  8.69it/s]\n 38%|███▊      | 19/50 [00:02<00:03,  8.71it/s]\n 40%|████      | 20/50 [00:02<00:03,  8.71it/s]\n 42%|████▏     | 21/50 [00:02<00:03,  8.62it/s]\n 44%|████▍     | 22/50 [00:02<00:03,  8.66it/s]\n 46%|████▌     | 23/50 [00:02<00:03,  8.69it/s]\n 48%|████▊     | 24/50 [00:02<00:02,  8.70it/s]\n 50%|█████     | 25/50 [00:02<00:02,  8.70it/s]\n 52%|█████▏    | 26/50 [00:03<00:02,  8.70it/s]\n 54%|█████▍    | 27/50 [00:03<00:02,  8.70it/s]\n 56%|█████▌    | 28/50 [00:03<00:02,  8.71it/s]\n 58%|█████▊    | 29/50 [00:03<00:02,  8.72it/s]\n 60%|██████    | 30/50 [00:03<00:02,  8.72it/s]\n 62%|██████▏   | 31/50 [00:03<00:02,  8.73it/s]\n 64%|██████▍   | 32/50 [00:03<00:02,  8.73it/s]\n 66%|██████▌   | 33/50 [00:03<00:01,  8.72it/s]\n 68%|██████▊   | 34/50 [00:03<00:01,  8.72it/s]\n 70%|███████   | 35/50 [00:04<00:01,  8.65it/s]\n 72%|███████▏  | 36/50 [00:04<00:01,  8.67it/s]\n 74%|███████▍  | 37/50 [00:04<00:01,  8.68it/s]\n 76%|███████▌  | 38/50 [00:04<00:01,  8.69it/s]\n 78%|███████▊  | 39/50 [00:04<00:01,  8.70it/s]\n 80%|████████  | 40/50 [00:04<00:01,  8.69it/s]\n 82%|████████▏ | 41/50 [00:04<00:01,  8.69it/s]\n 84%|████████▍ | 42/50 [00:04<00:00,  8.71it/s]\n 86%|████████▌ | 43/50 [00:04<00:00,  8.71it/s]\n 88%|████████▊ | 44/50 [00:05<00:00,  8.67it/s]\n 90%|█████████ | 45/50 [00:05<00:00,  8.67it/s]\n 92%|█████████▏| 46/50 [00:05<00:00,  8.67it/s]\n 94%|█████████▍| 47/50 [00:05<00:00,  8.68it/s]\n 96%|█████████▌| 48/50 [00:05<00:00,  8.69it/s]\n 98%|█████████▊| 49/50 [00:05<00:00,  8.67it/s]\n100%|██████████| 50/50 [00:05<00:00,  8.44it/s]\n100%|██████████| 50/50 [00:05<00:00,  8.63it/s]",
  "metrics": {
    "predict_time": 6.825229,
    "total_time": 6.903929
  },
  "output": [
    "https://replicate.delivery/pbxt/nySfVHmp27xpO6bGXVwn0LycmGVyveDBSC8OQeRTe7ABAtqBB/out-0.png"
  ],
  "started_at": "2023-02-03T12:45:46.056684Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/v7kbrzbsdjchxc3d37z5yheb6i",
    "cancel": "https://api.replicate.com/v1/predictions/v7kbrzbsdjchxc3d37z5yheb6i/cancel"
  },
  "version": "bb149dd20427beccf1b9f6332c7d5c233d914173fd463faa2c4a011080133afc"
}

Generated in

6.8 seconds

Tweak itReport

Using seed: 12291
The requested LoRAs are loaded.
  0%|          | 0/50 [00:00<?, ?it/s]
  2%|▏         | 1/50 [00:00<00:06,  7.09it/s]
  4%|▍         | 2/50 [00:00<00:06,  7.93it/s]
  6%|▌         | 3/50 [00:00<00:05,  8.20it/s]
  8%|▊         | 4/50 [00:00<00:05,  8.40it/s]
 10%|█         | 5/50 [00:00<00:05,  8.50it/s]
 12%|█▏        | 6/50 [00:00<00:05,  8.56it/s]
 14%|█▍        | 7/50 [00:00<00:04,  8.61it/s]
 16%|█▌        | 8/50 [00:00<00:04,  8.63it/s]
 18%|█▊        | 9/50 [00:01<00:04,  8.64it/s]
 20%|██        | 10/50 [00:01<00:04,  8.67it/s]
 22%|██▏       | 11/50 [00:01<00:04,  8.68it/s]
 24%|██▍       | 12/50 [00:01<00:04,  8.68it/s]
 26%|██▌       | 13/50 [00:01<00:04,  8.69it/s]
 28%|██▊       | 14/50 [00:01<00:04,  8.69it/s]
 30%|███       | 15/50 [00:01<00:04,  8.69it/s]
 32%|███▏      | 16/50 [00:01<00:03,  8.70it/s]
 34%|███▍      | 17/50 [00:01<00:03,  8.70it/s]
 36%|███▌      | 18/50 [00:02<00:03,  8.69it/s]
 38%|███▊      | 19/50 [00:02<00:03,  8.71it/s]
 40%|████      | 20/50 [00:02<00:03,  8.71it/s]
 42%|████▏     | 21/50 [00:02<00:03,  8.62it/s]
 44%|████▍     | 22/50 [00:02<00:03,  8.66it/s]
 46%|████▌     | 23/50 [00:02<00:03,  8.69it/s]
 48%|████▊     | 24/50 [00:02<00:02,  8.70it/s]
 50%|█████     | 25/50 [00:02<00:02,  8.70it/s]
 52%|█████▏    | 26/50 [00:03<00:02,  8.70it/s]
 54%|█████▍    | 27/50 [00:03<00:02,  8.70it/s]
 56%|█████▌    | 28/50 [00:03<00:02,  8.71it/s]
 58%|█████▊    | 29/50 [00:03<00:02,  8.72it/s]
 60%|██████    | 30/50 [00:03<00:02,  8.72it/s]
 62%|██████▏   | 31/50 [00:03<00:02,  8.73it/s]
 64%|██████▍   | 32/50 [00:03<00:02,  8.73it/s]
 66%|██████▌   | 33/50 [00:03<00:01,  8.72it/s]
 68%|██████▊   | 34/50 [00:03<00:01,  8.72it/s]
 70%|███████   | 35/50 [00:04<00:01,  8.65it/s]
 72%|███████▏  | 36/50 [00:04<00:01,  8.67it/s]
 74%|███████▍  | 37/50 [00:04<00:01,  8.68it/s]
 76%|███████▌  | 38/50 [00:04<00:01,  8.69it/s]
 78%|███████▊  | 39/50 [00:04<00:01,  8.70it/s]
 80%|████████  | 40/50 [00:04<00:01,  8.69it/s]
 82%|████████▏ | 41/50 [00:04<00:01,  8.69it/s]
 84%|████████▍ | 42/50 [00:04<00:00,  8.71it/s]
 86%|████████▌ | 43/50 [00:04<00:00,  8.71it/s]
 88%|████████▊ | 44/50 [00:05<00:00,  8.67it/s]
 90%|█████████ | 45/50 [00:05<00:00,  8.67it/s]
 92%|█████████▏| 46/50 [00:05<00:00,  8.67it/s]
 94%|█████████▍| 47/50 [00:05<00:00,  8.68it/s]
 96%|█████████▌| 48/50 [00:05<00:00,  8.69it/s]
 98%|█████████▊| 49/50 [00:05<00:00,  8.67it/s]
100%|██████████| 50/50 [00:05<00:00,  8.44it/s]
100%|██████████| 50/50 [00:05<00:00,  8.63it/s]

This output was created using a different version of the model, cloneofsimo/lora:bb149dd2.

Examples

View more examples

Run time and cost

This model costs approximately $0.015 to run on Replicate, or 66 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 11 seconds. The predict time for this model varies significantly based on the inputs.

Readme

LoRA inference

This model creates images from text, with given extra LoRA models.

There are two LoRA training models on Replicate:

cloneofsimo/lora-training has preset hyperparameters for face/object/style, that we’ve found to be optimal for those use cases
cloneofsimo/lora-advanced-training lets you set the hyperparameters yourself if you want full control

Model description

Famous state-of-the-art text2image diffusion model, stable-diffusion, can be used with LoRA to efficiently adapt to set of text, image pairs. This model takes multiple LoRA and generate images from text.

Caveats and recommendations

Use scale with less than 1 if the LoRA has too much effect. 0.5 ~ 0.8 is recommended for objects and less than 0.75 is recommended for styles.
Using multiple LoRAs does not always guarantee the effect you want.
Use Width, height of 512 x 512.