cloneofsimo/vintedois_lora – Run with an API on Replicate

cloneofsimo / vintedois_lora

LoRA, fp16 vintedois-diffusion-v0-1

Cold

Public
5.7K runs
T4

Run with an API

Playground API Examples README Versions

Input

prompt

string

Shift + Return to add a new line

close up portrait of <1> in a Sci Fi suit - 4k uhd, hyper detailed, photorealistic, steampunk, lovecraft colors, dan mumford colors, psychedelic black light, epic compositionclose up portrait of <1> in a Sci Fi suit - 4k uhd, hyper detailed, photorealistic, steampunk, lovecraft colors, dan mumford colors, psychedelic black light, epic composition

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

blurry, bad anatomy, blurred, watermark, grainy, signatureblurry, bad anatomy, blurred, watermark, grainy, signature

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/tLNfiG3fK2jZo0CrBG4cNTJNhEi7r117ANUBjWrLTkQRMraQA/tmpg9tq4is5me.safetensorshttps://replicate.delivery/pbxt/tLNfiG3fK2jZo0CrBG4cNTJNhEi7r117ANUBjWrLTkQRMraQA/tmpg9tq4is5me.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/vintedois_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/vintedois_lora using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "cloneofsimo/vintedois_lora:c43a53a23c00fdd1e2f0c403aecdc17296d58cc1dd455ae0fa613a0e5eb8232f",
  {
    input: {
      width: 512,
      height: 512,
      prompt: "close up portrait of <1> in a Sci Fi suit - 4k uhd, hyper detailed, photorealistic, steampunk, lovecraft colors, dan mumford colors, psychedelic black light, epic composition",
      lora_urls: "https://replicate.delivery/pbxt/tLNfiG3fK2jZo0CrBG4cNTJNhEi7r117ANUBjWrLTkQRMraQA/tmpg9tq4is5me.safetensors",
      scheduler: "DPMSolverMultistep",
      lora_scales: "0.5",
      num_outputs: 1,
      adapter_type: "sketch",
      guidance_scale: 7,
      negative_prompt: "blurry, bad anatomy, blurred, watermark, grainy, signature",
      prompt_strength: 0.8,
      num_inference_steps: 30
    }
  }
);

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

output = replicate.run(
    "cloneofsimo/vintedois_lora:c43a53a23c00fdd1e2f0c403aecdc17296d58cc1dd455ae0fa613a0e5eb8232f",
    input={
        "width": 512,
        "height": 512,
        "prompt": "close up portrait of <1> in a Sci Fi suit - 4k uhd, hyper detailed, photorealistic, steampunk, lovecraft colors, dan mumford colors, psychedelic black light, epic composition",
        "lora_urls": "https://replicate.delivery/pbxt/tLNfiG3fK2jZo0CrBG4cNTJNhEi7r117ANUBjWrLTkQRMraQA/tmpg9tq4is5me.safetensors",
        "scheduler": "DPMSolverMultistep",
        "lora_scales": "0.5",
        "num_outputs": 1,
        "adapter_type": "sketch",
        "guidance_scale": 7,
        "negative_prompt": "blurry, bad anatomy, blurred, watermark, grainy, signature",
        "prompt_strength": 0.8,
        "num_inference_steps": 30
    }
)
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/vintedois_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": "c43a53a23c00fdd1e2f0c403aecdc17296d58cc1dd455ae0fa613a0e5eb8232f",
    "input": {
      "width": 512,
      "height": 512,
      "prompt": "close up portrait of <1> in a Sci Fi suit - 4k uhd, hyper detailed, photorealistic, steampunk, lovecraft colors, dan mumford colors, psychedelic black light, epic composition",
      "lora_urls": "https://replicate.delivery/pbxt/tLNfiG3fK2jZo0CrBG4cNTJNhEi7r117ANUBjWrLTkQRMraQA/tmpg9tq4is5me.safetensors",
      "scheduler": "DPMSolverMultistep",
      "lora_scales": "0.5",
      "num_outputs": 1,
      "adapter_type": "sketch",
      "guidance_scale": 7,
      "negative_prompt": "blurry, bad anatomy, blurred, watermark, grainy, signature",
      "prompt_strength": 0.8,
      "num_inference_steps": 30
    }
  }' \
  https://api.replicate.com/v1/predictions

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

You can run this model locally using Cog. First, install Cog:

brew install cog

If you don’t have Homebrew, there are other installation options available.

Run this to download the model and run it in your local environment:

cog predict r8.im/cloneofsimo/vintedois_lora@sha256:c43a53a23c00fdd1e2f0c403aecdc17296d58cc1dd455ae0fa613a0e5eb8232f \
  -i 'width=512' \
  -i 'height=512' \
  -i 'prompt="close up portrait of <1> in a Sci Fi suit - 4k uhd, hyper detailed, photorealistic, steampunk, lovecraft colors, dan mumford colors, psychedelic black light, epic composition"' \
  -i 'lora_urls="https://replicate.delivery/pbxt/tLNfiG3fK2jZo0CrBG4cNTJNhEi7r117ANUBjWrLTkQRMraQA/tmpg9tq4is5me.safetensors"' \
  -i 'scheduler="DPMSolverMultistep"' \
  -i 'lora_scales="0.5"' \
  -i 'num_outputs=1' \
  -i 'adapter_type="sketch"' \
  -i 'guidance_scale=7' \
  -i 'negative_prompt="blurry, bad anatomy, blurred, watermark, grainy, signature"' \
  -i 'prompt_strength=0.8' \
  -i 'num_inference_steps=30'

To learn more, take a look at the Cog documentation.

Run this to download the model and run it in your local environment:

docker run -d -p 5000:5000 --gpus=all r8.im/cloneofsimo/vintedois_lora@sha256:c43a53a23c00fdd1e2f0c403aecdc17296d58cc1dd455ae0fa613a0e5eb8232f
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "width": 512,
      "height": 512,
      "prompt": "close up portrait of <1> in a Sci Fi suit - 4k uhd, hyper detailed, photorealistic, steampunk, lovecraft colors, dan mumford colors, psychedelic black light, epic composition",
      "lora_urls": "https://replicate.delivery/pbxt/tLNfiG3fK2jZo0CrBG4cNTJNhEi7r117ANUBjWrLTkQRMraQA/tmpg9tq4is5me.safetensors",
      "scheduler": "DPMSolverMultistep",
      "lora_scales": "0.5",
      "num_outputs": 1,
      "adapter_type": "sketch",
      "guidance_scale": 7,
      "negative_prompt": "blurry, bad anatomy, blurred, watermark, grainy, signature",
      "prompt_strength": 0.8,
      "num_inference_steps": 30
    }
  }' \
  http://localhost:5000/predictions

To learn more, take a look at the Cog documentation.

Output

{
  "completed_at": "2023-02-09T22:30:30.027937Z",
  "created_at": "2023-02-09T22:30:19.309173Z",
  "data_removed": false,
  "error": null,
  "id": "r7fivxppnnh7jbz47v3jnsgbty",
  "input": {
    "width": 512,
    "height": 512,
    "prompt": "close up portrait of <1> in a Sci Fi suit - 4k uhd, hyper detailed, photorealistic, steampunk, lovecraft colors, dan mumford colors, psychedelic black light, epic composition",
    "lora_urls": "https://replicate.delivery/pbxt/tLNfiG3fK2jZo0CrBG4cNTJNhEi7r117ANUBjWrLTkQRMraQA/tmpg9tq4is5me.safetensors",
    "scheduler": "DPMSolverMultistep",
    "lora_scales": "0.5",
    "num_outputs": 1,
    "guidance_scale": "7",
    "negative_prompt": "blurry, bad anatomy, blurred, watermark, grainy, signature",
    "num_inference_steps": "30"
  },
  "logs": "Using seed: 25844\nUsing disk cache...\nEmbedding <s1> replaced to <s0-0>\nEmbedding <s2> replaced to <s0-1>\n<s0-0>\nThe tokenizer already contains the token <s0-0>.\nReplacing <s0-0> embedding.\n<s0-1>\nThe tokenizer already contains the token <s0-1>.\nReplacing <s0-1> embedding.\nmerging time: 3.018888473510742\n  0%|          | 0/30 [00:00<?, ?it/s]\n  3%|▎         | 1/30 [00:00<00:07,  3.78it/s]\n  7%|▋         | 2/30 [00:00<00:06,  4.26it/s]\n 10%|█         | 3/30 [00:00<00:06,  4.45it/s]\n 13%|█▎        | 4/30 [00:00<00:05,  4.57it/s]\n 17%|█▋        | 5/30 [00:01<00:05,  4.56it/s]\n 20%|██        | 6/30 [00:01<00:05,  4.54it/s]\n 23%|██▎       | 7/30 [00:01<00:05,  4.60it/s]\n 27%|██▋       | 8/30 [00:01<00:04,  4.62it/s]\n 30%|███       | 9/30 [00:01<00:04,  4.67it/s]\n 33%|███▎      | 10/30 [00:02<00:04,  4.63it/s]\n 37%|███▋      | 11/30 [00:02<00:04,  4.59it/s]\n 40%|████      | 12/30 [00:02<00:03,  4.64it/s]\n 43%|████▎     | 13/30 [00:02<00:03,  4.66it/s]\n 47%|████▋     | 14/30 [00:03<00:03,  4.66it/s]\n 50%|█████     | 15/30 [00:03<00:03,  4.64it/s]\n 53%|█████▎    | 16/30 [00:03<00:03,  4.61it/s]\n 57%|█████▋    | 17/30 [00:03<00:02,  4.60it/s]\n 60%|██████    | 18/30 [00:03<00:02,  4.63it/s]\n 63%|██████▎   | 19/30 [00:04<00:02,  4.63it/s]\n 67%|██████▋   | 20/30 [00:04<00:02,  4.63it/s]\n 70%|███████   | 21/30 [00:04<00:01,  4.65it/s]\n 73%|███████▎  | 22/30 [00:04<00:01,  4.62it/s]\n 77%|███████▋  | 23/30 [00:05<00:01,  4.65it/s]\n 80%|████████  | 24/30 [00:05<00:01,  4.65it/s]\n 83%|████████▎ | 25/30 [00:05<00:01,  4.62it/s]\n 87%|████████▋ | 26/30 [00:05<00:00,  4.65it/s]\n 90%|█████████ | 27/30 [00:05<00:00,  4.65it/s]\n 93%|█████████▎| 28/30 [00:06<00:00,  4.64it/s]\n 97%|█████████▋| 29/30 [00:06<00:00,  4.65it/s]\n100%|██████████| 30/30 [00:06<00:00,  4.63it/s]\n100%|██████████| 30/30 [00:06<00:00,  4.60it/s]",
  "metrics": {
    "predict_time": 10.654866,
    "total_time": 10.718764
  },
  "output": [
    "https://replicate.delivery/pbxt/boT740OghXpnJNNSdOIQj05413hp51yzGExlfvOgWN1CMZOIA/out-0.png"
  ],
  "started_at": "2023-02-09T22:30:19.373071Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/r7fivxppnnh7jbz47v3jnsgbty",
    "cancel": "https://api.replicate.com/v1/predictions/r7fivxppnnh7jbz47v3jnsgbty/cancel"
  },
  "version": "2a7199fef2ad2cf1f14056744857604b92a5c3851472d60995d0bc25f12438f2"
}

Generated in

10.7 seconds

Tweak itReport

Using seed: 25844
Using disk cache...
Embedding <s1> replaced to <s0-0>
Embedding <s2> replaced to <s0-1>
<s0-0>
The tokenizer already contains the token <s0-0>.
Replacing <s0-0> embedding.
<s0-1>
The tokenizer already contains the token <s0-1>.
Replacing <s0-1> embedding.
merging time: 3.018888473510742
  0%|          | 0/30 [00:00<?, ?it/s]
  3%|▎         | 1/30 [00:00<00:07,  3.78it/s]
  7%|▋         | 2/30 [00:00<00:06,  4.26it/s]
 10%|█         | 3/30 [00:00<00:06,  4.45it/s]
 13%|█▎        | 4/30 [00:00<00:05,  4.57it/s]
 17%|█▋        | 5/30 [00:01<00:05,  4.56it/s]
 20%|██        | 6/30 [00:01<00:05,  4.54it/s]
 23%|██▎       | 7/30 [00:01<00:05,  4.60it/s]
 27%|██▋       | 8/30 [00:01<00:04,  4.62it/s]
 30%|███       | 9/30 [00:01<00:04,  4.67it/s]
 33%|███▎      | 10/30 [00:02<00:04,  4.63it/s]
 37%|███▋      | 11/30 [00:02<00:04,  4.59it/s]
 40%|████      | 12/30 [00:02<00:03,  4.64it/s]
 43%|████▎     | 13/30 [00:02<00:03,  4.66it/s]
 47%|████▋     | 14/30 [00:03<00:03,  4.66it/s]
 50%|█████     | 15/30 [00:03<00:03,  4.64it/s]
 53%|█████▎    | 16/30 [00:03<00:03,  4.61it/s]
 57%|█████▋    | 17/30 [00:03<00:02,  4.60it/s]
 60%|██████    | 18/30 [00:03<00:02,  4.63it/s]
 63%|██████▎   | 19/30 [00:04<00:02,  4.63it/s]
 67%|██████▋   | 20/30 [00:04<00:02,  4.63it/s]
 70%|███████   | 21/30 [00:04<00:01,  4.65it/s]
 73%|███████▎  | 22/30 [00:04<00:01,  4.62it/s]
 77%|███████▋  | 23/30 [00:05<00:01,  4.65it/s]
 80%|████████  | 24/30 [00:05<00:01,  4.65it/s]
 83%|████████▎ | 25/30 [00:05<00:01,  4.62it/s]
 87%|████████▋ | 26/30 [00:05<00:00,  4.65it/s]
 90%|█████████ | 27/30 [00:05<00:00,  4.65it/s]
 93%|█████████▎| 28/30 [00:06<00:00,  4.64it/s]
 97%|█████████▋| 29/30 [00:06<00:00,  4.65it/s]
100%|██████████| 30/30 [00:06<00:00,  4.63it/s]
100%|██████████| 30/30 [00:06<00:00,  4.60it/s]

This output was created using a different version of the model, cloneofsimo/vintedois_lora:2a7199fe.

Examples

View more examples

Run time and cost

This model costs approximately $0.0026 to run on Replicate, or 384 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 T4 GPU hardware. Predictions typically complete within 12 seconds.

Readme

This is a replicate ported fp16 model of https://huggingface.co/22h/vintedois-diffusion-v0-1 with LoRA capabilities.