lucataco/stable-diffusion-3.5-large-lora:ad0f061a

Version

You're looking at a specific version of this model. Jump to the model overview.

lucataco /stable-diffusion-3.5-large-lora:ad0f061a

Playground API

Input

prompt

string

Shift + Return to add a new line

Input prompt

Default: ""

aspect_ratio

string

Aspect ratio for the generated image

Default: "1:1"

guidance_scale

number

(minimum: 0, maximum: 20)

Scale for classifier-free guidance

Default: 4.5

image

file

Input image for img2img mode

prompt_strength

number

(minimum: 0, maximum: 1)

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

Default: 0.7

num_inference_steps

integer

(minimum: 1, maximum: 50)

Number of denoising steps. Recommended range is 28-50

Default: 28

seed

integer

Random seed. Leave blank to randomize the seed

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

hf_lora

string

Shift + Return to add a new line

https://huggingface.co/lucataco/SD3.5-Large-yarn-2/resolve/main/pytorch_lora_weights.safetensorshttps://huggingface.co/lucataco/SD3.5-Large-yarn-2/resolve/main/pytorch_lora_weights.safetensors

Full URL to Huggingface LoRA, CivitAI URL, or URL to a .safetensors file

lora_scale

number

(minimum: 0, maximum: 1)

Scale for the LoRA weights

Default: 0.8

disable_safety_checker

boolean

Disable safety checker for generated images. This feature is only available through the API. See [https://replicate.com/docs/how-does-replicate-work#safety](https://replicate.com/docs/how-does-replicate-work#safety)

Default: false

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

npx create-replicate --model=lucataco/stable-diffusion-3.5-large-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";
import fs from "node:fs";

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

Run lucataco/stable-diffusion-3.5-large-lora using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "lucataco/stable-diffusion-3.5-large-lora:ad0f061aaf2813ff8dbdba3613a952fca0bf443ef0ddd3ef500d66046ce97c23",
  {
    input: {
      prompt: "Frog, yarn art style",
      hf_lora: "https://huggingface.co/lucataco/SD3.5-Large-yarn-2/resolve/main/pytorch_lora_weights.safetensors",
      lora_scale: 1,
      aspect_ratio: "1:1",
      output_format: "webp",
      guidance_scale: 4.5,
      output_quality: 80,
      prompt_strength: 0.7,
      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 lucataco/stable-diffusion-3.5-large-lora using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "lucataco/stable-diffusion-3.5-large-lora:ad0f061aaf2813ff8dbdba3613a952fca0bf443ef0ddd3ef500d66046ce97c23",
    input={
        "prompt": "Frog, yarn art style",
        "hf_lora": "https://huggingface.co/lucataco/SD3.5-Large-yarn-2/resolve/main/pytorch_lora_weights.safetensors",
        "lora_scale": 1,
        "aspect_ratio": "1:1",
        "output_format": "webp",
        "guidance_scale": 4.5,
        "output_quality": 80,
        "prompt_strength": 0.7,
        "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 lucataco/stable-diffusion-3.5-large-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": "lucataco/stable-diffusion-3.5-large-lora:ad0f061aaf2813ff8dbdba3613a952fca0bf443ef0ddd3ef500d66046ce97c23",
    "input": {
      "prompt": "Frog, yarn art style",
      "hf_lora": "https://huggingface.co/lucataco/SD3.5-Large-yarn-2/resolve/main/pytorch_lora_weights.safetensors",
      "lora_scale": 1,
      "aspect_ratio": "1:1",
      "output_format": "webp",
      "guidance_scale": 4.5,
      "output_quality": 80,
      "prompt_strength": 0.7,
      "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": "2024-11-01T19:42:00.762609Z",
  "created_at": "2024-11-01T19:41:46.730000Z",
  "data_removed": false,
  "error": null,
  "id": "arhvz2w3d9rj00cjx4zvv42b78",
  "input": {
    "prompt": "Frog, yarn art style",
    "hf_lora": "https://huggingface.co/lucataco/SD3.5-Large-yarn-2/resolve/main/pytorch_lora_weights.safetensors",
    "lora_scale": 1,
    "aspect_ratio": "1:1",
    "output_format": "webp",
    "guidance_scale": 4.5,
    "output_quality": 80,
    "prompt_strength": 0.7,
    "num_inference_steps": 28
  },
  "logs": "Using seed: 52957\nPrompt: Frog, yarn art style\ntxt2img mode\nLoading LoRA took: 0.00 seconds\n  0%|          | 0/28 [00:00<?, ?it/s]\n  4%|▎         | 1/28 [00:00<00:13,  2.08it/s]\n  7%|▋         | 2/28 [00:00<00:10,  2.44it/s]\n 11%|█         | 3/28 [00:01<00:11,  2.26it/s]\n 14%|█▍        | 4/28 [00:01<00:11,  2.18it/s]\n 18%|█▊        | 5/28 [00:02<00:10,  2.14it/s]\n 21%|██▏       | 6/28 [00:02<00:10,  2.11it/s]\n 25%|██▌       | 7/28 [00:03<00:10,  2.10it/s]\n 29%|██▊       | 8/28 [00:03<00:09,  2.09it/s]\n 32%|███▏      | 9/28 [00:04<00:09,  2.08it/s]\n 36%|███▌      | 10/28 [00:04<00:08,  2.08it/s]\n 39%|███▉      | 11/28 [00:05<00:08,  2.07it/s]\n 43%|████▎     | 12/28 [00:05<00:07,  2.07it/s]\n 46%|████▋     | 13/28 [00:06<00:07,  2.07it/s]\n 50%|█████     | 14/28 [00:06<00:06,  2.07it/s]\n 54%|█████▎    | 15/28 [00:07<00:06,  2.07it/s]\n 57%|█████▋    | 16/28 [00:07<00:05,  2.07it/s]\n 61%|██████    | 17/28 [00:08<00:05,  2.06it/s]\n 64%|██████▍   | 18/28 [00:08<00:04,  2.06it/s]\n 68%|██████▊   | 19/28 [00:09<00:04,  2.06it/s]\n 71%|███████▏  | 20/28 [00:09<00:03,  2.06it/s]\n 75%|███████▌  | 21/28 [00:10<00:03,  2.06it/s]\n 79%|███████▊  | 22/28 [00:10<00:02,  2.06it/s]\n 82%|████████▏ | 23/28 [00:11<00:02,  2.06it/s]\n 86%|████████▌ | 24/28 [00:11<00:01,  2.06it/s]\n 89%|████████▉ | 25/28 [00:11<00:01,  2.06it/s]\n 93%|█████████▎| 26/28 [00:12<00:00,  2.06it/s]\n 96%|█████████▋| 27/28 [00:12<00:00,  2.06it/s]\n100%|██████████| 28/28 [00:13<00:00,  2.06it/s]\n100%|██████████| 28/28 [00:13<00:00,  2.08it/s]",
  "metrics": {
    "predict_time": 14.022834929,
    "total_time": 14.032609
  },
  "output": [
    "https://replicate.delivery/yhqm/WKTZ1ZnQRYZ4H9nYCfNwL34ZfGeTLkg7iBemxmIAeoXDhwldC/out-0.webp"
  ],
  "started_at": "2024-11-01T19:41:46.739774Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/qoxq-forjqxshlyxo5w4dt65casntzgirel5pym6b5kl3vasfgbanbh3q",
    "get": "https://api.replicate.com/v1/predictions/arhvz2w3d9rj00cjx4zvv42b78",
    "cancel": "https://api.replicate.com/v1/predictions/arhvz2w3d9rj00cjx4zvv42b78/cancel"
  },
  "version": "ad0f061aaf2813ff8dbdba3613a952fca0bf443ef0ddd3ef500d66046ce97c23"
}

Generated in

14.0 seconds

Tweak it ShareReport View full prediction