yonatanbenezra / mylora

model: dev
prompt: A clear and sharp photo of Yonatan working on a computer, sitting at a desk in a modern office setting. The background is unblurred, showing an organized workspace with shelves, books, and a coffee mug on the table. The lighting is natural, with soft shadows. The photo is taken from an Android phone perspective, capturing a realistic and detailed composition, with Yonatan focused on his work.
go_fast
lora_scale: 1
megapixels: 1
num_outputs: 1
aspect_ratio: 1:1
output_format: webp
guidance_scale: 3
output_quality: 80
prompt_strength: 0.8
extra_lora_scale: 1
num_inference_steps: 28

{
  "model": "dev",
  "prompt": "A clear and sharp photo of Yonatan working on a computer, sitting at a desk in a modern office setting. The background is unblurred, showing an organized workspace with shelves, books, and a coffee mug on the table. The lighting is natural, with soft shadows. The photo is taken from an Android phone perspective, capturing a realistic and detailed composition, with Yonatan focused on his work.",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}

Install Replicate’s Node.js client library:

npm install replicate

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

const output = await replicate.run(
  "yonatanbenezra/mylora:d45243b657fbb6e9dcfcb76e9030377a144237f6a57bcbed667faae309f9f6c4",
  {
    input: {
      model: "dev",
      prompt: "A clear and sharp photo of Yonatan working on a computer, sitting at a desk in a modern office setting. The background is unblurred, showing an organized workspace with shelves, books, and a coffee mug on the table. The lighting is natural, with soft shadows. The photo is taken from an Android phone perspective, capturing a realistic and detailed composition, with Yonatan focused on his work.",
      go_fast: false,
      lora_scale: 1,
      megapixels: "1",
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "webp",
      guidance_scale: 3,
      output_quality: 80,
      prompt_strength: 0.8,
      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

Import the client:

import replicate

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

output = replicate.run(
    "yonatanbenezra/mylora:d45243b657fbb6e9dcfcb76e9030377a144237f6a57bcbed667faae309f9f6c4",
    input={
        "model": "dev",
        "prompt": "A clear and sharp photo of Yonatan working on a computer, sitting at a desk in a modern office setting. The background is unblurred, showing an organized workspace with shelves, books, and a coffee mug on the table. The lighting is natural, with soft shadows. The photo is taken from an Android phone perspective, capturing a realistic and detailed composition, with Yonatan focused on his work.",
        "go_fast": False,
        "lora_scale": 1,
        "megapixels": "1",
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "webp",
        "guidance_scale": 3,
        "output_quality": 80,
        "prompt_strength": 0.8,
        "extra_lora_scale": 1,
        "num_inference_steps": 28
    }
)

# 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.

Run yonatanbenezra/mylora 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": "yonatanbenezra/mylora:d45243b657fbb6e9dcfcb76e9030377a144237f6a57bcbed667faae309f9f6c4",
    "input": {
      "model": "dev",
      "prompt": "A clear and sharp photo of Yonatan working on a computer, sitting at a desk in a modern office setting. The background is unblurred, showing an organized workspace with shelves, books, and a coffee mug on the table. The lighting is natural, with soft shadows. The photo is taken from an Android phone perspective, capturing a realistic and detailed composition, with Yonatan focused on his work.",
      "go_fast": false,
      "lora_scale": 1,
      "megapixels": "1",
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "webp",
      "guidance_scale": 3,
      "output_quality": 80,
      "prompt_strength": 0.8,
      "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": "2024-12-21T15:54:06.996631Z",
  "created_at": "2024-12-21T15:53:57.351000Z",
  "data_removed": false,
  "error": null,
  "id": "d5wx9dq7cxrmc0ckx7pbxzwf20",
  "input": {
    "model": "dev",
    "prompt": "A clear and sharp photo of Yonatan working on a computer, sitting at a desk in a modern office setting. The background is unblurred, showing an organized workspace with shelves, books, and a coffee mug on the table. The lighting is natural, with soft shadows. The photo is taken from an Android phone perspective, capturing a realistic and detailed composition, with Yonatan focused on his work.",
    "go_fast": false,
    "lora_scale": 1,
    "megapixels": "1",
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "webp",
    "guidance_scale": 3,
    "output_quality": 80,
    "prompt_strength": 0.8,
    "extra_lora_scale": 1,
    "num_inference_steps": 28
  },
  "logs": "2024-12-21 15:53:57.929 | DEBUG    | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys\n2024-12-21 15:53:57.929 | DEBUG    | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted\nApplying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]\nApplying LoRA:  91%|█████████ | 276/304 [00:00<00:00, 2757.74it/s]\nApplying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2689.32it/s]\n2024-12-21 15:53:58.043 | SUCCESS  | fp8.lora_loading:unload_loras:564 - LoRAs unloaded in 0.11s\nfree=29072826122240\nDownloading weights\n2024-12-21T15:53:58Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpg_q94seh/weights url=https://replicate.delivery/xezq/81bfpSzwFwVsbKKZmQMAjpo5uDbooHroXkDHzXmfKVXTLJ9TA/trained_model.tar\n2024-12-21T15:54:00Z | INFO  | [ Complete ] dest=/tmp/tmpg_q94seh/weights size=\"172 MB\" total_elapsed=2.572s url=https://replicate.delivery/xezq/81bfpSzwFwVsbKKZmQMAjpo5uDbooHroXkDHzXmfKVXTLJ9TA/trained_model.tar\nDownloaded weights in 2.60s\n2024-12-21 15:54:00.639 | INFO     | fp8.lora_loading:convert_lora_weights:498 - Loading LoRA weights for /src/weights-cache/09bd7400fcb3b9ea\n2024-12-21 15:54:00.710 | INFO     | fp8.lora_loading:convert_lora_weights:519 - LoRA weights loaded\n2024-12-21 15:54:00.710 | DEBUG    | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys\n2024-12-21 15:54:00.710 | DEBUG    | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted\nApplying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]\nApplying LoRA:  91%|█████████ | 277/304 [00:00<00:00, 2760.25it/s]\nApplying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2694.65it/s]\n2024-12-21 15:54:00.824 | SUCCESS  | fp8.lora_loading:load_lora:539 - LoRA applied in 0.18s\nUsing seed: 16798\n0it [00:00, ?it/s]\n1it [00:00,  8.34it/s]\n2it [00:00,  5.83it/s]\n3it [00:00,  5.31it/s]\n4it [00:00,  5.09it/s]\n5it [00:00,  4.94it/s]\n6it [00:01,  4.85it/s]\n7it [00:01,  4.83it/s]\n8it [00:01,  4.82it/s]\n9it [00:01,  4.81it/s]\n10it [00:02,  4.76it/s]\n11it [00:02,  4.75it/s]\n12it [00:02,  4.76it/s]\n13it [00:02,  4.76it/s]\n14it [00:02,  4.76it/s]\n15it [00:03,  4.74it/s]\n16it [00:03,  4.73it/s]\n17it [00:03,  4.75it/s]\n18it [00:03,  4.76it/s]\n19it [00:03,  4.76it/s]\n20it [00:04,  4.75it/s]\n21it [00:04,  4.73it/s]\n22it [00:04,  4.74it/s]\n23it [00:04,  4.74it/s]\n24it [00:04,  4.74it/s]\n25it [00:05,  4.73it/s]\n26it [00:05,  4.73it/s]\n27it [00:05,  4.73it/s]\n28it [00:05,  4.74it/s]\n28it [00:05,  4.82it/s]\nTotal safe images: 1 out of 1",
  "metrics": {
    "predict_time": 9.066485862,
    "total_time": 9.645631
  },
  "output": [
    "https://replicate.delivery/xezq/TVIl3awJmeWYKSuullcHsNZ2hCmireehTOfyP7zOiru4pl0PB/out-0.webp"
  ],
  "started_at": "2024-12-21T15:53:57.930145Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-xgfxbyvu5gdbhuqe45x7zorkefba5e7p3euqzdnflexuo3ndppba",
    "get": "https://api.replicate.com/v1/predictions/d5wx9dq7cxrmc0ckx7pbxzwf20",
    "cancel": "https://api.replicate.com/v1/predictions/d5wx9dq7cxrmc0ckx7pbxzwf20/cancel"
  },
  "version": "d45243b657fbb6e9dcfcb76e9030377a144237f6a57bcbed667faae309f9f6c4"
}

Generated in

9.1 seconds

Tweak it ShareReport

2024-12-21 15:53:57.929 | DEBUG    | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys
2024-12-21 15:53:57.929 | DEBUG    | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted
Applying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]
Applying LoRA:  91%|█████████ | 276/304 [00:00<00:00, 2757.74it/s]
Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2689.32it/s]
2024-12-21 15:53:58.043 | SUCCESS  | fp8.lora_loading:unload_loras:564 - LoRAs unloaded in 0.11s
free=29072826122240
Downloading weights
2024-12-21T15:53:58Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpg_q94seh/weights url=https://replicate.delivery/xezq/81bfpSzwFwVsbKKZmQMAjpo5uDbooHroXkDHzXmfKVXTLJ9TA/trained_model.tar
2024-12-21T15:54:00Z | INFO  | [ Complete ] dest=/tmp/tmpg_q94seh/weights size="172 MB" total_elapsed=2.572s url=https://replicate.delivery/xezq/81bfpSzwFwVsbKKZmQMAjpo5uDbooHroXkDHzXmfKVXTLJ9TA/trained_model.tar
Downloaded weights in 2.60s
2024-12-21 15:54:00.639 | INFO     | fp8.lora_loading:convert_lora_weights:498 - Loading LoRA weights for /src/weights-cache/09bd7400fcb3b9ea
2024-12-21 15:54:00.710 | INFO     | fp8.lora_loading:convert_lora_weights:519 - LoRA weights loaded
2024-12-21 15:54:00.710 | DEBUG    | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys
2024-12-21 15:54:00.710 | DEBUG    | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted
Applying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]
Applying LoRA:  91%|█████████ | 277/304 [00:00<00:00, 2760.25it/s]
Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2694.65it/s]
2024-12-21 15:54:00.824 | SUCCESS  | fp8.lora_loading:load_lora:539 - LoRA applied in 0.18s
Using seed: 16798
0it [00:00, ?it/s]
1it [00:00,  8.34it/s]
2it [00:00,  5.83it/s]
3it [00:00,  5.31it/s]
4it [00:00,  5.09it/s]
5it [00:00,  4.94it/s]
6it [00:01,  4.85it/s]
7it [00:01,  4.83it/s]
8it [00:01,  4.82it/s]
9it [00:01,  4.81it/s]
10it [00:02,  4.76it/s]
11it [00:02,  4.75it/s]
12it [00:02,  4.76it/s]
13it [00:02,  4.76it/s]
14it [00:02,  4.76it/s]
15it [00:03,  4.74it/s]
16it [00:03,  4.73it/s]
17it [00:03,  4.75it/s]
18it [00:03,  4.76it/s]
19it [00:03,  4.76it/s]
20it [00:04,  4.75it/s]
21it [00:04,  4.73it/s]
22it [00:04,  4.74it/s]
23it [00:04,  4.74it/s]
24it [00:04,  4.74it/s]
25it [00:05,  4.73it/s]
26it [00:05,  4.73it/s]
27it [00:05,  4.73it/s]
28it [00:05,  4.74it/s]
28it [00:05,  4.82it/s]
Total safe images: 1 out of 1

Want to make some of these yourself?

Run this model