ltejedor / cmf

{
  "width": 512,
  "height": 512,
  "prompt": "a chair made of marble, glossy finish, in the style of TOK",
  "refine": "no_refiner",
  "scheduler": "K_EULER",
  "lora_scale": 0.6,
  "num_outputs": 3,
  "guidance_scale": 7.5,
  "apply_watermark": true,
  "high_noise_frac": 0.8,
  "negative_prompt": "",
  "prompt_strength": 0.8,
  "num_inference_steps": 50
}

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

const output = await replicate.run(
  "ltejedor/cmf:3af83ef60d86efbf374edb788fa4183a6067416e2fadafe709350dc1efe37d1d",
  {
    input: {
      width: 512,
      height: 512,
      prompt: "a chair made of marble, glossy finish, in the style of TOK",
      refine: "no_refiner",
      scheduler: "K_EULER",
      lora_scale: 0.6,
      num_outputs: 3,
      guidance_scale: 7.5,
      apply_watermark: true,
      high_noise_frac: 0.8,
      negative_prompt: "",
      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

Import the client:

import replicate

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

output = replicate.run(
    "ltejedor/cmf:3af83ef60d86efbf374edb788fa4183a6067416e2fadafe709350dc1efe37d1d",
    input={
        "width": 512,
        "height": 512,
        "prompt": "a chair made of marble, glossy finish, in the style of TOK",
        "refine": "no_refiner",
        "scheduler": "K_EULER",
        "lora_scale": 0.6,
        "num_outputs": 3,
        "guidance_scale": 7.5,
        "apply_watermark": True,
        "high_noise_frac": 0.8,
        "negative_prompt": "",
        "prompt_strength": 0.8,
        "num_inference_steps": 50
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run ltejedor/cmf 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": "ltejedor/cmf:3af83ef60d86efbf374edb788fa4183a6067416e2fadafe709350dc1efe37d1d",
    "input": {
      "width": 512,
      "height": 512,
      "prompt": "a chair made of marble, glossy finish, in the style of TOK",
      "refine": "no_refiner",
      "scheduler": "K_EULER",
      "lora_scale": 0.6,
      "num_outputs": 3,
      "guidance_scale": 7.5,
      "apply_watermark": true,
      "high_noise_frac": 0.8,
      "negative_prompt": "",
      "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": "2025-03-18T17:27:28.495286Z",
  "created_at": "2025-03-18T17:27:08.465000Z",
  "data_removed": false,
  "error": null,
  "id": "p9pe1pkvp5rm80cnn95sr9p47w",
  "input": {
    "width": 512,
    "height": 512,
    "prompt": "a chair made of marble, glossy finish, in the style of TOK",
    "refine": "no_refiner",
    "scheduler": "K_EULER",
    "lora_scale": 0.6,
    "num_outputs": 3,
    "guidance_scale": 7.5,
    "apply_watermark": true,
    "high_noise_frac": 0.8,
    "negative_prompt": "",
    "prompt_strength": 0.8,
    "num_inference_steps": 50
  },
  "logs": "Using seed: 36202\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: a chair made of marble, glossy finish, in the style of <s0><s1>\ntxt2img mode\n  0%|          | 0/50 [00:00<?, ?it/s]\n  4%|▍         | 2/50 [00:00<00:04, 10.95it/s]\n  8%|▊         | 4/50 [00:00<00:04, 10.81it/s]\n 12%|█▏        | 6/50 [00:00<00:04, 10.75it/s]\n 16%|█▌        | 8/50 [00:00<00:03, 10.75it/s]\n 20%|██        | 10/50 [00:00<00:03, 10.73it/s]\n 24%|██▍       | 12/50 [00:01<00:03, 10.72it/s]\n 28%|██▊       | 14/50 [00:01<00:03, 10.71it/s]\n 32%|███▏      | 16/50 [00:01<00:03, 10.72it/s]\n 36%|███▌      | 18/50 [00:01<00:02, 10.70it/s]\n 40%|████      | 20/50 [00:01<00:02, 10.70it/s]\n 44%|████▍     | 22/50 [00:02<00:02, 10.70it/s]\n 48%|████▊     | 24/50 [00:02<00:02, 10.70it/s]\n 52%|█████▏    | 26/50 [00:02<00:02, 10.69it/s]\n 56%|█████▌    | 28/50 [00:02<00:02, 10.68it/s]\n 60%|██████    | 30/50 [00:02<00:01, 10.70it/s]\n 64%|██████▍   | 32/50 [00:02<00:01, 10.69it/s]\n 68%|██████▊   | 34/50 [00:03<00:01, 10.69it/s]\n 72%|███████▏  | 36/50 [00:03<00:01, 10.70it/s]\n 76%|███████▌  | 38/50 [00:03<00:01, 10.69it/s]\n 80%|████████  | 40/50 [00:03<00:00, 10.68it/s]\n 84%|████████▍ | 42/50 [00:03<00:00, 10.70it/s]\n 88%|████████▊ | 44/50 [00:04<00:00, 10.69it/s]\n 92%|█████████▏| 46/50 [00:04<00:00, 10.67it/s]\n 96%|█████████▌| 48/50 [00:04<00:00, 10.64it/s]\n100%|██████████| 50/50 [00:04<00:00, 10.64it/s]\n100%|██████████| 50/50 [00:04<00:00, 10.69it/s]",
  "metrics": {
    "predict_time": 7.241624247,
    "total_time": 20.030286
  },
  "output": [
    "https://replicate.delivery/xezq/jH2qfoGbHj3kJKhwPdyI9CxK37dQfg8ZngO1r9LiwPjA81ZUA/out-0.png",
    "https://replicate.delivery/xezq/UMut0LQBbi48CdJXOWepIlfSDe6OPvus25YPIVKxyhZB4rzoA/out-1.png",
    "https://replicate.delivery/xezq/m5zk3UIvYJpjHBNtzoYzwlPOVRRwgFsLCYjTJCVklMGAf6MKA/out-2.png"
  ],
  "started_at": "2025-03-18T17:27:21.253662Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-lj2bcw7ibsrnaclbhdulep34m54ptim4yjrd36st6cybtcoeucla",
    "get": "https://api.replicate.com/v1/predictions/p9pe1pkvp5rm80cnn95sr9p47w",
    "cancel": "https://api.replicate.com/v1/predictions/p9pe1pkvp5rm80cnn95sr9p47w/cancel"
  },
  "version": "3af83ef60d86efbf374edb788fa4183a6067416e2fadafe709350dc1efe37d1d"
}

Generated in

7.3 seconds

Tweak it ShareReport

Want to make some of these yourself?

Run this model