@fermatresearch's fermatresearch/sdxl-improved-refiner

Model

fermatresearch/sdxl-improved-refiner:58534db9

d5uroutbzbbvo44gmehlqzalay

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

2m 45s

Created

almost 2 years ago

Webhook

–

Input

prompt: An astronaut riding a rainbow unicorn, cinematic, dramatic
negative_prompt: Empty string
width: 768
height: 768
num_outputs: 1
scheduler: K_EULER
num_inference_steps: 25
guidance_scale: 7.5
prompt_strength: 0.8
seed: 16010
refine: expert_ensemble_refiner
high_noise_frac: 0.8
tile_refine: true
tile_refine_strength: 0.5
tile_refine_conditioning_strength: 0.5
tile_refine_steps: 20
apply_watermark: true
lora_scale: 0.6

{
  "apply_watermark": true,
  "guidance_scale": 7.5,
  "height": 768,
  "high_noise_frac": 0.8,
  "lora_scale": 0.6,
  "negative_prompt": "",
  "num_inference_steps": 25,
  "num_outputs": 1,
  "prompt": "An astronaut riding a rainbow unicorn, cinematic, dramatic",
  "prompt_strength": 0.8,
  "refine": "expert_ensemble_refiner",
  "scheduler": "K_EULER",
  "seed": 16010,
  "tile_refine": true,
  "tile_refine_conditioning_strength": 0.5,
  "tile_refine_steps": 20,
  "tile_refine_strength": 0.5,
  "width": 768
}

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=r8_aUP**********************************

This is your API token. Keep it to yourself.

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 fermatresearch/sdxl-improved-refiner using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "fermatresearch/sdxl-improved-refiner:58534db966a6866fa7e699482ebf8b508a8c39e197bb8ed7ce2d9b1e1cc6527e",
  {
    input: {
      apply_watermark: true,
      guidance_scale: 7.5,
      height: 768,
      high_noise_frac: 0.8,
      lora_scale: 0.6,
      negative_prompt: "",
      num_inference_steps: 25,
      num_outputs: 1,
      prompt: "An astronaut riding a rainbow unicorn, cinematic, dramatic",
      prompt_strength: 0.8,
      refine: "expert_ensemble_refiner",
      scheduler: "K_EULER",
      seed: 16010,
      tile_refine: true,
      tile_refine_conditioning_strength: 0.5,
      tile_refine_steps: 20,
      tile_refine_strength: 0.5,
      width: 768
    }
  }
);

// 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=r8_aUP**********************************

This is your API token. Keep it to yourself.

Import the client:

import replicate

Run fermatresearch/sdxl-improved-refiner using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "fermatresearch/sdxl-improved-refiner:58534db966a6866fa7e699482ebf8b508a8c39e197bb8ed7ce2d9b1e1cc6527e",
    input={
        "apply_watermark": True,
        "guidance_scale": 7.5,
        "height": 768,
        "high_noise_frac": 0.8,
        "lora_scale": 0.6,
        "negative_prompt": "",
        "num_inference_steps": 25,
        "num_outputs": 1,
        "prompt": "An astronaut riding a rainbow unicorn, cinematic, dramatic",
        "prompt_strength": 0.8,
        "refine": "expert_ensemble_refiner",
        "scheduler": "K_EULER",
        "seed": 16010,
        "tile_refine": True,
        "tile_refine_conditioning_strength": 0.5,
        "tile_refine_steps": 20,
        "tile_refine_strength": 0.5,
        "width": 768
    }
)

# 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.

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=r8_aUP**********************************

This is your API token. Keep it to yourself.

Run fermatresearch/sdxl-improved-refiner 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": "fermatresearch/sdxl-improved-refiner:58534db966a6866fa7e699482ebf8b508a8c39e197bb8ed7ce2d9b1e1cc6527e",
    "input": {
      "apply_watermark": true,
      "guidance_scale": 7.5,
      "height": 768,
      "high_noise_frac": 0.8,
      "lora_scale": 0.6,
      "negative_prompt": "",
      "num_inference_steps": 25,
      "num_outputs": 1,
      "prompt": "An astronaut riding a rainbow unicorn, cinematic, dramatic",
      "prompt_strength": 0.8,
      "refine": "expert_ensemble_refiner",
      "scheduler": "K_EULER",
      "seed": 16010,
      "tile_refine": true,
      "tile_refine_conditioning_strength": 0.5,
      "tile_refine_steps": 20,
      "tile_refine_strength": 0.5,
      "width": 768
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "id": "d5uroutbzbbvo44gmehlqzalay",
  "model": "fermatresearch/sdxl-improved-refiner",
  "version": "58534db966a6866fa7e699482ebf8b508a8c39e197bb8ed7ce2d9b1e1cc6527e",
  "input": {
    "apply_watermark": true,
    "guidance_scale": 7.5,
    "height": 768,
    "high_noise_frac": 0.8,
    "lora_scale": 0.6,
    "negative_prompt": "",
    "num_inference_steps": 25,
    "num_outputs": 1,
    "prompt": "An astronaut riding a rainbow unicorn, cinematic, dramatic",
    "prompt_strength": 0.8,
    "refine": "expert_ensemble_refiner",
    "scheduler": "K_EULER",
    "seed": 16010,
    "tile_refine": true,
    "tile_refine_conditioning_strength": 0.5,
    "tile_refine_steps": 20,
    "tile_refine_strength": 0.5,
    "width": 768
  },
  "logs": "Using seed: 16010\nPrompt: An astronaut riding a rainbow unicorn, cinematic, dramatic\ntxt2img mode\n  0%|          | 0/20 [00:00<?, ?it/s]\n  5%|▌         | 1/20 [00:00<00:05,  3.59it/s]\n 10%|█         | 2/20 [00:00<00:03,  5.40it/s]\n 15%|█▌        | 3/20 [00:00<00:02,  6.43it/s]\n 20%|██        | 4/20 [00:00<00:02,  7.05it/s]\n 25%|██▌       | 5/20 [00:00<00:02,  7.44it/s]\n 30%|███       | 6/20 [00:00<00:01,  7.69it/s]\n 35%|███▌      | 7/20 [00:01<00:01,  7.86it/s]\n 40%|████      | 8/20 [00:01<00:01,  7.97it/s]\n 45%|████▌     | 9/20 [00:01<00:01,  8.05it/s]\n 50%|█████     | 10/20 [00:01<00:01,  8.11it/s]\n 55%|█████▌    | 11/20 [00:01<00:01,  8.16it/s]\n 60%|██████    | 12/20 [00:01<00:00,  8.20it/s]\n 65%|██████▌   | 13/20 [00:01<00:00,  8.22it/s]\n 70%|███████   | 14/20 [00:01<00:00,  8.24it/s]\n 75%|███████▌  | 15/20 [00:01<00:00,  8.25it/s]\n 80%|████████  | 16/20 [00:02<00:00,  8.25it/s]\n 85%|████████▌ | 17/20 [00:02<00:00,  8.26it/s]\n 90%|█████████ | 18/20 [00:02<00:00,  8.26it/s]\n 95%|█████████▌| 19/20 [00:02<00:00,  8.26it/s]\n100%|██████████| 20/20 [00:02<00:00,  8.27it/s]\n100%|██████████| 20/20 [00:02<00:00,  7.76it/s]\n  0%|          | 0/5 [00:00<?, ?it/s]\n 20%|██        | 1/5 [00:00<00:00,  7.31it/s]\n 40%|████      | 2/5 [00:00<00:00,  7.66it/s]\n 60%|██████    | 3/5 [00:00<00:00,  7.78it/s]\n 80%|████████  | 4/5 [00:00<00:00,  7.83it/s]\n100%|██████████| 5/5 [00:00<00:00,  7.87it/s]\n100%|██████████| 5/5 [00:00<00:00,  7.79it/s]\n  0%|          | 0/10 [00:00<?, ?it/s]\n 10%|█         | 1/10 [00:00<00:01,  5.82it/s]\n 30%|███       | 3/10 [00:00<00:00,  8.12it/s]\n 40%|████      | 4/10 [00:00<00:00,  7.73it/s]\n 50%|█████     | 5/10 [00:00<00:00,  7.49it/s]\n 60%|██████    | 6/10 [00:00<00:00,  7.35it/s]\n 70%|███████   | 7/10 [00:00<00:00,  7.25it/s]\n 80%|████████  | 8/10 [00:01<00:00,  7.18it/s]\n 90%|█████████ | 9/10 [00:01<00:00,  7.14it/s]\n100%|██████████| 10/10 [00:01<00:00,  7.12it/s]\n100%|██████████| 10/10 [00:01<00:00,  7.27it/s]",
  "output": [
    "https://replicate.delivery/pbxt/uVlVR57RGYrNIJRQZ1NwDEs8xhoEQfLhxnkJO0bkddJdHjGJA/out-0.png"
  ],
  "data_removed": false,
  "error": null,
  "source": "web",
  "status": "succeeded",
  "created_at": "2024-01-16T16:38:46.808996Z",
  "started_at": "2024-01-16T16:41:24.224533Z",
  "completed_at": "2024-01-16T16:41:31.780825Z",
  "urls": {
    "cancel": "https://api.replicate.com/v1/predictions/d5uroutbzbbvo44gmehlqzalay/cancel",
    "get": "https://api.replicate.com/v1/predictions/d5uroutbzbbvo44gmehlqzalay"
  },
  "metrics": {
    "predict_time": 7.556292,
    "total_time": 164.971829
  }
}

Generated in

7.6 seconds

Tweak it Report

Using seed: 16010 Prompt: An astronaut riding a rainbow unicorn, cinematic, dramatic txt2img mode 0%| | 0/20 [00:00<?, ?it/s] 5%|▌ | 1/20 [00:00<00:05, 3.59it/s] 10%|█ | 2/20 [00:00<00:03, 5.40it/s] 15%|█▌ | 3/20 [00:00<00:02, 6.43it/s] 20%|██ | 4/20 [00:00<00:02, 7.05it/s] 25%|██▌ | 5/20 [00:00<00:02, 7.44it/s] 30%|███ | 6/20 [00:00<00:01, 7.69it/s] 35%|███▌ | 7/20 [00:01<00:01, 7.86it/s] 40%|████ | 8/20 [00:01<00:01, 7.97it/s] 45%|████▌ | 9/20 [00:01<00:01, 8.05it/s] 50%|█████ | 10/20 [00:01<00:01, 8.11it/s] 55%|█████▌ | 11/20 [00:01<00:01, 8.16it/s] 60%|██████ | 12/20 [00:01<00:00, 8.20it/s] 65%|██████▌ | 13/20 [00:01<00:00, 8.22it/s] 70%|███████ | 14/20 [00:01<00:00, 8.24it/s] 75%|███████▌ | 15/20 [00:01<00:00, 8.25it/s] 80%|████████ | 16/20 [00:02<00:00, 8.25it/s] 85%|████████▌ | 17/20 [00:02<00:00, 8.26it/s] 90%|█████████ | 18/20 [00:02<00:00, 8.26it/s] 95%|█████████▌| 19/20 [00:02<00:00, 8.26it/s] 100%|██████████| 20/20 [00:02<00:00, 8.27it/s] 100%|██████████| 20/20 [00:02<00:00, 7.76it/s] 0%| | 0/5 [00:00<?, ?it/s] 20%|██ | 1/5 [00:00<00:00, 7.31it/s] 40%|████ | 2/5 [00:00<00:00, 7.66it/s] 60%|██████ | 3/5 [00:00<00:00, 7.78it/s] 80%|████████ | 4/5 [00:00<00:00, 7.83it/s] 100%|██████████| 5/5 [00:00<00:00, 7.87it/s] 100%|██████████| 5/5 [00:00<00:00, 7.79it/s] 0%| | 0/10 [00:00<?, ?it/s] 10%|█ | 1/10 [00:00<00:01, 5.82it/s] 30%|███ | 3/10 [00:00<00:00, 8.12it/s] 40%|████ | 4/10 [00:00<00:00, 7.73it/s] 50%|█████ | 5/10 [00:00<00:00, 7.49it/s] 60%|██████ | 6/10 [00:00<00:00, 7.35it/s] 70%|███████ | 7/10 [00:00<00:00, 7.25it/s] 80%|████████ | 8/10 [00:01<00:00, 7.18it/s] 90%|█████████ | 9/10 [00:01<00:00, 7.14it/s] 100%|██████████| 10/10 [00:01<00:00, 7.12it/s] 100%|██████████| 10/10 [00:01<00:00, 7.27it/s]