Prediction

Model

faraz2023/andreas-feininger2:c281f81e

gokuok3bcjagn6us2r2vf4452y

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

2m 18s

Created

about 2 years ago

Webhook

–

Input

prompt: In style of andreas feininger, a large blooming red rose in the middle of gloomy city. The flower is one connected plant.
negative_prompt: disconnected iterm; ugly; low-quality
image: null
width: 2048
height: 2048
num_outputs: 1
scheduler: K_EULER
num_inference_steps: 114
guidance_scale: 9.47
prompt_strength: 0.8
seed: 340234
refine: expert_ensemble_refiner
high_noise_frac: 0.77
refine_steps: null
apply_watermark: false
lora_scale: 0.6

{
  "apply_watermark": false,
  "guidance_scale": 9.47,
  "height": 2048,
  "high_noise_frac": 0.77,
  "image": null,
  "lora_scale": 0.6,
  "negative_prompt": "disconnected iterm; ugly; low-quality",
  "num_inference_steps": 114,
  "num_outputs": 1,
  "prompt": "In style of andreas feininger, a large blooming red rose in the middle of gloomy city. The flower is one connected plant. \n",
  "prompt_strength": 0.8,
  "refine": "expert_ensemble_refiner",
  "refine_steps": null,
  "scheduler": "K_EULER",
  "seed": 340234,
  "width": 2048
}

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=r8_Bf0**********************************

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 faraz2023/andreas-feininger2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "faraz2023/andreas-feininger2:c281f81e1840b5f84f30dcfd471a9df88855fe86d66a606ce6917963e6cd6bd4",
  {
    input: {
      apply_watermark: false,
      guidance_scale: 9.47,
      height: 2048,
      high_noise_frac: 0.77,
      lora_scale: 0.6,
      negative_prompt: "disconnected iterm; ugly; low-quality",
      num_inference_steps: 114,
      num_outputs: 1,
      prompt: "In style of andreas feininger, a large blooming red rose in the middle of gloomy city. The flower is one connected plant. \n",
      prompt_strength: 0.8,
      refine: "expert_ensemble_refiner",
      scheduler: "K_EULER",
      seed: 340234,
      width: 2048
    }
  }
);

// 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_Bf0**********************************

This is your API token. Keep it to yourself.

Import the client:

import replicate

Run faraz2023/andreas-feininger2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "faraz2023/andreas-feininger2:c281f81e1840b5f84f30dcfd471a9df88855fe86d66a606ce6917963e6cd6bd4",
    input={
        "apply_watermark": False,
        "guidance_scale": 9.47,
        "height": 2048,
        "high_noise_frac": 0.77,
        "lora_scale": 0.6,
        "negative_prompt": "disconnected iterm; ugly; low-quality",
        "num_inference_steps": 114,
        "num_outputs": 1,
        "prompt": "In style of andreas feininger, a large blooming red rose in the middle of gloomy city. The flower is one connected plant. \n",
        "prompt_strength": 0.8,
        "refine": "expert_ensemble_refiner",
        "scheduler": "K_EULER",
        "seed": 340234,
        "width": 2048
    }
)

# 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_Bf0**********************************

This is your API token. Keep it to yourself.

Run faraz2023/andreas-feininger2 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": "faraz2023/andreas-feininger2:c281f81e1840b5f84f30dcfd471a9df88855fe86d66a606ce6917963e6cd6bd4",
    "input": {
      "apply_watermark": false,
      "guidance_scale": 9.47,
      "height": 2048,
      "high_noise_frac": 0.77,
      "lora_scale": 0.6,
      "negative_prompt": "disconnected iterm; ugly; low-quality",
      "num_inference_steps": 114,
      "num_outputs": 1,
      "prompt": "In style of andreas feininger, a large blooming red rose in the middle of gloomy city. The flower is one connected plant. \\n",
      "prompt_strength": 0.8,
      "refine": "expert_ensemble_refiner",
      "scheduler": "K_EULER",
      "seed": 340234,
      "width": 2048
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "id": "gokuok3bcjagn6us2r2vf4452y",
  "model": "faraz2023/andreas-feininger2",
  "version": "c281f81e1840b5f84f30dcfd471a9df88855fe86d66a606ce6917963e6cd6bd4",
  "input": {
    "apply_watermark": false,
    "guidance_scale": 9.47,
    "height": 2048,
    "high_noise_frac": 0.77,
    "image": null,
    "lora_scale": 0.6,
    "negative_prompt": "disconnected iterm; ugly; low-quality",
    "num_inference_steps": 114,
    "num_outputs": 1,
    "prompt": "In style of andreas feininger, a large blooming red rose in the middle of gloomy city. The flower is one connected plant. \n",
    "prompt_strength": 0.8,
    "refine": "expert_ensemble_refiner",
    "refine_steps": null,
    "scheduler": "K_EULER",
    "seed": 340234,
    "width": 2048
  },
  "logs": "Using seed: 340234\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: In style of andreas feininger, a large blooming red rose in the middle of gloomy city. The flower is one connected plant.\ntxt2img mode\n  0%|          | 0/66 [00:00<?, ?it/s]\n  2%|▏         | 1/66 [00:01<01:29,  1.38s/it]\n  3%|▎         | 2/66 [00:02<01:28,  1.38s/it]\n  5%|▍         | 3/66 [00:04<01:27,  1.38s/it]\n  6%|▌         | 4/66 [00:05<01:25,  1.38s/it]\n  8%|▊         | 5/66 [00:06<01:24,  1.39s/it]\n  9%|▉         | 6/66 [00:08<01:23,  1.39s/it]\n 11%|█         | 7/66 [00:09<01:21,  1.39s/it]\n 12%|█▏        | 8/66 [00:11<01:20,  1.39s/it]\n 14%|█▎        | 9/66 [00:12<01:18,  1.38s/it]\n 15%|█▌        | 10/66 [00:13<01:17,  1.38s/it]\n 17%|█▋        | 11/66 [00:15<01:16,  1.39s/it]\n 18%|█▊        | 12/66 [00:16<01:14,  1.38s/it]\n 20%|█▉        | 13/66 [00:18<01:13,  1.39s/it]\n 21%|██        | 14/66 [00:19<01:12,  1.39s/it]\n 23%|██▎       | 15/66 [00:20<01:10,  1.39s/it]\n 24%|██▍       | 16/66 [00:22<01:09,  1.39s/it]\n 26%|██▌       | 17/66 [00:23<01:08,  1.39s/it]\n 27%|██▋       | 18/66 [00:24<01:06,  1.39s/it]\n 29%|██▉       | 19/66 [00:26<01:05,  1.39s/it]\n 30%|███       | 20/66 [00:27<01:03,  1.39s/it]\n 32%|███▏      | 21/66 [00:29<01:02,  1.39s/it]\n 33%|███▎      | 22/66 [00:30<01:01,  1.39s/it]\n 35%|███▍      | 23/66 [00:31<00:59,  1.39s/it]\n 36%|███▋      | 24/66 [00:33<00:58,  1.39s/it]\n 38%|███▊      | 25/66 [00:34<00:56,  1.39s/it]\n 39%|███▉      | 26/66 [00:36<00:55,  1.39s/it]\n 41%|████      | 27/66 [00:37<00:54,  1.39s/it]\n 42%|████▏     | 28/66 [00:38<00:52,  1.39s/it]\n 44%|████▍     | 29/66 [00:40<00:51,  1.39s/it]\n 45%|████▌     | 30/66 [00:41<00:50,  1.39s/it]\n 47%|████▋     | 31/66 [00:43<00:48,  1.39s/it]\n 48%|████▊     | 32/66 [00:44<00:47,  1.39s/it]\n 50%|█████     | 33/66 [00:45<00:45,  1.39s/it]\n 52%|█████▏    | 34/66 [00:47<00:44,  1.39s/it]\n 53%|█████▎    | 35/66 [00:48<00:43,  1.39s/it]\n 55%|█████▍    | 36/66 [00:49<00:41,  1.39s/it]\n 56%|█████▌    | 37/66 [00:51<00:40,  1.39s/it]\n 58%|█████▊    | 38/66 [00:52<00:38,  1.39s/it]\n 59%|█████▉    | 39/66 [00:54<00:37,  1.39s/it]\n 61%|██████    | 40/66 [00:55<00:36,  1.39s/it]\n 62%|██████▏   | 41/66 [00:56<00:34,  1.39s/it]\n 64%|██████▎   | 42/66 [00:58<00:33,  1.39s/it]\n 65%|██████▌   | 43/66 [00:59<00:32,  1.39s/it]\n 67%|██████▋   | 44/66 [01:01<00:30,  1.39s/it]\n 68%|██████▊   | 45/66 [01:02<00:29,  1.39s/it]\n 70%|██████▉   | 46/66 [01:03<00:27,  1.39s/it]\n 71%|███████   | 47/66 [01:05<00:26,  1.39s/it]\n 73%|███████▎  | 48/66 [01:06<00:25,  1.39s/it]\n 74%|███████▍  | 49/66 [01:08<00:23,  1.39s/it]\n 76%|███████▌  | 50/66 [01:09<00:22,  1.39s/it]\n 77%|███████▋  | 51/66 [01:10<00:20,  1.39s/it]\n 79%|███████▉  | 52/66 [01:12<00:19,  1.39s/it]\n 80%|████████  | 53/66 [01:13<00:18,  1.39s/it]\n 82%|████████▏ | 54/66 [01:15<00:16,  1.39s/it]\n 83%|████████▎ | 55/66 [01:16<00:15,  1.39s/it]\n 85%|████████▍ | 56/66 [01:17<00:13,  1.39s/it]\n 86%|████████▋ | 57/66 [01:19<00:12,  1.39s/it]\n 88%|████████▊ | 58/66 [01:20<00:11,  1.40s/it]\n 89%|████████▉ | 59/66 [01:22<00:09,  1.39s/it]\n 91%|█████████ | 60/66 [01:23<00:08,  1.40s/it]\n 92%|█████████▏| 61/66 [01:24<00:06,  1.39s/it]\n 94%|█████████▍| 62/66 [01:26<00:05,  1.40s/it]\n 95%|█████████▌| 63/66 [01:27<00:04,  1.39s/it]\n 97%|█████████▋| 64/66 [01:29<00:02,  1.39s/it]\n 98%|█████████▊| 65/66 [01:30<00:01,  1.39s/it]\n100%|██████████| 66/66 [01:31<00:00,  1.40s/it]\n100%|██████████| 66/66 [01:31<00:00,  1.39s/it]\n  0%|          | 0/29 [00:00<?, ?it/s]\n  3%|▎         | 1/29 [00:01<00:39,  1.41s/it]\n  7%|▋         | 2/29 [00:02<00:38,  1.42s/it]\n 10%|█         | 3/29 [00:04<00:36,  1.42s/it]\n 14%|█▍        | 4/29 [00:05<00:35,  1.41s/it]\n 17%|█▋        | 5/29 [00:07<00:33,  1.42s/it]\n 21%|██        | 6/29 [00:08<00:32,  1.42s/it]\n 24%|██▍       | 7/29 [00:09<00:31,  1.41s/it]\n 28%|██▊       | 8/29 [00:11<00:29,  1.41s/it]\n 31%|███       | 9/29 [00:12<00:28,  1.41s/it]\n 34%|███▍      | 10/29 [00:14<00:26,  1.41s/it]\n 38%|███▊      | 11/29 [00:15<00:25,  1.41s/it]\n 41%|████▏     | 12/29 [00:16<00:24,  1.41s/it]\n 45%|████▍     | 13/29 [00:18<00:22,  1.41s/it]\n 48%|████▊     | 14/29 [00:19<00:21,  1.41s/it]\n 52%|█████▏    | 15/29 [00:21<00:19,  1.42s/it]\n 55%|█████▌    | 16/29 [00:22<00:18,  1.42s/it]\n 59%|█████▊    | 17/29 [00:24<00:17,  1.42s/it]\n 62%|██████▏   | 18/29 [00:25<00:15,  1.42s/it]\n 66%|██████▌   | 19/29 [00:26<00:14,  1.42s/it]\n 69%|██████▉   | 20/29 [00:28<00:12,  1.42s/it]\n 72%|███████▏  | 21/29 [00:29<00:11,  1.42s/it]\n 76%|███████▌  | 22/29 [00:31<00:09,  1.42s/it]\n 79%|███████▉  | 23/29 [00:32<00:08,  1.42s/it]\n 83%|████████▎ | 24/29 [00:33<00:07,  1.42s/it]\n 86%|████████▌ | 25/29 [00:35<00:05,  1.42s/it]\n 90%|████████▉ | 26/29 [00:36<00:04,  1.42s/it]\n 93%|█████████▎| 27/29 [00:38<00:02,  1.42s/it]\n 97%|█████████▋| 28/29 [00:39<00:01,  1.42s/it]\n100%|██████████| 29/29 [00:41<00:00,  1.42s/it]\n100%|██████████| 29/29 [00:41<00:00,  1.42s/it]",
  "output": [
    "https://pbxt.replicate.delivery/dOOeuOKt0kVwUiaEPNcxu0dRJV4gJOxJv2JS08mpoKofm3sRA/out-0.png"
  ],
  "data_removed": false,
  "error": null,
  "source": "web",
  "status": "succeeded",
  "created_at": "2023-10-10T21:50:46.431928Z",
  "started_at": "2023-10-10T21:50:47.067605Z",
  "completed_at": "2023-10-10T21:53:04.546496Z",
  "urls": {
    "cancel": "https://api.replicate.com/v1/predictions/gokuok3bcjagn6us2r2vf4452y/cancel",
    "get": "https://api.replicate.com/v1/predictions/gokuok3bcjagn6us2r2vf4452y"
  },
  "metrics": {
    "predict_time": 137.478891,
    "total_time": 138.114568
  }
}

Generated in

2 minutes 17 seconds

Tweak it Report

Using seed: 340234 Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: In style of andreas feininger, a large blooming red rose in the middle of gloomy city. The flower is one connected plant. txt2img mode 0%| | 0/66 [00:00<?, ?it/s] 2%|▏ | 1/66 [00:01<01:29, 1.38s/it] 3%|▎ | 2/66 [00:02<01:28, 1.38s/it] 5%|▍ | 3/66 [00:04<01:27, 1.38s/it] 6%|▌ | 4/66 [00:05<01:25, 1.38s/it] 8%|▊ | 5/66 [00:06<01:24, 1.39s/it] 9%|▉ | 6/66 [00:08<01:23, 1.39s/it] 11%|█ | 7/66 [00:09<01:21, 1.39s/it] 12%|█▏ | 8/66 [00:11<01:20, 1.39s/it] 14%|█▎ | 9/66 [00:12<01:18, 1.38s/it] 15%|█▌ | 10/66 [00:13<01:17, 1.38s/it] 17%|█▋ | 11/66 [00:15<01:16, 1.39s/it] 18%|█▊ | 12/66 [00:16<01:14, 1.38s/it] 20%|█▉ | 13/66 [00:18<01:13, 1.39s/it] 21%|██ | 14/66 [00:19<01:12, 1.39s/it] 23%|██▎ | 15/66 [00:20<01:10, 1.39s/it] 24%|██▍ | 16/66 [00:22<01:09, 1.39s/it] 26%|██▌ | 17/66 [00:23<01:08, 1.39s/it] 27%|██▋ | 18/66 [00:24<01:06, 1.39s/it] 29%|██▉ | 19/66 [00:26<01:05, 1.39s/it] 30%|███ | 20/66 [00:27<01:03, 1.39s/it] 32%|███▏ | 21/66 [00:29<01:02, 1.39s/it] 33%|███▎ | 22/66 [00:30<01:01, 1.39s/it] 35%|███▍ | 23/66 [00:31<00:59, 1.39s/it] 36%|███▋ | 24/66 [00:33<00:58, 1.39s/it] 38%|███▊ | 25/66 [00:34<00:56, 1.39s/it] 39%|███▉ | 26/66 [00:36<00:55, 1.39s/it] 41%|████ | 27/66 [00:37<00:54, 1.39s/it] 42%|████▏ | 28/66 [00:38<00:52, 1.39s/it] 44%|████▍ | 29/66 [00:40<00:51, 1.39s/it] 45%|████▌ | 30/66 [00:41<00:50, 1.39s/it] 47%|████▋ | 31/66 [00:43<00:48, 1.39s/it] 48%|████▊ | 32/66 [00:44<00:47, 1.39s/it] 50%|█████ | 33/66 [00:45<00:45, 1.39s/it] 52%|█████▏ | 34/66 [00:47<00:44, 1.39s/it] 53%|█████▎ | 35/66 [00:48<00:43, 1.39s/it] 55%|█████▍ | 36/66 [00:49<00:41, 1.39s/it] 56%|█████▌ | 37/66 [00:51<00:40, 1.39s/it] 58%|█████▊ | 38/66 [00:52<00:38, 1.39s/it] 59%|█████▉ | 39/66 [00:54<00:37, 1.39s/it] 61%|██████ | 40/66 [00:55<00:36, 1.39s/it] 62%|██████▏ | 41/66 [00:56<00:34, 1.39s/it] 64%|██████▎ | 42/66 [00:58<00:33, 1.39s/it] 65%|██████▌ | 43/66 [00:59<00:32, 1.39s/it] 67%|██████▋ | 44/66 [01:01<00:30, 1.39s/it] 68%|██████▊ | 45/66 [01:02<00:29, 1.39s/it] 70%|██████▉ | 46/66 [01:03<00:27, 1.39s/it] 71%|███████ | 47/66 [01:05<00:26, 1.39s/it] 73%|███████▎ | 48/66 [01:06<00:25, 1.39s/it] 74%|███████▍ | 49/66 [01:08<00:23, 1.39s/it] 76%|███████▌ | 50/66 [01:09<00:22, 1.39s/it] 77%|███████▋ | 51/66 [01:10<00:20, 1.39s/it] 79%|███████▉ | 52/66 [01:12<00:19, 1.39s/it] 80%|████████ | 53/66 [01:13<00:18, 1.39s/it] 82%|████████▏ | 54/66 [01:15<00:16, 1.39s/it] 83%|████████▎ | 55/66 [01:16<00:15, 1.39s/it] 85%|████████▍ | 56/66 [01:17<00:13, 1.39s/it] 86%|████████▋ | 57/66 [01:19<00:12, 1.39s/it] 88%|████████▊ | 58/66 [01:20<00:11, 1.40s/it] 89%|████████▉ | 59/66 [01:22<00:09, 1.39s/it] 91%|█████████ | 60/66 [01:23<00:08, 1.40s/it] 92%|█████████▏| 61/66 [01:24<00:06, 1.39s/it] 94%|█████████▍| 62/66 [01:26<00:05, 1.40s/it] 95%|█████████▌| 63/66 [01:27<00:04, 1.39s/it] 97%|█████████▋| 64/66 [01:29<00:02, 1.39s/it] 98%|█████████▊| 65/66 [01:30<00:01, 1.39s/it] 100%|██████████| 66/66 [01:31<00:00, 1.40s/it] 100%|██████████| 66/66 [01:31<00:00, 1.39s/it] 0%| | 0/29 [00:00<?, ?it/s] 3%|▎ | 1/29 [00:01<00:39, 1.41s/it] 7%|▋ | 2/29 [00:02<00:38, 1.42s/it] 10%|█ | 3/29 [00:04<00:36, 1.42s/it] 14%|█▍ | 4/29 [00:05<00:35, 1.41s/it] 17%|█▋ | 5/29 [00:07<00:33, 1.42s/it] 21%|██ | 6/29 [00:08<00:32, 1.42s/it] 24%|██▍ | 7/29 [00:09<00:31, 1.41s/it] 28%|██▊ | 8/29 [00:11<00:29, 1.41s/it] 31%|███ | 9/29 [00:12<00:28, 1.41s/it] 34%|███▍ | 10/29 [00:14<00:26, 1.41s/it] 38%|███▊ | 11/29 [00:15<00:25, 1.41s/it] 41%|████▏ | 12/29 [00:16<00:24, 1.41s/it] 45%|████▍ | 13/29 [00:18<00:22, 1.41s/it] 48%|████▊ | 14/29 [00:19<00:21, 1.41s/it] 52%|█████▏ | 15/29 [00:21<00:19, 1.42s/it] 55%|█████▌ | 16/29 [00:22<00:18, 1.42s/it] 59%|█████▊ | 17/29 [00:24<00:17, 1.42s/it] 62%|██████▏ | 18/29 [00:25<00:15, 1.42s/it] 66%|██████▌ | 19/29 [00:26<00:14, 1.42s/it] 69%|██████▉ | 20/29 [00:28<00:12, 1.42s/it] 72%|███████▏ | 21/29 [00:29<00:11, 1.42s/it] 76%|███████▌ | 22/29 [00:31<00:09, 1.42s/it] 79%|███████▉ | 23/29 [00:32<00:08, 1.42s/it] 83%|████████▎ | 24/29 [00:33<00:07, 1.42s/it] 86%|████████▌ | 25/29 [00:35<00:05, 1.42s/it] 90%|████████▉ | 26/29 [00:36<00:04, 1.42s/it] 93%|█████████▎| 27/29 [00:38<00:02, 1.42s/it] 97%|█████████▋| 28/29 [00:39<00:01, 1.42s/it] 100%|██████████| 29/29 [00:41<00:00, 1.42s/it] 100%|██████████| 29/29 [00:41<00:00, 1.42s/it]