Prediction

Model

fofr/sd3-explorer:ba332080

vmp5h000c9rgj0cg5d6813mmnr

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

7.8s

Created

over 1 year ago by fofr

Webhook

–

Input

model: sd3_medium_incl_clips_t5xxlfp16.safetensors
width: 1156
height: 768
steps: 32
sampler: dpmpp_2m
scheduler: sgm_uniform
shift: 6
guidance_scale: 4
number_of_images: 1
use_triple_prompt: true
triple_prompt_clip_g: a cartoon, dreamy anime background, a photo of a dog
triple_prompt_clip_l: a cartoon, dreamy anime background, a photo of a dog
triple_prompt_t5: the words written across the sky say "hello world", written in clouds from a plane, above the dog
triple_prompt_empty_padding: true
negative_prompt: Empty string
negative_conditioning_end: 0
output_format: webp
output_quality: 80

{
  "guidance_scale": 4,
  "height": 768,
  "model": "sd3_medium_incl_clips_t5xxlfp16.safetensors",
  "negative_conditioning_end": 0,
  "negative_prompt": "",
  "number_of_images": 1,
  "output_format": "webp",
  "output_quality": 80,
  "sampler": "dpmpp_2m",
  "scheduler": "sgm_uniform",
  "shift": 6,
  "steps": 32,
  "triple_prompt_clip_g": "a cartoon, dreamy anime background, a photo of a dog",
  "triple_prompt_clip_l": "a cartoon, dreamy anime background, a photo of a dog",
  "triple_prompt_empty_padding": true,
  "triple_prompt_t5": "the words written across the sky say \"hello world\", written in clouds from a plane, above the dog",
  "use_triple_prompt": true,
  "width": 1156
}

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=r8_Zqn**********************************

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 fofr/sd3-explorer using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "fofr/sd3-explorer:ba3320806125ae93991c899010c998e4ee6a9dc6bdd89aeb6ecbd992815650a9",
  {
    input: {
      guidance_scale: 4,
      height: 768,
      model: "sd3_medium_incl_clips_t5xxlfp16.safetensors",
      negative_conditioning_end: 0,
      negative_prompt: "",
      number_of_images: 1,
      output_format: "webp",
      output_quality: 80,
      sampler: "dpmpp_2m",
      scheduler: "sgm_uniform",
      shift: 6,
      steps: 32,
      triple_prompt_clip_g: "a cartoon, dreamy anime background, a photo of a dog",
      triple_prompt_clip_l: "a cartoon, dreamy anime background, a photo of a dog",
      triple_prompt_empty_padding: true,
      triple_prompt_t5: "the words written across the sky say \"hello world\", written in clouds from a plane, above the dog",
      use_triple_prompt: true,
      width: 1156
    }
  }
);

// 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_Zqn**********************************

This is your API token. Keep it to yourself.

Import the client:

import replicate

Run fofr/sd3-explorer using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "fofr/sd3-explorer:ba3320806125ae93991c899010c998e4ee6a9dc6bdd89aeb6ecbd992815650a9",
    input={
        "guidance_scale": 4,
        "height": 768,
        "model": "sd3_medium_incl_clips_t5xxlfp16.safetensors",
        "negative_conditioning_end": 0,
        "negative_prompt": "",
        "number_of_images": 1,
        "output_format": "webp",
        "output_quality": 80,
        "sampler": "dpmpp_2m",
        "scheduler": "sgm_uniform",
        "shift": 6,
        "steps": 32,
        "triple_prompt_clip_g": "a cartoon, dreamy anime background, a photo of a dog",
        "triple_prompt_clip_l": "a cartoon, dreamy anime background, a photo of a dog",
        "triple_prompt_empty_padding": True,
        "triple_prompt_t5": "the words written across the sky say \"hello world\", written in clouds from a plane, above the dog",
        "use_triple_prompt": True,
        "width": 1156
    }
)

# 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_Zqn**********************************

This is your API token. Keep it to yourself.

Run fofr/sd3-explorer 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": "fofr/sd3-explorer:ba3320806125ae93991c899010c998e4ee6a9dc6bdd89aeb6ecbd992815650a9",
    "input": {
      "guidance_scale": 4,
      "height": 768,
      "model": "sd3_medium_incl_clips_t5xxlfp16.safetensors",
      "negative_conditioning_end": 0,
      "negative_prompt": "",
      "number_of_images": 1,
      "output_format": "webp",
      "output_quality": 80,
      "sampler": "dpmpp_2m",
      "scheduler": "sgm_uniform",
      "shift": 6,
      "steps": 32,
      "triple_prompt_clip_g": "a cartoon, dreamy anime background, a photo of a dog",
      "triple_prompt_clip_l": "a cartoon, dreamy anime background, a photo of a dog",
      "triple_prompt_empty_padding": true,
      "triple_prompt_t5": "the words written across the sky say \\"hello world\\", written in clouds from a plane, above the dog",
      "use_triple_prompt": true,
      "width": 1156
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "id": "vmp5h000c9rgj0cg5d6813mmnr",
  "model": "fofr/sd3-explorer",
  "version": "ba3320806125ae93991c899010c998e4ee6a9dc6bdd89aeb6ecbd992815650a9",
  "input": {
    "guidance_scale": 4,
    "height": 768,
    "model": "sd3_medium_incl_clips_t5xxlfp16.safetensors",
    "negative_conditioning_end": 0,
    "negative_prompt": "",
    "number_of_images": 1,
    "output_format": "webp",
    "output_quality": 80,
    "sampler": "dpmpp_2m",
    "scheduler": "sgm_uniform",
    "shift": 6,
    "steps": 32,
    "triple_prompt_clip_g": "a cartoon, dreamy anime background, a photo of a dog",
    "triple_prompt_clip_l": "a cartoon, dreamy anime background, a photo of a dog",
    "triple_prompt_empty_padding": true,
    "triple_prompt_t5": "the words written across the sky say \"hello world\", written in clouds from a plane, above the dog",
    "use_triple_prompt": true,
    "width": 1156
  },
  "logs": "Random seed set to: 2283277244\nChecking weights\n✅ sd3_medium_incl_clips_t5xxlfp16.safetensors exists in ComfyUI/models/checkpoints\n====================================\nRunning workflow\ngot prompt\nExecuting node 291, title: CLIPTextEncodeSD3, class type: CLIPTextEncodeSD3\nExecuting node 271, title: KSampler, class type: KSampler\n  0%|          | 0/32 [00:00<?, ?it/s]\n  6%|▋         | 2/32 [00:00<00:05,  5.25it/s]\n  9%|▉         | 3/32 [00:00<00:05,  5.23it/s]\n 12%|█▎        | 4/32 [00:00<00:05,  5.22it/s]\n 16%|█▌        | 5/32 [00:00<00:05,  5.20it/s]\n 19%|█▉        | 6/32 [00:01<00:04,  5.20it/s]\n 22%|██▏       | 7/32 [00:01<00:04,  5.20it/s]\n 25%|██▌       | 8/32 [00:01<00:04,  5.20it/s]\n 28%|██▊       | 9/32 [00:01<00:04,  5.19it/s]\n 31%|███▏      | 10/32 [00:01<00:04,  5.18it/s]\n 34%|███▍      | 11/32 [00:02<00:04,  5.18it/s]\n 38%|███▊      | 12/32 [00:02<00:03,  5.18it/s]\n 41%|████      | 13/32 [00:02<00:03,  5.19it/s]\n 44%|████▍     | 14/32 [00:02<00:03,  5.20it/s]\n 47%|████▋     | 15/32 [00:02<00:03,  5.19it/s]\n 50%|█████     | 16/32 [00:03<00:03,  5.19it/s]\n 53%|█████▎    | 17/32 [00:03<00:02,  5.19it/s]\n 56%|█████▋    | 18/32 [00:03<00:02,  5.19it/s]\n 59%|█████▉    | 19/32 [00:03<00:02,  5.19it/s]\n 62%|██████▎   | 20/32 [00:03<00:02,  5.19it/s]\n 66%|██████▌   | 21/32 [00:04<00:02,  5.18it/s]\n 69%|██████▉   | 22/32 [00:04<00:01,  5.18it/s]\n 72%|███████▏  | 23/32 [00:04<00:01,  5.18it/s]\n 75%|███████▌  | 24/32 [00:04<00:01,  5.17it/s]\n 78%|███████▊  | 25/32 [00:04<00:01,  5.17it/s]\n 81%|████████▏ | 26/32 [00:05<00:01,  5.17it/s]\n 84%|████████▍ | 27/32 [00:05<00:00,  5.16it/s]\n 88%|████████▊ | 28/32 [00:05<00:00,  5.16it/s]\n 91%|█████████ | 29/32 [00:05<00:00,  5.17it/s]\n 94%|█████████▍| 30/32 [00:05<00:00,  5.17it/s]\n 97%|█████████▋| 31/32 [00:05<00:00,  5.17it/s]\n100%|██████████| 32/32 [00:06<00:00,  5.18it/s]\n100%|██████████| 32/32 [00:06<00:00,  5.19it/s]\nExecuting node 231, title: VAE Decode, class type: VAEDecode\nExecuting node 273, title: Save Image, class type: SaveImage\nPrompt executed in 6.63 seconds\noutputs:  {'273': {'images': [{'filename': 'SD3_00001_.png', 'subfolder': '', 'type': 'output'}]}}\n====================================\nSD3_00001_.png",
  "output": [
    "https://replicate.delivery/pbxt/MJb55kWPbaIxF1DQfb3IMhYD1P6M5BuMZb3hdUnwPKQ3b5fSA/SD3_00001_.webp"
  ],
  "data_removed": false,
  "error": null,
  "source": "web",
  "status": "succeeded",
  "created_at": "2024-06-18T12:21:59.522Z",
  "started_at": "2024-06-18T12:21:59.55885Z",
  "completed_at": "2024-06-18T12:22:07.3654Z",
  "urls": {
    "cancel": "https://api.replicate.com/v1/predictions/vmp5h000c9rgj0cg5d6813mmnr/cancel",
    "get": "https://api.replicate.com/v1/predictions/vmp5h000c9rgj0cg5d6813mmnr",
    "web": "https://replicate.com/p/vmp5h000c9rgj0cg5d6813mmnr"
  },
  "metrics": {
    "predict_time": 7.806549779,
    "total_time": 7.8434
  }
}

Generated in

7.8 seconds

Tweak it Report

Random seed set to: 2283277244 Checking weights ✅ sd3_medium_incl_clips_t5xxlfp16.safetensors exists in ComfyUI/models/checkpoints ==================================== Running workflow got prompt Executing node 291, title: CLIPTextEncodeSD3, class type: CLIPTextEncodeSD3 Executing node 271, title: KSampler, class type: KSampler 0%| | 0/32 [00:00<?, ?it/s] 6%|▋ | 2/32 [00:00<00:05, 5.25it/s] 9%|▉ | 3/32 [00:00<00:05, 5.23it/s] 12%|█▎ | 4/32 [00:00<00:05, 5.22it/s] 16%|█▌ | 5/32 [00:00<00:05, 5.20it/s] 19%|█▉ | 6/32 [00:01<00:04, 5.20it/s] 22%|██▏ | 7/32 [00:01<00:04, 5.20it/s] 25%|██▌ | 8/32 [00:01<00:04, 5.20it/s] 28%|██▊ | 9/32 [00:01<00:04, 5.19it/s] 31%|███▏ | 10/32 [00:01<00:04, 5.18it/s] 34%|███▍ | 11/32 [00:02<00:04, 5.18it/s] 38%|███▊ | 12/32 [00:02<00:03, 5.18it/s] 41%|████ | 13/32 [00:02<00:03, 5.19it/s] 44%|████▍ | 14/32 [00:02<00:03, 5.20it/s] 47%|████▋ | 15/32 [00:02<00:03, 5.19it/s] 50%|█████ | 16/32 [00:03<00:03, 5.19it/s] 53%|█████▎ | 17/32 [00:03<00:02, 5.19it/s] 56%|█████▋ | 18/32 [00:03<00:02, 5.19it/s] 59%|█████▉ | 19/32 [00:03<00:02, 5.19it/s] 62%|██████▎ | 20/32 [00:03<00:02, 5.19it/s] 66%|██████▌ | 21/32 [00:04<00:02, 5.18it/s] 69%|██████▉ | 22/32 [00:04<00:01, 5.18it/s] 72%|███████▏ | 23/32 [00:04<00:01, 5.18it/s] 75%|███████▌ | 24/32 [00:04<00:01, 5.17it/s] 78%|███████▊ | 25/32 [00:04<00:01, 5.17it/s] 81%|████████▏ | 26/32 [00:05<00:01, 5.17it/s] 84%|████████▍ | 27/32 [00:05<00:00, 5.16it/s] 88%|████████▊ | 28/32 [00:05<00:00, 5.16it/s] 91%|█████████ | 29/32 [00:05<00:00, 5.17it/s] 94%|█████████▍| 30/32 [00:05<00:00, 5.17it/s] 97%|█████████▋| 31/32 [00:05<00:00, 5.17it/s] 100%|██████████| 32/32 [00:06<00:00, 5.18it/s] 100%|██████████| 32/32 [00:06<00:00, 5.19it/s] Executing node 231, title: VAE Decode, class type: VAEDecode Executing node 273, title: Save Image, class type: SaveImage Prompt executed in 6.63 seconds outputs: {'273': {'images': [{'filename': 'SD3_00001_.png', 'subfolder': '', 'type': 'output'}]}} ==================================== SD3_00001_.png