fofr/sd3-explorer:ba332080 – Run with an API on Replicate

Version

You're looking at a specific version of this model. Jump to the model overview.

fofr /sd3-explorer:ba332080

Input

prompt

string

Shift + Return to add a new line

a closeup photo of a man standing in a foresta closeup photo of a man standing in a forest

This prompt is ignored when using the triple prompt mode. See below.

Default: ""

model

string

Pick whether to use T5-XXL in fp16, fp8 or not at all

Default: "sd3_medium_incl_clips_t5xxlfp16.safetensors"

width

integer

The width of the image

Default: 1024

height

integer

The height of the image

Default: 1024

steps

integer

The number of steps to run the diffusion model for

Default: 28

sampler

string

The sampler to use for the diffusion model

Default: "dpmpp_2m"

scheduler

string

The scheduler to use for the diffusion model

Default: "sgm_uniform"

shift

number

(minimum: 0, maximum: 20)

The timestep scheduling shift. Try values 6.0 and 2.0 to experiment with effects.

Default: 3

guidance_scale

number

(minimum: 0, maximum: 20)

The guidance scale tells the model how similar the output should be to the prompt.

Default: 4.5

number_of_images

integer

(minimum: 1, maximum: 10)

The number of images to generate

Default: 1

use_triple_prompt

boolean

Default: false

triple_prompt_clip_g

string

Shift + Return to add a new line

The prompt that will be passed to just the CLIP-G model.

Default: ""

triple_prompt_clip_l

string

Shift + Return to add a new line

The prompt that will be passed to just the CLIP-L model.

Default: ""

triple_prompt_t5

string

Shift + Return to add a new line

The prompt that will be passed to just the T5-XXL model.

Default: ""

triple_prompt_empty_padding

boolean

Whether to add padding for empty prompts. Useful if you only want to pass a prompt to one or two of the three text encoders. Has no effect when all prompts are filled. Disable this for interesting effects.

Default: true

negative_prompt

string

Shift + Return to add a new line

Negative prompts do not really work in SD3. This will simply cause your output image to vary in unpredictable ways.

Default: ""

negative_conditioning_end

number

(minimum: 0, maximum: 1)

When the negative conditioning should stop being applied. By default it is disabled.

Default: 0

output_format

string

Format of the output images

Default: "webp"

output_quality

integer

(minimum: 0, maximum: 100)

Quality of the output images, from 0 to 100. 100 is best quality, 0 is lowest quality.

Default: 80

seed

integer

Set a seed for reproducibility. Random by default.

Run this model in Node.js with one line of code:

npx create-replicate --model=fofr/sd3-explorer

or set up a project from scratch

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";

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: {
      seed: 20,
      model: "sd3_medium_incl_clips_t5xxlfp16.safetensors",
      shift: 3,
      steps: 32,
      width: 1024,
      height: 1024,
      prompt: "a closeup photo of a man standing in a forest",
      sampler: "dpmpp_2m",
      scheduler: "sgm_uniform",
      output_format: "webp",
      guidance_scale: 4.5,
      output_quality: 80,
      negative_prompt: "",
      number_of_images: 1,
      triple_prompt_t5: "",
      use_triple_prompt: false,
      triple_prompt_clip_g: "",
      triple_prompt_clip_l: "",
      negative_conditioning_end: 0,
      triple_prompt_empty_padding: true
    }
  }
);

// 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=<paste-your-token-here>

Find your API token in your account settings.

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={
        "seed": 20,
        "model": "sd3_medium_incl_clips_t5xxlfp16.safetensors",
        "shift": 3,
        "steps": 32,
        "width": 1024,
        "height": 1024,
        "prompt": "a closeup photo of a man standing in a forest",
        "sampler": "dpmpp_2m",
        "scheduler": "sgm_uniform",
        "output_format": "webp",
        "guidance_scale": 4.5,
        "output_quality": 80,
        "negative_prompt": "",
        "number_of_images": 1,
        "triple_prompt_t5": "",
        "use_triple_prompt": False,
        "triple_prompt_clip_g": "",
        "triple_prompt_clip_l": "",
        "negative_conditioning_end": 0,
        "triple_prompt_empty_padding": True
    }
)
print(output)

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=<paste-your-token-here>

Find your API token in your account settings.

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": "ba3320806125ae93991c899010c998e4ee6a9dc6bdd89aeb6ecbd992815650a9",
    "input": {
      "seed": 20,
      "model": "sd3_medium_incl_clips_t5xxlfp16.safetensors",
      "shift": 3,
      "steps": 32,
      "width": 1024,
      "height": 1024,
      "prompt": "a closeup photo of a man standing in a forest",
      "sampler": "dpmpp_2m",
      "scheduler": "sgm_uniform",
      "output_format": "webp",
      "guidance_scale": 4.5,
      "output_quality": 80,
      "negative_prompt": "",
      "number_of_images": 1,
      "triple_prompt_t5": "",
      "use_triple_prompt": false,
      "triple_prompt_clip_g": "",
      "triple_prompt_clip_l": "",
      "negative_conditioning_end": 0,
      "triple_prompt_empty_padding": true
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2024-06-18T12:41:52.961851Z",
  "created_at": "2024-06-18T12:41:37.873000Z",
  "data_removed": false,
  "error": null,
  "id": "vhbjm0qva5rgp0cg5devah6n34",
  "input": {
    "seed": 20,
    "model": "sd3_medium_incl_clips_t5xxlfp16.safetensors",
    "shift": 3,
    "steps": 32,
    "width": 1024,
    "height": 1024,
    "prompt": "a closeup photo of a man standing in a forest",
    "sampler": "dpmpp_2m",
    "scheduler": "sgm_uniform",
    "output_format": "webp",
    "guidance_scale": 4.5,
    "output_quality": 80,
    "negative_prompt": "",
    "number_of_images": 1,
    "triple_prompt_t5": "",
    "use_triple_prompt": false,
    "triple_prompt_clip_g": "",
    "triple_prompt_clip_l": "",
    "negative_conditioning_end": 0,
    "triple_prompt_empty_padding": true
  },
  "logs": "Seed set to: 20\nChecking weights\n✅ sd3_medium_incl_clips_t5xxlfp16.safetensors exists in ComfyUI/models/checkpoints\n====================================\nRunning workflow\ngot prompt\nExecuting node 6, title: CLIP Text Encode (Prompt), class type: CLIPTextEncode\nExecuting node 271, title: KSampler, class type: KSampler\n  0%|          | 0/32 [00:00<?, ?it/s]\n  6%|▋         | 2/32 [00:00<00:07,  4.26it/s]\n  9%|▉         | 3/32 [00:00<00:06,  4.25it/s]\n 12%|█▎        | 4/32 [00:00<00:06,  4.23it/s]\n 16%|█▌        | 5/32 [00:01<00:06,  4.23it/s]\n 19%|█▉        | 6/32 [00:01<00:06,  4.22it/s]\n 22%|██▏       | 7/32 [00:01<00:05,  4.22it/s]\n 25%|██▌       | 8/32 [00:01<00:05,  4.21it/s]\n 28%|██▊       | 9/32 [00:02<00:05,  4.21it/s]\n 31%|███▏      | 10/32 [00:02<00:05,  4.20it/s]\n 34%|███▍      | 11/32 [00:02<00:04,  4.20it/s]\n 38%|███▊      | 12/32 [00:02<00:04,  4.20it/s]\n 41%|████      | 13/32 [00:03<00:04,  4.20it/s]\n 44%|████▍     | 14/32 [00:03<00:04,  4.21it/s]\n 47%|████▋     | 15/32 [00:03<00:04,  4.21it/s]\n 50%|█████     | 16/32 [00:03<00:03,  4.20it/s]\n 53%|█████▎    | 17/32 [00:04<00:03,  4.20it/s]\n 56%|█████▋    | 18/32 [00:04<00:03,  4.20it/s]\n 59%|█████▉    | 19/32 [00:04<00:03,  4.20it/s]\n 62%|██████▎   | 20/32 [00:04<00:02,  4.19it/s]\n 66%|██████▌   | 21/32 [00:04<00:02,  4.19it/s]\n 69%|██████▉   | 22/32 [00:05<00:02,  4.20it/s]\n 72%|███████▏  | 23/32 [00:05<00:02,  4.20it/s]\n 75%|███████▌  | 24/32 [00:05<00:01,  4.20it/s]\n 78%|███████▊  | 25/32 [00:05<00:01,  4.20it/s]\n 81%|████████▏ | 26/32 [00:06<00:01,  4.20it/s]\n 84%|████████▍ | 27/32 [00:06<00:01,  4.19it/s]\n 88%|████████▊ | 28/32 [00:06<00:00,  4.20it/s]\n 91%|█████████ | 29/32 [00:06<00:00,  4.20it/s]\n 94%|█████████▍| 30/32 [00:07<00:00,  4.19it/s]\n 97%|█████████▋| 31/32 [00:07<00:00,  4.20it/s]\n100%|██████████| 32/32 [00:07<00:00,  4.19it/s]\n100%|██████████| 32/32 [00:07<00:00,  4.20it/s]\nExecuting node 231, title: VAE Decode, class type: VAEDecode\nExecuting node 273, title: Save Image, class type: SaveImage\nPrompt executed in 8.26 seconds\noutputs:  {'273': {'images': [{'filename': 'SD3_00001_.png', 'subfolder': '', 'type': 'output'}]}}\n====================================\nSD3_00001_.png",
  "metrics": {
    "predict_time": 8.785583497,
    "total_time": 15.088851
  },
  "output": [
    "https://replicate.delivery/pbxt/216yKDg001rTGNLIzZYUBw8yDeuRYQb5NEIbOTr523HIl5fSA/SD3_00001_.webp"
  ],
  "started_at": "2024-06-18T12:41:44.176268Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/vhbjm0qva5rgp0cg5devah6n34",
    "cancel": "https://api.replicate.com/v1/predictions/vhbjm0qva5rgp0cg5devah6n34/cancel"
  },
  "version": "ba3320806125ae93991c899010c998e4ee6a9dc6bdd89aeb6ecbd992815650a9"
}

Generated in

8.8 seconds

Tweak itReport

Seed set to: 20
Checking weights
✅ sd3_medium_incl_clips_t5xxlfp16.safetensors exists in ComfyUI/models/checkpoints
====================================
Running workflow
got prompt
Executing node 6, title: CLIP Text Encode (Prompt), class type: CLIPTextEncode
Executing node 271, title: KSampler, class type: KSampler
  0%|          | 0/32 [00:00<?, ?it/s]
  6%|▋         | 2/32 [00:00<00:07,  4.26it/s]
  9%|▉         | 3/32 [00:00<00:06,  4.25it/s]
 12%|█▎        | 4/32 [00:00<00:06,  4.23it/s]
 16%|█▌        | 5/32 [00:01<00:06,  4.23it/s]
 19%|█▉        | 6/32 [00:01<00:06,  4.22it/s]
 22%|██▏       | 7/32 [00:01<00:05,  4.22it/s]
 25%|██▌       | 8/32 [00:01<00:05,  4.21it/s]
 28%|██▊       | 9/32 [00:02<00:05,  4.21it/s]
 31%|███▏      | 10/32 [00:02<00:05,  4.20it/s]
 34%|███▍      | 11/32 [00:02<00:04,  4.20it/s]
 38%|███▊      | 12/32 [00:02<00:04,  4.20it/s]
 41%|████      | 13/32 [00:03<00:04,  4.20it/s]
 44%|████▍     | 14/32 [00:03<00:04,  4.21it/s]
 47%|████▋     | 15/32 [00:03<00:04,  4.21it/s]
 50%|█████     | 16/32 [00:03<00:03,  4.20it/s]
 53%|█████▎    | 17/32 [00:04<00:03,  4.20it/s]
 56%|█████▋    | 18/32 [00:04<00:03,  4.20it/s]
 59%|█████▉    | 19/32 [00:04<00:03,  4.20it/s]
 62%|██████▎   | 20/32 [00:04<00:02,  4.19it/s]
 66%|██████▌   | 21/32 [00:04<00:02,  4.19it/s]
 69%|██████▉   | 22/32 [00:05<00:02,  4.20it/s]
 72%|███████▏  | 23/32 [00:05<00:02,  4.20it/s]
 75%|███████▌  | 24/32 [00:05<00:01,  4.20it/s]
 78%|███████▊  | 25/32 [00:05<00:01,  4.20it/s]
 81%|████████▏ | 26/32 [00:06<00:01,  4.20it/s]
 84%|████████▍ | 27/32 [00:06<00:01,  4.19it/s]
 88%|████████▊ | 28/32 [00:06<00:00,  4.20it/s]
 91%|█████████ | 29/32 [00:06<00:00,  4.20it/s]
 94%|█████████▍| 30/32 [00:07<00:00,  4.19it/s]
 97%|█████████▋| 31/32 [00:07<00:00,  4.20it/s]
100%|██████████| 32/32 [00:07<00:00,  4.19it/s]
100%|██████████| 32/32 [00:07<00:00,  4.20it/s]
Executing node 231, title: VAE Decode, class type: VAEDecode
Executing node 273, title: Save Image, class type: SaveImage
Prompt executed in 8.26 seconds
outputs:  {'273': {'images': [{'filename': 'SD3_00001_.png', 'subfolder': '', 'type': 'output'}]}}
====================================
SD3_00001_.png