zelenioncode/custum_model_safetonsors | Run with an API on Replicate

zelenioncode / custum_model_safetonsors

DreamBooth safetensors model use RealVisXL

Cold

Public
757 runs
L40S

Iterate in playground

Run with an API

Playground API Examples README Versions

Input

safetensors

string

Shift + Return to add a new line

https://huggingface.co/WGlint/sfya_ReaVis_V5.1_noVAE/blob/main/sfya_rv.safetensorshttps://huggingface.co/WGlint/sfya_ReaVis_V5.1_noVAE/blob/main/sfya_rv.safetensors

Enter a safetensors (direct link download)

Default: "https://huggingface.co/WGlint/sfya_ReaVis_V5.1_noVAE/blob/main/sfya_rv.safetensors"

prompt

string

Shift + Return to add a new line

photograph of casual sophisticated ohwx woman, looking camera, classic side part, tailored black three-piece suit,skin imperfections, 8k uhd, dsir, soft lighting, high quality, film grain, Fujifilm XT3photograph of casual sophisticated ohwx woman, looking camera, classic side part, tailored black three-piece suit,skin imperfections, 8k uhd, dsir, soft lighting, high quality, film grain, Fujifilm XT3

Enter a prompt

Default: "dark shot, photo of a cute ohwx woman, perfect eyes, natural skin, skin moles, cinematic shot"

negative_prompt

string

Shift + Return to add a new line

Tattoos, (deformed iris, deformed pupils, semi-realistic, gi, 3d, render, sketch, cartoon, drawing, anime), text, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck, UnrealisticDreamTattoos, (deformed iris, deformed pupils, semi-realistic, gi, 3d, render, sketch, cartoon, drawing, anime), text, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck, UnrealisticDream

Enter a negative prompt

Default: "Tattoos, (deformed iris, deformed pupils, semi-realistic, gi, 3d, render, sketch, cartoon, drawing, anime), text, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck, UnrealisticDream"

scheduler

string

Scheduler to use

Default: "DDIM"

width

integer

Enter a width

Default: 768

height

integer

Enter a height

Default: 1024

guidance_scale

integer

Enter a guidance scale

Default: 7

num_inference_steps

integer

Enter a number of inference steps

Default: 40

seed

integer

Enter a seed

Default: 1334

number_picture

integer

(minimum: 1, maximum: 4)

Enter a number of picture

Default: 1

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

npx create-replicate --model=zelenioncode/custum_model_safetonsors

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";
import fs from "node:fs";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

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

const output = await replicate.run(
  "zelenioncode/custum_model_safetonsors:eef480e5d1bbed213f523e8f49ae4a34e853361a0b177e0cffa5b081e3246429",
  {
    input: {
      seed: 3456051406,
      width: 768,
      height: 1024,
      prompt: "photograph of casual sophisticated ohwx woman, looking camera, classic side part, tailored black three-piece suit,skin imperfections, 8k uhd, dsir, soft lighting, high quality, film grain, Fujifilm XT3",
      scheduler: "DDIM",
      safetensors: "https://huggingface.co/WGlint/sfya_ReaVis_V5.1_noVAE/blob/main/sfya_rv.safetensors",
      guidance_scale: 7,
      number_picture: 4,
      negative_prompt: "Tattoos, (deformed iris, deformed pupils, semi-realistic, gi, 3d, render, sketch, cartoon, drawing, anime), text, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck, UnrealisticDream",
      num_inference_steps: 40
    }
  }
);

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

output = replicate.run(
    "zelenioncode/custum_model_safetonsors:eef480e5d1bbed213f523e8f49ae4a34e853361a0b177e0cffa5b081e3246429",
    input={
        "seed": 3456051406,
        "width": 768,
        "height": 1024,
        "prompt": "photograph of casual sophisticated ohwx woman, looking camera, classic side part, tailored black three-piece suit,skin imperfections, 8k uhd, dsir, soft lighting, high quality, film grain, Fujifilm XT3",
        "scheduler": "DDIM",
        "safetensors": "https://huggingface.co/WGlint/sfya_ReaVis_V5.1_noVAE/blob/main/sfya_rv.safetensors",
        "guidance_scale": 7,
        "number_picture": 4,
        "negative_prompt": "Tattoos, (deformed iris, deformed pupils, semi-realistic, gi, 3d, render, sketch, cartoon, drawing, anime), text, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck, UnrealisticDream",
        "num_inference_steps": 40
    }
)
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 zelenioncode/custum_model_safetonsors 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": "zelenioncode/custum_model_safetonsors:eef480e5d1bbed213f523e8f49ae4a34e853361a0b177e0cffa5b081e3246429",
    "input": {
      "seed": 3456051406,
      "width": 768,
      "height": 1024,
      "prompt": "photograph of casual sophisticated ohwx woman, looking camera, classic side part, tailored black three-piece suit,skin imperfections, 8k uhd, dsir, soft lighting, high quality, film grain, Fujifilm XT3",
      "scheduler": "DDIM",
      "safetensors": "https://huggingface.co/WGlint/sfya_ReaVis_V5.1_noVAE/blob/main/sfya_rv.safetensors",
      "guidance_scale": 7,
      "number_picture": 4,
      "negative_prompt": "Tattoos, (deformed iris, deformed pupils, semi-realistic, gi, 3d, render, sketch, cartoon, drawing, anime), text, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck, UnrealisticDream",
      "num_inference_steps": 40
    }
  }' \
  https://api.replicate.com/v1/predictions

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

You can run this model locally using Cog. First, install Cog:

brew install cog

If you don’t have Homebrew, there are other installation options available.

Run this to download the model and run it in your local environment:

cog predict r8.im/zelenioncode/custum_model_safetonsors@sha256:eef480e5d1bbed213f523e8f49ae4a34e853361a0b177e0cffa5b081e3246429 \
  -i 'seed=3456051406' \
  -i 'width=768' \
  -i 'height=1024' \
  -i 'prompt="photograph of casual sophisticated ohwx woman, looking camera, classic side part, tailored black three-piece suit,skin imperfections, 8k uhd, dsir, soft lighting, high quality, film grain, Fujifilm XT3"' \
  -i 'scheduler="DDIM"' \
  -i 'safetensors="https://huggingface.co/WGlint/sfya_ReaVis_V5.1_noVAE/blob/main/sfya_rv.safetensors"' \
  -i 'guidance_scale=7' \
  -i 'number_picture=4' \
  -i 'negative_prompt="Tattoos, (deformed iris, deformed pupils, semi-realistic, gi, 3d, render, sketch, cartoon, drawing, anime), text, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck, UnrealisticDream"' \
  -i 'num_inference_steps=40'

To learn more, take a look at the Cog documentation.

Run this to download the model and run it in your local environment:

docker run -d -p 5000:5000 --gpus=all r8.im/zelenioncode/custum_model_safetonsors@sha256:eef480e5d1bbed213f523e8f49ae4a34e853361a0b177e0cffa5b081e3246429
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "seed": 3456051406,
      "width": 768,
      "height": 1024,
      "prompt": "photograph of casual sophisticated ohwx woman, looking camera, classic side part, tailored black three-piece suit,skin imperfections, 8k uhd, dsir, soft lighting, high quality, film grain, Fujifilm XT3",
      "scheduler": "DDIM",
      "safetensors": "https://huggingface.co/WGlint/sfya_ReaVis_V5.1_noVAE/blob/main/sfya_rv.safetensors",
      "guidance_scale": 7,
      "number_picture": 4,
      "negative_prompt": "Tattoos, (deformed iris, deformed pupils, semi-realistic, gi, 3d, render, sketch, cartoon, drawing, anime), text, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck, UnrealisticDream",
      "num_inference_steps": 40
    }
  }' \
  http://localhost:5000/predictions

To learn more, take a look at the Cog documentation.

Output

{
  "completed_at": "2023-12-17T19:59:21.786786Z",
  "created_at": "2023-12-17T19:59:06.046473Z",
  "data_removed": false,
  "error": null,
  "id": "5kse7pdbe7m4h4hbu4ekveqt5e",
  "input": {
    "seed": 3456051406,
    "width": 768,
    "height": 1024,
    "prompt": "photograph of casual sophisticated ohwx woman, looking camera, classic side part, tailored black three-piece suit,skin imperfections, 8k uhd, dsir, soft lighting, high quality, film grain, Fujifilm XT3",
    "WithRVXL": true,
    "guidance_scale": 7,
    "number_picture": 4,
    "negative_prompt": "Tattoos, (deformed iris, deformed pupils, semi-realistic, gi, 3d, render, sketch, cartoon, drawing, anime), text, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck, UnrealisticDream",
    "num_inference_steps": 40
  },
  "logs": "0%|          | 0/40 [00:00<?, ?it/s]\n  2%|▎         | 1/40 [00:00<00:12,  3.17it/s]\n  5%|▌         | 2/40 [00:00<00:11,  3.27it/s]\n  8%|▊         | 3/40 [00:00<00:11,  3.30it/s]\n 10%|█         | 4/40 [00:01<00:10,  3.31it/s]\n 12%|█▎        | 5/40 [00:01<00:10,  3.32it/s]\n 15%|█▌        | 6/40 [00:01<00:10,  3.33it/s]\n 18%|█▊        | 7/40 [00:02<00:09,  3.33it/s]\n 20%|██        | 8/40 [00:02<00:09,  3.33it/s]\n 22%|██▎       | 9/40 [00:02<00:09,  3.32it/s]\n 25%|██▌       | 10/40 [00:03<00:09,  3.32it/s]\n 28%|██▊       | 11/40 [00:03<00:08,  3.32it/s]\n 30%|███       | 12/40 [00:03<00:08,  3.32it/s]\n 32%|███▎      | 13/40 [00:03<00:08,  3.32it/s]\n 35%|███▌      | 14/40 [00:04<00:07,  3.33it/s]\n 38%|███▊      | 15/40 [00:04<00:07,  3.33it/s]\n 40%|████      | 16/40 [00:04<00:07,  3.33it/s]\n 42%|████▎     | 17/40 [00:05<00:06,  3.33it/s]\n 45%|████▌     | 18/40 [00:05<00:06,  3.33it/s]\n 48%|████▊     | 19/40 [00:05<00:06,  3.32it/s]\n 50%|█████     | 20/40 [00:06<00:06,  3.32it/s]\n 52%|█████▎    | 21/40 [00:06<00:05,  3.32it/s]\n 55%|█████▌    | 22/40 [00:06<00:05,  3.32it/s]\n 57%|█████▊    | 23/40 [00:06<00:05,  3.32it/s]\n 60%|██████    | 24/40 [00:07<00:04,  3.32it/s]\n 62%|██████▎   | 25/40 [00:07<00:04,  3.32it/s]\n 65%|██████▌   | 26/40 [00:07<00:04,  3.32it/s]\n 68%|██████▊   | 27/40 [00:08<00:03,  3.32it/s]\n 70%|███████   | 28/40 [00:08<00:03,  3.32it/s]\n 72%|███████▎  | 29/40 [00:08<00:03,  3.32it/s]\n 75%|███████▌  | 30/40 [00:09<00:03,  3.32it/s]\n 78%|███████▊  | 31/40 [00:09<00:02,  3.32it/s]\n 80%|████████  | 32/40 [00:09<00:02,  3.32it/s]\n 82%|████████▎ | 33/40 [00:09<00:02,  3.32it/s]\n 85%|████████▌ | 34/40 [00:10<00:01,  3.32it/s]\n 88%|████████▊ | 35/40 [00:10<00:01,  3.32it/s]\n 90%|█████████ | 36/40 [00:10<00:01,  3.32it/s]\n 92%|█████████▎| 37/40 [00:11<00:00,  3.32it/s]\n 95%|█████████▌| 38/40 [00:11<00:00,  3.32it/s]\n 98%|█████████▊| 39/40 [00:11<00:00,  3.32it/s]\n100%|██████████| 40/40 [00:12<00:00,  3.32it/s]\n100%|██████████| 40/40 [00:12<00:00,  3.32it/s]\nStableDiffusionXLPipeline {\n\"_class_name\": \"StableDiffusionXLPipeline\",\n\"_diffusers_version\": \"0.24.0\",\n\"feature_extractor\": [\nnull,\nnull\n],\n\"force_zeros_for_empty_prompt\": true,\n\"image_encoder\": [\nnull,\nnull\n],\n\"scheduler\": [\n\"diffusers\",\n\"EulerDiscreteScheduler\"\n],\n\"text_encoder\": [\n\"transformers\",\n\"CLIPTextModel\"\n],\n\"text_encoder_2\": [\n\"transformers\",\n\"CLIPTextModelWithProjection\"\n],\n\"tokenizer\": [\n\"transformers\",\n\"CLIPTokenizer\"\n],\n\"tokenizer_2\": [\n\"transformers\",\n\"CLIPTokenizer\"\n],\n\"unet\": [\n\"diffusers\",\n\"UNet2DConditionModel\"\n],\n\"vae\": [\n\"diffusers\",\n\"AutoencoderKL\"\n]\n}",
  "metrics": {
    "predict_time": 15.723499,
    "total_time": 15.740313
  },
  "output": [
    "https://replicate.delivery/pbxt/vxbYdrEID9oAKBEpMtcz7EP7ECPZPHdaU6EpR7C9AcHGF0gE/output_0.png",
    "https://replicate.delivery/pbxt/zttINejIQUWsUSosGtlYQ5x9DzMPaKi5o2ZAjfQJwEPZUQDSA/output_1.png",
    "https://replicate.delivery/pbxt/SNfXIDcPp2y7KyiTUkx5Zf6oxTWYjIzdD2Txm5eP6sdyogGkA/output_2.png",
    "https://replicate.delivery/pbxt/3qczqSwKJLZAD9Q1APpaTwJVWodS68ab5cNyNwOyhMZGF0gE/output_3.png"
  ],
  "started_at": "2023-12-17T19:59:06.063287Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/5kse7pdbe7m4h4hbu4ekveqt5e",
    "cancel": "https://api.replicate.com/v1/predictions/5kse7pdbe7m4h4hbu4ekveqt5e/cancel"
  },
  "version": "fbc6b8aa2b270d55b81836e4feee38c2f1051e79c6f414aa7ede98af5ef25781"
}

Generated in

15.7 seconds

Tweak itReport View full prediction

0%|          | 0/40 [00:00<?, ?it/s]
  2%|▎         | 1/40 [00:00<00:12,  3.17it/s]
  5%|▌         | 2/40 [00:00<00:11,  3.27it/s]
  8%|▊         | 3/40 [00:00<00:11,  3.30it/s]
 10%|█         | 4/40 [00:01<00:10,  3.31it/s]
 12%|█▎        | 5/40 [00:01<00:10,  3.32it/s]
 15%|█▌        | 6/40 [00:01<00:10,  3.33it/s]
 18%|█▊        | 7/40 [00:02<00:09,  3.33it/s]
 20%|██        | 8/40 [00:02<00:09,  3.33it/s]
 22%|██▎       | 9/40 [00:02<00:09,  3.32it/s]
 25%|██▌       | 10/40 [00:03<00:09,  3.32it/s]
 28%|██▊       | 11/40 [00:03<00:08,  3.32it/s]
 30%|███       | 12/40 [00:03<00:08,  3.32it/s]
 32%|███▎      | 13/40 [00:03<00:08,  3.32it/s]
 35%|███▌      | 14/40 [00:04<00:07,  3.33it/s]
 38%|███▊      | 15/40 [00:04<00:07,  3.33it/s]
 40%|████      | 16/40 [00:04<00:07,  3.33it/s]
 42%|████▎     | 17/40 [00:05<00:06,  3.33it/s]
 45%|████▌     | 18/40 [00:05<00:06,  3.33it/s]
 48%|████▊     | 19/40 [00:05<00:06,  3.32it/s]
 50%|█████     | 20/40 [00:06<00:06,  3.32it/s]
 52%|█████▎    | 21/40 [00:06<00:05,  3.32it/s]
 55%|█████▌    | 22/40 [00:06<00:05,  3.32it/s]
 57%|█████▊    | 23/40 [00:06<00:05,  3.32it/s]
 60%|██████    | 24/40 [00:07<00:04,  3.32it/s]
 62%|██████▎   | 25/40 [00:07<00:04,  3.32it/s]
 65%|██████▌   | 26/40 [00:07<00:04,  3.32it/s]
 68%|██████▊   | 27/40 [00:08<00:03,  3.32it/s]
 70%|███████   | 28/40 [00:08<00:03,  3.32it/s]
 72%|███████▎  | 29/40 [00:08<00:03,  3.32it/s]
 75%|███████▌  | 30/40 [00:09<00:03,  3.32it/s]
 78%|███████▊  | 31/40 [00:09<00:02,  3.32it/s]
 80%|████████  | 32/40 [00:09<00:02,  3.32it/s]
 82%|████████▎ | 33/40 [00:09<00:02,  3.32it/s]
 85%|████████▌ | 34/40 [00:10<00:01,  3.32it/s]
 88%|████████▊ | 35/40 [00:10<00:01,  3.32it/s]
 90%|█████████ | 36/40 [00:10<00:01,  3.32it/s]
 92%|█████████▎| 37/40 [00:11<00:00,  3.32it/s]
 95%|█████████▌| 38/40 [00:11<00:00,  3.32it/s]
 98%|█████████▊| 39/40 [00:11<00:00,  3.32it/s]
100%|██████████| 40/40 [00:12<00:00,  3.32it/s]
100%|██████████| 40/40 [00:12<00:00,  3.32it/s]
StableDiffusionXLPipeline {
"_class_name": "StableDiffusionXLPipeline",
"_diffusers_version": "0.24.0",
"feature_extractor": [
null,
null
],
"force_zeros_for_empty_prompt": true,
"image_encoder": [
null,
null
],
"scheduler": [
"diffusers",
"EulerDiscreteScheduler"
],
"text_encoder": [
"transformers",
"CLIPTextModel"
],
"text_encoder_2": [
"transformers",
"CLIPTextModelWithProjection"
],
"tokenizer": [
"transformers",
"CLIPTokenizer"
],
"tokenizer_2": [
"transformers",
"CLIPTokenizer"
],
"unet": [
"diffusers",
"UNet2DConditionModel"
],
"vae": [
"diffusers",
"AutoencoderKL"
]
}

This output was created using a different version of the model, zelenioncode/custum_model_safetonsors:fbc6b8aa.

Examples

View more examples

Run time and cost

This model costs approximately $0.088 to run on Replicate, or 11 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia L40S GPU hardware. Predictions typically complete within 91 seconds. The predict time for this model varies significantly based on the inputs.

Readme

This model doesn't have a readme.