aisha-ai-official/sdxl-sim-v3-ultrares-b – Run with an API on Replicate

aisha-ai-official / sdxl-sim-v3-ultrares-b

Cold

Public
49 runs
L40S
Weights
License

Iterate in playground

Run with an API

Playground API Examples README Versions

Input

model

string

The model to use

Default: "SDXL-Sim-v3-Ultrares-b"

vae

string

The VAE to use

Default: "default"

prompt

string

Shift + Return to add a new line

a beautiful woman with dark-purple short hair and purple eyes on a street. She is wearing casual clothes with a hot cleavage. She is smiling when look to the viewera beautiful woman with dark-purple short hair and purple eyes on a street. She is wearing casual clothes with a hot cleavage. She is smiling when look to the viewer

The prompt, uses Compel weighting syntax

Default: "street, 1girl, dark-purple short hair, purple eyes, medium breasts, cleavage, casual clothes, smile, V"

negative_prompt

string

Shift + Return to add a new line

The negative prompt (For things you don't want), uses Compel weighting syntax

Default: "nsfw, naked"

cfg_scale

number

(minimum: 1, maximum: 50)

CFG scale defines how much attention the model pays to the prompt when generating, set to 1 to disable

Default: 7

guidance_rescale

number

(minimum: 0, maximum: 5)

The amount to rescale CFG generated noise to avoid generating overexposed images, set to 0 or 1 to disable

Default: 1

pag_scale

number

(minimum: 0, maximum: 50)

PAG scale is similar to CFG but it literally makes the result better, it's compatible with CFG too, set to 0 to disable

Default: 0

clip_skip

integer

(minimum: 1)

How many CLIP layers to skip, 1 is actually no skip, this is the behavior in A1111 so it's aligned to it

Default: 1

width

integer

(minimum: 1, maximum: 4096)

The width of the image

Default: 1024

height

integer

(minimum: 1, maximum: 4096)

The height of the image

Default: 1024

prepend_preprompt

boolean

Prepend preprompt (Prompt: "portrait photo of " Negative prompt: "low resolution, lowres, bad anatomy, bad hands, missing fingers, worst quality, low quality, normal quality, poor quality, bad hands, mutated hands, mutated fingers, extra finger, six fingers, deformed, worst, ")

Default: true

scheduler

string

The scheduler to use

Default: "Euler a"

steps

integer

(minimum: 1, maximum: 100)

The steps when generating

Default: 50

batch_size

integer

(minimum: 1, maximum: 4)

Number of images to generate (1-4), note if you set this to 4, some high resolution gens might fail because of not enough VRAM

Default: 1

seed

integer

The seed used when generating, set to -1 for random seed

Default: -1

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

npx create-replicate --model=aisha-ai-official/sdxl-sim-v3-ultrares-b

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 aisha-ai-official/sdxl-sim-v3-ultrares-b using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "aisha-ai-official/sdxl-sim-v3-ultrares-b:86a8bffc3c28a4bfdd56614cef93b46c8ca694aea7731ee1f9d4fed14e640d31",
  {
    input: {
      vae: "default",
      seed: -1,
      model: "SDXL-Sim-v3-Ultrares-b",
      steps: 50,
      width: 1024,
      height: 1024,
      prompt: "a beautiful woman with dark-purple short hair and purple eyes on a street. She is wearing casual clothes with a hot cleavage. She is smiling when look to the viewer",
      cfg_scale: 5,
      clip_skip: 1,
      pag_scale: 1,
      scheduler: "Euler a",
      batch_size: 1,
      negative_prompt: "nsfw, naked",
      guidance_rescale: 1,
      prepend_preprompt: 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 aisha-ai-official/sdxl-sim-v3-ultrares-b using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "aisha-ai-official/sdxl-sim-v3-ultrares-b:86a8bffc3c28a4bfdd56614cef93b46c8ca694aea7731ee1f9d4fed14e640d31",
    input={
        "vae": "default",
        "seed": -1,
        "model": "SDXL-Sim-v3-Ultrares-b",
        "steps": 50,
        "width": 1024,
        "height": 1024,
        "prompt": "a beautiful woman with dark-purple short hair and purple eyes on a street. She is wearing casual clothes with a hot cleavage. She is smiling when look to the viewer",
        "cfg_scale": 5,
        "clip_skip": 1,
        "pag_scale": 1,
        "scheduler": "Euler a",
        "batch_size": 1,
        "negative_prompt": "nsfw, naked",
        "guidance_rescale": 1,
        "prepend_preprompt": 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 aisha-ai-official/sdxl-sim-v3-ultrares-b 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": "aisha-ai-official/sdxl-sim-v3-ultrares-b:86a8bffc3c28a4bfdd56614cef93b46c8ca694aea7731ee1f9d4fed14e640d31",
    "input": {
      "vae": "default",
      "seed": -1,
      "model": "SDXL-Sim-v3-Ultrares-b",
      "steps": 50,
      "width": 1024,
      "height": 1024,
      "prompt": "a beautiful woman with dark-purple short hair and purple eyes on a street. She is wearing casual clothes with a hot cleavage. She is smiling when look to the viewer",
      "cfg_scale": 5,
      "clip_skip": 1,
      "pag_scale": 1,
      "scheduler": "Euler a",
      "batch_size": 1,
      "negative_prompt": "nsfw, naked",
      "guidance_rescale": 1,
      "prepend_preprompt": true
    }
  }' \
  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/aisha-ai-official/sdxl-sim-v3-ultrares-b@sha256:86a8bffc3c28a4bfdd56614cef93b46c8ca694aea7731ee1f9d4fed14e640d31 \
  -i 'vae="default"' \
  -i 'seed=-1' \
  -i 'model="SDXL-Sim-v3-Ultrares-b"' \
  -i 'steps=50' \
  -i 'width=1024' \
  -i 'height=1024' \
  -i 'prompt="a beautiful woman with dark-purple short hair and purple eyes on a street. She is wearing casual clothes with a hot cleavage. She is smiling when look to the viewer"' \
  -i 'cfg_scale=5' \
  -i 'clip_skip=1' \
  -i 'pag_scale=1' \
  -i 'scheduler="Euler a"' \
  -i 'batch_size=1' \
  -i 'negative_prompt="nsfw, naked"' \
  -i 'guidance_rescale=1' \
  -i 'prepend_preprompt=true'

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/aisha-ai-official/sdxl-sim-v3-ultrares-b@sha256:86a8bffc3c28a4bfdd56614cef93b46c8ca694aea7731ee1f9d4fed14e640d31
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "vae": "default",
      "seed": -1,
      "model": "SDXL-Sim-v3-Ultrares-b",
      "steps": 50,
      "width": 1024,
      "height": 1024,
      "prompt": "a beautiful woman with dark-purple short hair and purple eyes on a street. She is wearing casual clothes with a hot cleavage. She is smiling when look to the viewer",
      "cfg_scale": 5,
      "clip_skip": 1,
      "pag_scale": 1,
      "scheduler": "Euler a",
      "batch_size": 1,
      "negative_prompt": "nsfw, naked",
      "guidance_rescale": 1,
      "prepend_preprompt": true
    }
  }' \
  http://localhost:5000/predictions

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

Output

{
  "completed_at": "2025-02-27T01:24:20.121928Z",
  "created_at": "2025-02-27T01:24:10.911000Z",
  "data_removed": false,
  "error": null,
  "id": "he3hy58a3xrma0cn8m0svrnm7m",
  "input": {
    "vae": "default",
    "seed": -1,
    "model": "SDXL-Sim-v3-Ultrares-b",
    "steps": 50,
    "width": 1024,
    "height": 1024,
    "prompt": "a beautiful woman with dark-purple short hair and purple eyes on a street. She is wearing casual clothes with a hot cleavage. She is smiling when look to the viewer",
    "cfg_scale": 5,
    "clip_skip": 1,
    "pag_scale": 1,
    "scheduler": "Euler a",
    "batch_size": 1,
    "negative_prompt": "nsfw, naked",
    "guidance_rescale": 1,
    "prepend_preprompt": true
  },
  "logs": "Using text to image mode.\nUsing seed: 615852690\n  0%|          | 0/50 [00:00<?, ?it/s]\n  4%|▍         | 2/50 [00:00<00:05,  9.09it/s]\n  6%|▌         | 3/50 [00:00<00:05,  7.83it/s]\n  8%|▊         | 4/50 [00:00<00:06,  7.33it/s]\n 10%|█         | 5/50 [00:00<00:06,  7.06it/s]\n 12%|█▏        | 6/50 [00:00<00:06,  6.91it/s]\n 14%|█▍        | 7/50 [00:00<00:06,  6.81it/s]\n 16%|█▌        | 8/50 [00:01<00:06,  6.74it/s]\n 18%|█▊        | 9/50 [00:01<00:06,  6.69it/s]\n 20%|██        | 10/50 [00:01<00:06,  6.66it/s]\n 22%|██▏       | 11/50 [00:01<00:05,  6.63it/s]\n 24%|██▍       | 12/50 [00:01<00:05,  6.61it/s]\n 26%|██▌       | 13/50 [00:01<00:05,  6.60it/s]\n 28%|██▊       | 14/50 [00:02<00:05,  6.58it/s]\n 30%|███       | 15/50 [00:02<00:05,  6.58it/s]\n 32%|███▏      | 16/50 [00:02<00:05,  6.57it/s]\n 34%|███▍      | 17/50 [00:02<00:05,  6.57it/s]\n 36%|███▌      | 18/50 [00:02<00:04,  6.56it/s]\n 38%|███▊      | 19/50 [00:02<00:04,  6.55it/s]\n 40%|████      | 20/50 [00:02<00:04,  6.56it/s]\n 42%|████▏     | 21/50 [00:03<00:04,  6.55it/s]\n 44%|████▍     | 22/50 [00:03<00:04,  6.55it/s]\n 46%|████▌     | 23/50 [00:03<00:04,  6.55it/s]\n 48%|████▊     | 24/50 [00:03<00:03,  6.54it/s]\n 50%|█████     | 25/50 [00:03<00:03,  6.55it/s]\n 52%|█████▏    | 26/50 [00:03<00:03,  6.54it/s]\n 54%|█████▍    | 27/50 [00:04<00:03,  6.53it/s]\n 56%|█████▌    | 28/50 [00:04<00:03,  6.54it/s]\n 58%|█████▊    | 29/50 [00:04<00:03,  6.54it/s]\n 60%|██████    | 30/50 [00:04<00:03,  6.54it/s]\n 62%|██████▏   | 31/50 [00:04<00:02,  6.54it/s]\n 64%|██████▍   | 32/50 [00:04<00:02,  6.53it/s]\n 66%|██████▌   | 33/50 [00:04<00:02,  6.52it/s]\n 68%|██████▊   | 34/50 [00:05<00:02,  6.53it/s]\n 70%|███████   | 35/50 [00:05<00:02,  6.52it/s]\n 72%|███████▏  | 36/50 [00:05<00:02,  6.51it/s]\n 74%|███████▍  | 37/50 [00:05<00:01,  6.51it/s]\n 76%|███████▌  | 38/50 [00:05<00:01,  6.51it/s]\n 78%|███████▊  | 39/50 [00:05<00:01,  6.51it/s]\n 80%|████████  | 40/50 [00:06<00:01,  6.51it/s]\n 82%|████████▏ | 41/50 [00:06<00:01,  6.52it/s]\n 84%|████████▍ | 42/50 [00:06<00:01,  6.51it/s]\n 86%|████████▌ | 43/50 [00:06<00:01,  6.51it/s]\n 88%|████████▊ | 44/50 [00:06<00:00,  6.51it/s]\n 90%|█████████ | 45/50 [00:06<00:00,  6.50it/s]\n 92%|█████████▏| 46/50 [00:06<00:00,  6.51it/s]\n 94%|█████████▍| 47/50 [00:07<00:00,  6.50it/s]\n 96%|█████████▌| 48/50 [00:07<00:00,  6.50it/s]\n 98%|█████████▊| 49/50 [00:07<00:00,  6.49it/s]\n100%|██████████| 50/50 [00:07<00:00,  6.49it/s]\n100%|██████████| 50/50 [00:07<00:00,  6.61it/s]",
  "metrics": {
    "predict_time": 9.203185678,
    "total_time": 9.210928
  },
  "output": [
    "https://replicate.delivery/xezq/twewu43AZA1nMayFkHFDNyM1cerGjmITuwB5peyiI7XIGumoA/0.png"
  ],
  "started_at": "2025-02-27T01:24:10.918743Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-dx4ftxw72a72c6fmab3yrjub5q2okcptkljyv2g5j75anffrvgja",
    "get": "https://api.replicate.com/v1/predictions/he3hy58a3xrma0cn8m0svrnm7m",
    "cancel": "https://api.replicate.com/v1/predictions/he3hy58a3xrma0cn8m0svrnm7m/cancel"
  },
  "version": "86a8bffc3c28a4bfdd56614cef93b46c8ca694aea7731ee1f9d4fed14e640d31"
}

Generated in

9.2 seconds

Tweak it ShareReport

Using text to image mode.
Using seed: 615852690
  0%|          | 0/50 [00:00<?, ?it/s]
  4%|▍         | 2/50 [00:00<00:05,  9.09it/s]
  6%|▌         | 3/50 [00:00<00:05,  7.83it/s]
  8%|▊         | 4/50 [00:00<00:06,  7.33it/s]
 10%|█         | 5/50 [00:00<00:06,  7.06it/s]
 12%|█▏        | 6/50 [00:00<00:06,  6.91it/s]
 14%|█▍        | 7/50 [00:00<00:06,  6.81it/s]
 16%|█▌        | 8/50 [00:01<00:06,  6.74it/s]
 18%|█▊        | 9/50 [00:01<00:06,  6.69it/s]
 20%|██        | 10/50 [00:01<00:06,  6.66it/s]
 22%|██▏       | 11/50 [00:01<00:05,  6.63it/s]
 24%|██▍       | 12/50 [00:01<00:05,  6.61it/s]
 26%|██▌       | 13/50 [00:01<00:05,  6.60it/s]
 28%|██▊       | 14/50 [00:02<00:05,  6.58it/s]
 30%|███       | 15/50 [00:02<00:05,  6.58it/s]
 32%|███▏      | 16/50 [00:02<00:05,  6.57it/s]
 34%|███▍      | 17/50 [00:02<00:05,  6.57it/s]
 36%|███▌      | 18/50 [00:02<00:04,  6.56it/s]
 38%|███▊      | 19/50 [00:02<00:04,  6.55it/s]
 40%|████      | 20/50 [00:02<00:04,  6.56it/s]
 42%|████▏     | 21/50 [00:03<00:04,  6.55it/s]
 44%|████▍     | 22/50 [00:03<00:04,  6.55it/s]
 46%|████▌     | 23/50 [00:03<00:04,  6.55it/s]
 48%|████▊     | 24/50 [00:03<00:03,  6.54it/s]
 50%|█████     | 25/50 [00:03<00:03,  6.55it/s]
 52%|█████▏    | 26/50 [00:03<00:03,  6.54it/s]
 54%|█████▍    | 27/50 [00:04<00:03,  6.53it/s]
 56%|█████▌    | 28/50 [00:04<00:03,  6.54it/s]
 58%|█████▊    | 29/50 [00:04<00:03,  6.54it/s]
 60%|██████    | 30/50 [00:04<00:03,  6.54it/s]
 62%|██████▏   | 31/50 [00:04<00:02,  6.54it/s]
 64%|██████▍   | 32/50 [00:04<00:02,  6.53it/s]
 66%|██████▌   | 33/50 [00:04<00:02,  6.52it/s]
 68%|██████▊   | 34/50 [00:05<00:02,  6.53it/s]
 70%|███████   | 35/50 [00:05<00:02,  6.52it/s]
 72%|███████▏  | 36/50 [00:05<00:02,  6.51it/s]
 74%|███████▍  | 37/50 [00:05<00:01,  6.51it/s]
 76%|███████▌  | 38/50 [00:05<00:01,  6.51it/s]
 78%|███████▊  | 39/50 [00:05<00:01,  6.51it/s]
 80%|████████  | 40/50 [00:06<00:01,  6.51it/s]
 82%|████████▏ | 41/50 [00:06<00:01,  6.52it/s]
 84%|████████▍ | 42/50 [00:06<00:01,  6.51it/s]
 86%|████████▌ | 43/50 [00:06<00:01,  6.51it/s]
 88%|████████▊ | 44/50 [00:06<00:00,  6.51it/s]
 90%|█████████ | 45/50 [00:06<00:00,  6.50it/s]
 92%|█████████▏| 46/50 [00:06<00:00,  6.51it/s]
 94%|█████████▍| 47/50 [00:07<00:00,  6.50it/s]
 96%|█████████▌| 48/50 [00:07<00:00,  6.50it/s]
 98%|█████████▊| 49/50 [00:07<00:00,  6.49it/s]
100%|██████████| 50/50 [00:07<00:00,  6.49it/s]
100%|██████████| 50/50 [00:07<00:00,  6.61it/s]