proverbai/ghost_mix_bakedvae | Run with an API on Replicate

proverbai / ghost_mix_bakedvae

Cold

Public
4.3K runs
T4

Iterate in playground

Run with an API

Playground API Examples README Versions

Input

prompt

string

Shift + Return to add a new line

(masterpiece, top quality, best quality, official art, beautiful and aesthetic:1.2), (1girl), extreme detailed,(fractal art:1.3),colorful,highest detailed
(masterpiece, top quality, best quality, official art, beautiful and aesthetic:1.2), (1girl), extreme detailed,(fractal art:1.3),colorful,highest detailed

Input prompt

Default: "a photo of an astronaut riding a horse on mars"

negative_prompt

string

Shift + Return to add a new line

(worst quality, low quality:2), monochrome, zombie,overexposure, watermark,text,bad anatomy,bad hand,extra hands,extra fingers,too many fingers,fused fingers,bad arm,distorted arm,extra arms,fused arms,extra legs,missing leg,disembodied leg,extra nipples, detached arm, liquid hand,inverted hand,disembodied limb, small breasts, loli, oversized head,extra body,completely nude, extra navel,easynegative,(hair between eyes),sketch, duplicate, ugly, huge eyes, text, logo, worst face, (bad and mutated hands:1.3), (blurry:2.0), horror, geometry, bad_prompt, (bad hands), (missing fingers), multiple limbs, bad anatomy, (interlocked fingers:1.2), Ugly Fingers, (extra digit and hands and fingers and legs and arms:1.4), ((2girl)), (deformed fingers:1.2), (long fingers:1.2),(bad-artist-anime), bad-artist, bad hand, extra legs ,(ng_deepnegative_v1_75t)
(worst quality, low quality:2), monochrome, zombie,overexposure, watermark,text,bad anatomy,bad hand,extra hands,extra fingers,too many fingers,fused fingers,bad arm,distorted arm,extra arms,fused arms,extra legs,missing leg,disembodied leg,extra nipples, detached arm, liquid hand,inverted hand,disembodied limb, small breasts, loli, oversized head,extra body,completely nude, extra navel,easynegative,(hair between eyes),sketch, duplicate, ugly, huge eyes, text, logo, worst face, (bad and mutated hands:1.3), (blurry:2.0), horror, geometry, bad_prompt, (bad hands), (missing fingers), multiple limbs, bad anatomy, (interlocked fingers:1.2), Ugly Fingers, (extra digit and hands and fingers and legs and arms:1.4), ((2girl)), (deformed fingers:1.2), (long fingers:1.2),(bad-artist-anime), bad-artist, bad hand, extra legs ,(ng_deepnegative_v1_75t)

Specify things to not see in the output

width

integer

Width of output image. Maximum size is 1024x768 or 768x1024 because of memory limits

Default: 768

height

integer

Height of output image. Maximum size is 1024x768 or 768x1024 because of memory limits

Default: 768

num_outputs

integer

(minimum: 1, maximum: 4)

Number of images to output.

Default: 1

num_inference_steps

integer

(minimum: 1, maximum: 500)

Number of denoising steps

Default: 50

guidance_scale

number

(minimum: 1, maximum: 20)

Scale for classifier-free guidance

Default: 7.5

scheduler

string

Choose a scheduler.

Default: "DPMSolverMultistep"

seed

integer

Random seed. Leave blank to randomize the seed

loraUrl

string

Choose a lora.

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

npx create-replicate --model=proverbai/ghost_mix_bakedvae

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

const output = await replicate.run(
  "proverbai/ghost_mix_bakedvae:6e5ccb6c98714bd56880d89ac956f7dbb2318ca8970cbcd4e4eaea174dd5d8c7",
  {
    input: {
      seed: 1015468391,
      width: 512,
      height: 768,
      prompt: "(masterpiece, top quality, best quality, official art, beautiful and aesthetic:1.2), (1girl), extreme detailed,(fractal art:1.3),colorful,highest detailed\n",
      loraUrl: "AnimeTarot.safetensors",
      scheduler: "DPMSolverMultistep",
      num_outputs: 1,
      guidance_scale: 6,
      negative_prompt: "(worst quality, low quality:2), monochrome, zombie,overexposure, watermark,text,bad anatomy,bad hand,extra hands,extra fingers,too many fingers,fused fingers,bad arm,distorted arm,extra arms,fused arms,extra legs,missing leg,disembodied leg,extra nipples, detached arm, liquid hand,inverted hand,disembodied limb, small breasts, loli, oversized head,extra body,completely nude, extra navel,easynegative,(hair between eyes),sketch, duplicate, ugly, huge eyes, text, logo, worst face, (bad and mutated hands:1.3), (blurry:2.0), horror, geometry, bad_prompt, (bad hands), (missing fingers), multiple limbs, bad anatomy, (interlocked fingers:1.2), Ugly Fingers, (extra digit and hands and fingers and legs and arms:1.4), ((2girl)), (deformed fingers:1.2), (long fingers:1.2),(bad-artist-anime), bad-artist, bad hand, extra legs ,(ng_deepnegative_v1_75t)\n",
      num_inference_steps: 30
    }
  }
);

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

output = replicate.run(
    "proverbai/ghost_mix_bakedvae:6e5ccb6c98714bd56880d89ac956f7dbb2318ca8970cbcd4e4eaea174dd5d8c7",
    input={
        "seed": 1015468391,
        "width": 512,
        "height": 768,
        "prompt": "(masterpiece, top quality, best quality, official art, beautiful and aesthetic:1.2), (1girl), extreme detailed,(fractal art:1.3),colorful,highest detailed\n",
        "loraUrl": "AnimeTarot.safetensors",
        "scheduler": "DPMSolverMultistep",
        "num_outputs": 1,
        "guidance_scale": 6,
        "negative_prompt": "(worst quality, low quality:2), monochrome, zombie,overexposure, watermark,text,bad anatomy,bad hand,extra hands,extra fingers,too many fingers,fused fingers,bad arm,distorted arm,extra arms,fused arms,extra legs,missing leg,disembodied leg,extra nipples, detached arm, liquid hand,inverted hand,disembodied limb, small breasts, loli, oversized head,extra body,completely nude, extra navel,easynegative,(hair between eyes),sketch, duplicate, ugly, huge eyes, text, logo, worst face, (bad and mutated hands:1.3), (blurry:2.0), horror, geometry, bad_prompt, (bad hands), (missing fingers), multiple limbs, bad anatomy, (interlocked fingers:1.2), Ugly Fingers, (extra digit and hands and fingers and legs and arms:1.4), ((2girl)), (deformed fingers:1.2), (long fingers:1.2),(bad-artist-anime), bad-artist, bad hand, extra legs ,(ng_deepnegative_v1_75t)\n",
        "num_inference_steps": 30
    }
)
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 proverbai/ghost_mix_bakedvae 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": "proverbai/ghost_mix_bakedvae:6e5ccb6c98714bd56880d89ac956f7dbb2318ca8970cbcd4e4eaea174dd5d8c7",
    "input": {
      "seed": 1015468391,
      "width": 512,
      "height": 768,
      "prompt": "(masterpiece, top quality, best quality, official art, beautiful and aesthetic:1.2), (1girl), extreme detailed,(fractal art:1.3),colorful,highest detailed\\n",
      "loraUrl": "AnimeTarot.safetensors",
      "scheduler": "DPMSolverMultistep",
      "num_outputs": 1,
      "guidance_scale": 6,
      "negative_prompt": "(worst quality, low quality:2), monochrome, zombie,overexposure, watermark,text,bad anatomy,bad hand,extra hands,extra fingers,too many fingers,fused fingers,bad arm,distorted arm,extra arms,fused arms,extra legs,missing leg,disembodied leg,extra nipples, detached arm, liquid hand,inverted hand,disembodied limb, small breasts, loli, oversized head,extra body,completely nude, extra navel,easynegative,(hair between eyes),sketch, duplicate, ugly, huge eyes, text, logo, worst face, (bad and mutated hands:1.3), (blurry:2.0), horror, geometry, bad_prompt, (bad hands), (missing fingers), multiple limbs, bad anatomy, (interlocked fingers:1.2), Ugly Fingers, (extra digit and hands and fingers and legs and arms:1.4), ((2girl)), (deformed fingers:1.2), (long fingers:1.2),(bad-artist-anime), bad-artist, bad hand, extra legs ,(ng_deepnegative_v1_75t)\\n",
      "num_inference_steps": 30
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2023-06-10T10:14:46.084553Z",
  "created_at": "2023-06-10T10:09:52.819429Z",
  "data_removed": false,
  "error": null,
  "id": "jcoxdjrbwrciaojovpngyxxfni",
  "input": {
    "seed": 1015468391,
    "width": "512",
    "height": 768,
    "prompt": "(masterpiece, top quality, best quality, official art, beautiful and aesthetic:1.2), (1girl), extreme detailed,(fractal art:1.3),colorful,highest detailed\n",
    "scheduler": "DPMSolverMultistep",
    "num_outputs": 1,
    "guidance_scale": 6,
    "negative_prompt": "(worst quality, low quality:2), monochrome, zombie,overexposure, watermark,text,bad anatomy,bad hand,extra hands,extra fingers,too many fingers,fused fingers,bad arm,distorted arm,extra arms,fused arms,extra legs,missing leg,disembodied leg,extra nipples, detached arm, liquid hand,inverted hand,disembodied limb, small breasts, loli, oversized head,extra body,completely nude, extra navel,easynegative,(hair between eyes),sketch, duplicate, ugly, huge eyes, text, logo, worst face, (bad and mutated hands:1.3), (blurry:2.0), horror, geometry, bad_prompt, (bad hands), (missing fingers), multiple limbs, bad anatomy, (interlocked fingers:1.2), Ugly Fingers, (extra digit and hands and fingers and legs and arms:1.4), ((2girl)), (deformed fingers:1.2), (long fingers:1.2),(bad-artist-anime), bad-artist, bad hand, extra legs ,(ng_deepnegative_v1_75t)\n",
    "num_inference_steps": 30
  },
  "logs": "Using seed: 1015468391\nThe config attributes {'dynamic_thresholding_ratio': 0.995, 'sample_max_value': 1.0, 'thresholding': False} were passed to DDIMInverseScheduler, but are not expected and will be ignored. Please verify your scheduler_config.json configuration file.\nThe config attributes {'clip_sample': False, 'clip_sample_range': 1.0, 'dynamic_thresholding_ratio': 0.995, 'sample_max_value': 1.0, 'thresholding': False} were passed to KarrasVeScheduler, but are not expected and will be ignored. Please verify your scheduler_config.json configuration file.\n/root/.pyenv/versions/3.11.1/lib/python3.11/site-packages/diffusers/configuration_utils.py:135: FutureWarning: Accessing config attribute `use_karras_sigmas` directly via 'HeunDiscreteScheduler' object attribute is deprecated. Please access 'use_karras_sigmas' over 'HeunDiscreteScheduler's config object instead, e.g. 'scheduler.config.use_karras_sigmas'.\ndeprecate(\"direct config name access\", \"1.0.0\", deprecation_message, standard_warn=False)\nnone lora\n  0%|          | 0/30 [00:00<?, ?it/s]\n  3%|▎         | 1/30 [00:02<01:20,  2.78s/it]\n  7%|▋         | 2/30 [00:03<00:43,  1.54s/it]\n 10%|█         | 3/30 [00:04<00:31,  1.15s/it]\n 13%|█▎        | 4/30 [00:04<00:25,  1.03it/s]\n 17%|█▋        | 5/30 [00:05<00:21,  1.15it/s]\n 20%|██        | 6/30 [00:06<00:19,  1.24it/s]\n 23%|██▎       | 7/30 [00:06<00:17,  1.30it/s]\n 27%|██▋       | 8/30 [00:07<00:16,  1.34it/s]\n 30%|███       | 9/30 [00:08<00:15,  1.38it/s]\n 33%|███▎      | 10/30 [00:08<00:14,  1.40it/s]\n 37%|███▋      | 11/30 [00:09<00:13,  1.41it/s]\n 40%|████      | 12/30 [00:10<00:12,  1.42it/s]\n 43%|████▎     | 13/30 [00:11<00:11,  1.43it/s]\n 47%|████▋     | 14/30 [00:11<00:11,  1.44it/s]\n 50%|█████     | 15/30 [00:12<00:10,  1.44it/s]\n 53%|█████▎    | 16/30 [00:13<00:09,  1.44it/s]\n 57%|█████▋    | 17/30 [00:13<00:09,  1.44it/s]\n 60%|██████    | 18/30 [00:14<00:08,  1.44it/s]\n 63%|██████▎   | 19/30 [00:15<00:07,  1.44it/s]\n 67%|██████▋   | 20/30 [00:15<00:06,  1.44it/s]\n 70%|███████   | 21/30 [00:16<00:06,  1.44it/s]\n 73%|███████▎  | 22/30 [00:17<00:05,  1.43it/s]\n 77%|███████▋  | 23/30 [00:17<00:04,  1.43it/s]\n 80%|████████  | 24/30 [00:18<00:04,  1.43it/s]\n 83%|████████▎ | 25/30 [00:19<00:03,  1.43it/s]\n 87%|████████▋ | 26/30 [00:20<00:02,  1.43it/s]\n 90%|█████████ | 27/30 [00:20<00:02,  1.43it/s]\n 93%|█████████▎| 28/30 [00:21<00:01,  1.43it/s]\n 97%|█████████▋| 29/30 [00:22<00:00,  1.43it/s]\n100%|██████████| 30/30 [00:22<00:00,  1.42it/s]\n100%|██████████| 30/30 [00:22<00:00,  1.31it/s]",
  "metrics": {
    "predict_time": 26.299823,
    "total_time": 293.265124
  },
  "output": [
    "https://replicate.delivery/pbxt/03Z1FDXbjTJxAV3j9B3rTRgel6vC0NdaCLLBwmypv7zKefIiA/out-0.png"
  ],
  "started_at": "2023-06-10T10:14:19.784730Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/jcoxdjrbwrciaojovpngyxxfni",
    "cancel": "https://api.replicate.com/v1/predictions/jcoxdjrbwrciaojovpngyxxfni/cancel"
  },
  "version": "6e5ccb6c98714bd56880d89ac956f7dbb2318ca8970cbcd4e4eaea174dd5d8c7"
}

Generated in

26.3 seconds

Tweak itReport View full prediction

Using seed: 1015468391
The config attributes {'dynamic_thresholding_ratio': 0.995, 'sample_max_value': 1.0, 'thresholding': False} were passed to DDIMInverseScheduler, but are not expected and will be ignored. Please verify your scheduler_config.json configuration file.
The config attributes {'clip_sample': False, 'clip_sample_range': 1.0, 'dynamic_thresholding_ratio': 0.995, 'sample_max_value': 1.0, 'thresholding': False} were passed to KarrasVeScheduler, but are not expected and will be ignored. Please verify your scheduler_config.json configuration file.
/root/.pyenv/versions/3.11.1/lib/python3.11/site-packages/diffusers/configuration_utils.py:135: FutureWarning: Accessing config attribute `use_karras_sigmas` directly via 'HeunDiscreteScheduler' object attribute is deprecated. Please access 'use_karras_sigmas' over 'HeunDiscreteScheduler's config object instead, e.g. 'scheduler.config.use_karras_sigmas'.
deprecate("direct config name access", "1.0.0", deprecation_message, standard_warn=False)
none lora
  0%|          | 0/30 [00:00<?, ?it/s]
  3%|▎         | 1/30 [00:02<01:20,  2.78s/it]
  7%|▋         | 2/30 [00:03<00:43,  1.54s/it]
 10%|█         | 3/30 [00:04<00:31,  1.15s/it]
 13%|█▎        | 4/30 [00:04<00:25,  1.03it/s]
 17%|█▋        | 5/30 [00:05<00:21,  1.15it/s]
 20%|██        | 6/30 [00:06<00:19,  1.24it/s]
 23%|██▎       | 7/30 [00:06<00:17,  1.30it/s]
 27%|██▋       | 8/30 [00:07<00:16,  1.34it/s]
 30%|███       | 9/30 [00:08<00:15,  1.38it/s]
 33%|███▎      | 10/30 [00:08<00:14,  1.40it/s]
 37%|███▋      | 11/30 [00:09<00:13,  1.41it/s]
 40%|████      | 12/30 [00:10<00:12,  1.42it/s]
 43%|████▎     | 13/30 [00:11<00:11,  1.43it/s]
 47%|████▋     | 14/30 [00:11<00:11,  1.44it/s]
 50%|█████     | 15/30 [00:12<00:10,  1.44it/s]
 53%|█████▎    | 16/30 [00:13<00:09,  1.44it/s]
 57%|█████▋    | 17/30 [00:13<00:09,  1.44it/s]
 60%|██████    | 18/30 [00:14<00:08,  1.44it/s]
 63%|██████▎   | 19/30 [00:15<00:07,  1.44it/s]
 67%|██████▋   | 20/30 [00:15<00:06,  1.44it/s]
 70%|███████   | 21/30 [00:16<00:06,  1.44it/s]
 73%|███████▎  | 22/30 [00:17<00:05,  1.43it/s]
 77%|███████▋  | 23/30 [00:17<00:04,  1.43it/s]
 80%|████████  | 24/30 [00:18<00:04,  1.43it/s]
 83%|████████▎ | 25/30 [00:19<00:03,  1.43it/s]
 87%|████████▋ | 26/30 [00:20<00:02,  1.43it/s]
 90%|█████████ | 27/30 [00:20<00:02,  1.43it/s]
 93%|█████████▎| 28/30 [00:21<00:01,  1.43it/s]
 97%|█████████▋| 29/30 [00:22<00:00,  1.43it/s]
100%|██████████| 30/30 [00:22<00:00,  1.42it/s]
100%|██████████| 30/30 [00:22<00:00,  1.31it/s]

Examples

View more examples

Run time and cost

This model costs approximately $0.045 to run on Replicate, or 22 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 T4 GPU hardware. Predictions typically complete within 4 minutes. The predict time for this model varies significantly based on the inputs.

Readme

This model doesn't have a readme.