omniedgeio/aquaaibase – Run with an API on Replicate

omniedgeio / aquaaibase

Model

Cold

Public
412 runs
A100 (80GB)

Iterate in playground

Run with an API

Playground API Examples Train README Versions

Input

prompt

string

Shift + Return to add a new line

The woman in the photo is wearing a blue dress and standing in a white room. She looks elegant and sophisticated, with her posture and outfit drawing attention. The white room serves as a simple and clean background for her attire.The lighting is bright and natural, realist detail, ue5, detailed character expressions, amazing quality, wallpaper, analog film grain. one person, 8k. In the style of EveningDressDFThe woman in the photo is wearing a blue dress and standing in a white room. She looks elegant and sophisticated, with her posture and outfit drawing attention. The white room serves as a simple and clean background for her attire.The lighting is bright and natural, realist detail, ue5, detailed character expressions, amazing quality, wallpaper, analog film grain. one person, 8k. In the style of EveningDressDF

Input prompt

Default: "An astronaut riding a rainbow unicorn"

negative_prompt

string

Shift + Return to add a new line

cropped face, cover face, cover visage, mutated hands, bad anatomy, bad hands, three hands, three legs, bad arms,(missing legs), missing arms, poorly drawn face, bad face, fused face, cloned face, worst face, three crus, extra crus, fused crus, worst feet, three feet, fused feet, fused thigh, three thigh, fused thigh, extra thigh, worst thigh, missing fingers, extra fingers, ugly fingers, long fingers, horn, extra eyes, huge eyes, 2girl, amputation, disconnected limbs, cartoon, cg, 3d, unreal, animate, not human, no head,(low quality, worst quality:1.4), cgi,  text, signature, watermark, extra limbs, cleavagecropped face, cover face, cover visage, mutated hands, bad anatomy, bad hands, three hands, three legs, bad arms,(missing legs), missing arms, poorly drawn face, bad face, fused face, cloned face, worst face, three crus, extra crus, fused crus, worst feet, three feet, fused feet, fused thigh, three thigh, fused thigh, extra thigh, worst thigh, missing fingers, extra fingers, ugly fingers, long fingers, horn, extra eyes, huge eyes, 2girl, amputation, disconnected limbs, cartoon, cg, 3d, unreal, animate, not human, no head,(low quality, worst quality:1.4), cgi,  text, signature, watermark, extra limbs, cleavage

Input Negative Prompt

Default: ""

image

file

Input image for img2img or inpaint mode

mask

file

Input mask for inpaint mode. Black areas will be preserved, white areas will be inpainted.

img2img

boolean

Use img2img pipeline, it will use the image input both as the control image and the base image.

controlnet

boolean

controlnet

condition_scale

number

(minimum: 0, maximum: 2)

The bigger this number is, the more ControlNet interferes

Default: 1.1

strength

number

(minimum: 0, maximum: 1)

When img2img is active, the denoising strength. 1 means total destruction of the input image.

Default: 0.8

width

integer

Width of output image

Default: 1024

height

integer

Height of output image

Default: 1024

num_outputs

integer

(minimum: 1, maximum: 4)

Number of images to output.

Default: 1

hdr

number

(minimum: 0, maximum: 1)

HDR improvement over the original image

Default: 0

scheduler

string

scheduler

Default: "K_EULER"

num_inference_steps

integer

(minimum: 1, maximum: 500)

Number of denoising steps

Default: 50

guidance_scale

number

(minimum: 1, maximum: 50)

Scale for classifier-free guidance

Default: 7.5

prompt_strength

number

(minimum: 0, maximum: 1)

Prompt strength when using img2img / inpaint. 1.0 corresponds to full destruction of information in image

Default: 0.8

seed

integer

Random seed. Leave blank to randomize the seed

refine

string

Which refine style to use

Default: "no_refiner"

high_noise_frac

number

(minimum: 0, maximum: 1)

For expert_ensemble_refiner, the fraction of noise to use

Default: 0.8

refine_steps

integer

For base_image_refiner, the number of steps to refine, defaults to num_inference_steps

Default: 10

apply_watermark

boolean

Applies a watermark to enable determining if an image is generated in downstream applications. If you have other provisions for generating or deploying images safely, you can use this to disable watermarking.

Default: true

lora_scale

number

(minimum: 0, maximum: 1)

LoRA additive scale. Only applicable on trained models.

Default: 0.6

disable_safety_checker

boolean

Disable safety checker for generated images. This feature is only available through the API. See [https://replicate.com/docs/how-does-replicate-work#safety](https://replicate.com/docs/how-does-replicate-work#safety)

Default: true

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

npx create-replicate --model=omniedgeio/aquaaibase

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

const output = await replicate.run(
  "omniedgeio/aquaaibase:905504d6a9a49716e92bb519c91494912dfb5dec43e20277679dfdbee0907bef",
  {
    input: {
      hdr: 0,
      width: 640,
      height: 840,
      prompt: "The woman in the photo is wearing a blue dress and standing in a white room. She looks elegant and sophisticated, with her posture and outfit drawing attention. The white room serves as a simple and clean background for her attire.The lighting is bright and natural, realist detail, ue5, detailed character expressions, amazing quality, wallpaper, analog film grain. one person, 8k. In the style of EveningDressDF",
      refine: "base_image_refiner",
      strength: 0.8,
      scheduler: "K_EULER_ANCESTRAL",
      lora_scale: 0.6,
      num_outputs: 1,
      refine_steps: 10,
      guidance_scale: 7.5,
      apply_watermark: false,
      condition_scale: 1.1,
      high_noise_frac: 0.8,
      negative_prompt: "cropped face, cover face, cover visage, mutated hands, bad anatomy, bad hands, three hands, three legs, bad arms,(missing legs), missing arms, poorly drawn face, bad face, fused face, cloned face, worst face, three crus, extra crus, fused crus, worst feet, three feet, fused feet, fused thigh, three thigh, fused thigh, extra thigh, worst thigh, missing fingers, extra fingers, ugly fingers, long fingers, horn, extra eyes, huge eyes, 2girl, amputation, disconnected limbs, cartoon, cg, 3d, unreal, animate, not human, no head,(low quality, worst quality:1.4), cgi,  text, signature, watermark, extra limbs, cleavage",
      prompt_strength: 0.8,
      num_inference_steps: 50
    }
  }
);

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

output = replicate.run(
    "omniedgeio/aquaaibase:905504d6a9a49716e92bb519c91494912dfb5dec43e20277679dfdbee0907bef",
    input={
        "hdr": 0,
        "width": 640,
        "height": 840,
        "prompt": "The woman in the photo is wearing a blue dress and standing in a white room. She looks elegant and sophisticated, with her posture and outfit drawing attention. The white room serves as a simple and clean background for her attire.The lighting is bright and natural, realist detail, ue5, detailed character expressions, amazing quality, wallpaper, analog film grain. one person, 8k. In the style of EveningDressDF",
        "refine": "base_image_refiner",
        "strength": 0.8,
        "scheduler": "K_EULER_ANCESTRAL",
        "lora_scale": 0.6,
        "num_outputs": 1,
        "refine_steps": 10,
        "guidance_scale": 7.5,
        "apply_watermark": False,
        "condition_scale": 1.1,
        "high_noise_frac": 0.8,
        "negative_prompt": "cropped face, cover face, cover visage, mutated hands, bad anatomy, bad hands, three hands, three legs, bad arms,(missing legs), missing arms, poorly drawn face, bad face, fused face, cloned face, worst face, three crus, extra crus, fused crus, worst feet, three feet, fused feet, fused thigh, three thigh, fused thigh, extra thigh, worst thigh, missing fingers, extra fingers, ugly fingers, long fingers, horn, extra eyes, huge eyes, 2girl, amputation, disconnected limbs, cartoon, cg, 3d, unreal, animate, not human, no head,(low quality, worst quality:1.4), cgi,  text, signature, watermark, extra limbs, cleavage",
        "prompt_strength": 0.8,
        "num_inference_steps": 50
    }
)
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 omniedgeio/aquaaibase 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": "omniedgeio/aquaaibase:905504d6a9a49716e92bb519c91494912dfb5dec43e20277679dfdbee0907bef",
    "input": {
      "hdr": 0,
      "width": 640,
      "height": 840,
      "prompt": "The woman in the photo is wearing a blue dress and standing in a white room. She looks elegant and sophisticated, with her posture and outfit drawing attention. The white room serves as a simple and clean background for her attire.The lighting is bright and natural, realist detail, ue5, detailed character expressions, amazing quality, wallpaper, analog film grain. one person, 8k. In the style of EveningDressDF",
      "refine": "base_image_refiner",
      "strength": 0.8,
      "scheduler": "K_EULER_ANCESTRAL",
      "lora_scale": 0.6,
      "num_outputs": 1,
      "refine_steps": 10,
      "guidance_scale": 7.5,
      "apply_watermark": false,
      "condition_scale": 1.1,
      "high_noise_frac": 0.8,
      "negative_prompt": "cropped face, cover face, cover visage, mutated hands, bad anatomy, bad hands, three hands, three legs, bad arms,(missing legs), missing arms, poorly drawn face, bad face, fused face, cloned face, worst face, three crus, extra crus, fused crus, worst feet, three feet, fused feet, fused thigh, three thigh, fused thigh, extra thigh, worst thigh, missing fingers, extra fingers, ugly fingers, long fingers, horn, extra eyes, huge eyes, 2girl, amputation, disconnected limbs, cartoon, cg, 3d, unreal, animate, not human, no head,(low quality, worst quality:1.4), cgi,  text, signature, watermark, extra limbs, cleavage",
      "prompt_strength": 0.8,
      "num_inference_steps": 50
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

out-0.png

{
  "completed_at": "2024-03-17T09:00:51.430850Z",
  "created_at": "2024-03-17T08:59:16.432454Z",
  "data_removed": false,
  "error": null,
  "id": "mhsoi4lbyzfbkqzd5duwz74zxq",
  "input": {
    "width": 640,
    "height": 840,
    "prompt": "The woman in the photo is wearing a blue dress and standing in a white room. She looks elegant and sophisticated, with her posture and outfit drawing attention. The white room serves as a simple and clean background for her attire.The lighting is bright and natural, realist detail, ue5, detailed character expressions, amazing quality, wallpaper, analog film grain. one person, 8k. In the style of EveningDressDF",
    "refine": "base_image_refiner",
    "scheduler": "K_EULER_ANCESTRAL",
    "apply_watermark": false,
    "negative_prompt": "cropped face, cover face, cover visage, mutated hands, bad anatomy, bad hands, three hands, three legs, bad arms,(missing legs), missing arms, poorly drawn face, bad face, fused face, cloned face, worst face, three crus, extra crus, fused crus, worst feet, three feet, fused feet, fused thigh, three thigh, fused thigh, extra thigh, worst thigh, missing fingers, extra fingers, ugly fingers, long fingers, horn, extra eyes, huge eyes, 2girl, amputation, disconnected limbs, cartoon, cg, 3d, unreal, animate, not human, no head,(low quality, worst quality:1.4), cgi,  text, signature, watermark, extra limbs, cleavage",
    "disable_safety_checker": true
  },
  "logs": "Using seed: 65503\nEnsuring enough disk space...\nFree disk space: 818957369344\nDownloading weights: https://replicate.delivery/pbxt/UP69cUtnOWL6LB8aoHYp5M5AJyfLFoW1gfREoHNzrglQ6BhSA/trained_model.tar\n2024-03-17T09:00:36Z | INFO  | [ Initiating ] dest=/src/weights-cache/62014fdd81e3f2bc minimum_chunk_size=150M url=https://replicate.delivery/pbxt/UP69cUtnOWL6LB8aoHYp5M5AJyfLFoW1gfREoHNzrglQ6BhSA/trained_model.tar\n2024-03-17T09:00:41Z | INFO  | [ Complete ] dest=/src/weights-cache/62014fdd81e3f2bc size=\"186 MB\" total_elapsed=4.852s url=https://replicate.delivery/pbxt/UP69cUtnOWL6LB8aoHYp5M5AJyfLFoW1gfREoHNzrglQ6BhSA/trained_model.tar\nb''\nDownloaded weights in 4.9480156898498535 seconds\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: The woman in the photo is wearing a blue dress and standing in a white room. She looks elegant and sophisticated, with her posture and outfit drawing attention. The white room serves as a simple and clean background for her attire.The lighting is bright and natural, realist detail, ue5, detailed character expressions, amazing quality, wallpaper, analog film grain. one person, 8k. In the style of EveningDressDF\ntxt2img mode\nToken indices sequence length is longer than the specified maximum sequence length for this model (86 > 77). Running this sequence through the model will result in indexing errors\nThe following part of your input was truncated because CLIP can only handle sequences up to 77 tokens: ['k. in the style of eveningdressdf']\nToken indices sequence length is longer than the specified maximum sequence length for this model (86 > 77). Running this sequence through the model will result in indexing errors\nThe following part of your input was truncated because CLIP can only handle sequences up to 77 tokens: ['k. in the style of eveningdressdf']\n  0%|          | 0/50 [00:00<?, ?it/s]\n  2%|▏         | 1/50 [00:00<00:38,  1.26it/s]\n  4%|▍         | 2/50 [00:00<00:18,  2.56it/s]\n  6%|▌         | 3/50 [00:01<00:12,  3.83it/s]\n  8%|▊         | 4/50 [00:01<00:09,  5.00it/s]\n 10%|█         | 5/50 [00:01<00:07,  6.02it/s]\n 12%|█▏        | 6/50 [00:01<00:06,  6.82it/s]\n 14%|█▍        | 7/50 [00:01<00:05,  7.48it/s]\n 16%|█▌        | 8/50 [00:01<00:05,  7.99it/s]\n 18%|█▊        | 9/50 [00:01<00:04,  8.36it/s]\n 20%|██        | 10/50 [00:01<00:04,  8.65it/s]\n 22%|██▏       | 11/50 [00:01<00:04,  8.87it/s]\n 24%|██▍       | 12/50 [00:01<00:04,  9.03it/s]\n 26%|██▌       | 13/50 [00:02<00:04,  9.15it/s]\n 28%|██▊       | 14/50 [00:02<00:03,  9.11it/s]\n 30%|███       | 15/50 [00:02<00:03,  9.16it/s]\n 32%|███▏      | 16/50 [00:02<00:03,  9.19it/s]\n 34%|███▍      | 17/50 [00:02<00:03,  9.22it/s]\n 36%|███▌      | 18/50 [00:02<00:03,  9.26it/s]\n 38%|███▊      | 19/50 [00:02<00:03,  9.28it/s]\n 40%|████      | 20/50 [00:02<00:03,  9.30it/s]\n 42%|████▏     | 21/50 [00:02<00:03,  9.33it/s]\n 44%|████▍     | 22/50 [00:03<00:03,  9.27it/s]\n 46%|████▌     | 23/50 [00:03<00:02,  9.29it/s]\n 48%|████▊     | 24/50 [00:03<00:02,  9.32it/s]\n 50%|█████     | 25/50 [00:03<00:02,  9.31it/s]\n 52%|█████▏    | 26/50 [00:03<00:02,  9.32it/s]\n 54%|█████▍    | 27/50 [00:03<00:02,  9.33it/s]\n 56%|█████▌    | 28/50 [00:03<00:02,  9.31it/s]\n 58%|█████▊    | 29/50 [00:03<00:02,  9.30it/s]\n 60%|██████    | 30/50 [00:03<00:02,  9.25it/s]\n 62%|██████▏   | 31/50 [00:04<00:02,  9.26it/s]\n 64%|██████▍   | 32/50 [00:04<00:01,  9.28it/s]\n 66%|██████▌   | 33/50 [00:04<00:01,  9.28it/s]\n 68%|██████▊   | 34/50 [00:04<00:01,  9.28it/s]\n 70%|███████   | 35/50 [00:04<00:01,  9.29it/s]\n 72%|███████▏  | 36/50 [00:04<00:01,  9.29it/s]\n 74%|███████▍  | 37/50 [00:04<00:01,  9.24it/s]\n 76%|███████▌  | 38/50 [00:04<00:01,  9.23it/s]\n 78%|███████▊  | 39/50 [00:04<00:01,  9.24it/s]\n 80%|████████  | 40/50 [00:04<00:01,  9.26it/s]\n 82%|████████▏ | 41/50 [00:05<00:00,  9.27it/s]\n 84%|████████▍ | 42/50 [00:05<00:00,  9.26it/s]\n 86%|████████▌ | 43/50 [00:05<00:00,  9.26it/s]\n 88%|████████▊ | 44/50 [00:05<00:00,  9.27it/s]\n 90%|█████████ | 45/50 [00:05<00:00,  9.28it/s]\n 92%|█████████▏| 46/50 [00:05<00:00,  9.29it/s]\n 94%|█████████▍| 47/50 [00:05<00:00,  9.29it/s]\n 96%|█████████▌| 48/50 [00:05<00:00,  9.25it/s]\n 98%|█████████▊| 49/50 [00:05<00:00,  9.25it/s]\n100%|██████████| 50/50 [00:06<00:00,  9.25it/s]\n100%|██████████| 50/50 [00:06<00:00,  8.24it/s]\nToken indices sequence length is longer than the specified maximum sequence length for this model (86 > 77). Running this sequence through the model will result in indexing errors\nThe following part of your input was truncated because CLIP can only handle sequences up to 77 tokens: ['k. in the style of eveningdressdf']\n  0%|          | 0/15 [00:00<?, ?it/s]\n  7%|▋         | 1/15 [00:00<00:01,  9.75it/s]\n 20%|██        | 3/15 [00:00<00:00, 13.17it/s]\n 33%|███▎      | 5/15 [00:00<00:00, 14.04it/s]\n 47%|████▋     | 7/15 [00:00<00:00, 14.38it/s]\n 60%|██████    | 9/15 [00:00<00:00, 14.59it/s]\n 73%|███████▎  | 11/15 [00:00<00:00, 14.72it/s]\n 87%|████████▋ | 13/15 [00:00<00:00, 14.81it/s]\n100%|██████████| 15/15 [00:01<00:00, 14.85it/s]\n100%|██████████| 15/15 [00:01<00:00, 14.44it/s]",
  "metrics": {
    "predict_time": 15.137104,
    "total_time": 94.998396
  },
  "output": [
    "https://replicate.delivery/pbxt/a4kBibUqVjaoL1TwYLR4res2epkWzmKBG4SwM9wQLehEaMClA/out-0.png"
  ],
  "started_at": "2024-03-17T09:00:36.293746Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/mhsoi4lbyzfbkqzd5duwz74zxq",
    "cancel": "https://api.replicate.com/v1/predictions/mhsoi4lbyzfbkqzd5duwz74zxq/cancel"
  },
  "version": "59583f621010a8034d8eac35efbd4aeb4040477398c4a75cb8de5f5772b2aac4"
}

Generated in

15.1 seconds

Tweak itReport

Using seed: 65503
Ensuring enough disk space...
Free disk space: 818957369344
Downloading weights: https://replicate.delivery/pbxt/UP69cUtnOWL6LB8aoHYp5M5AJyfLFoW1gfREoHNzrglQ6BhSA/trained_model.tar
2024-03-17T09:00:36Z | INFO  | [ Initiating ] dest=/src/weights-cache/62014fdd81e3f2bc minimum_chunk_size=150M url=https://replicate.delivery/pbxt/UP69cUtnOWL6LB8aoHYp5M5AJyfLFoW1gfREoHNzrglQ6BhSA/trained_model.tar
2024-03-17T09:00:41Z | INFO  | [ Complete ] dest=/src/weights-cache/62014fdd81e3f2bc size="186 MB" total_elapsed=4.852s url=https://replicate.delivery/pbxt/UP69cUtnOWL6LB8aoHYp5M5AJyfLFoW1gfREoHNzrglQ6BhSA/trained_model.tar
b''
Downloaded weights in 4.9480156898498535 seconds
Loading fine-tuned model
Does not have Unet. assume we are using LoRA
Loading Unet LoRA
Prompt: The woman in the photo is wearing a blue dress and standing in a white room. She looks elegant and sophisticated, with her posture and outfit drawing attention. The white room serves as a simple and clean background for her attire.The lighting is bright and natural, realist detail, ue5, detailed character expressions, amazing quality, wallpaper, analog film grain. one person, 8k. In the style of EveningDressDF
txt2img mode
Token indices sequence length is longer than the specified maximum sequence length for this model (86 > 77). Running this sequence through the model will result in indexing errors
The following part of your input was truncated because CLIP can only handle sequences up to 77 tokens: ['k. in the style of eveningdressdf']
Token indices sequence length is longer than the specified maximum sequence length for this model (86 > 77). Running this sequence through the model will result in indexing errors
The following part of your input was truncated because CLIP can only handle sequences up to 77 tokens: ['k. in the style of eveningdressdf']
  0%|          | 0/50 [00:00<?, ?it/s]
  2%|▏         | 1/50 [00:00<00:38,  1.26it/s]
  4%|▍         | 2/50 [00:00<00:18,  2.56it/s]
  6%|▌         | 3/50 [00:01<00:12,  3.83it/s]
  8%|▊         | 4/50 [00:01<00:09,  5.00it/s]
 10%|█         | 5/50 [00:01<00:07,  6.02it/s]
 12%|█▏        | 6/50 [00:01<00:06,  6.82it/s]
 14%|█▍        | 7/50 [00:01<00:05,  7.48it/s]
 16%|█▌        | 8/50 [00:01<00:05,  7.99it/s]
 18%|█▊        | 9/50 [00:01<00:04,  8.36it/s]
 20%|██        | 10/50 [00:01<00:04,  8.65it/s]
 22%|██▏       | 11/50 [00:01<00:04,  8.87it/s]
 24%|██▍       | 12/50 [00:01<00:04,  9.03it/s]
 26%|██▌       | 13/50 [00:02<00:04,  9.15it/s]
 28%|██▊       | 14/50 [00:02<00:03,  9.11it/s]
 30%|███       | 15/50 [00:02<00:03,  9.16it/s]
 32%|███▏      | 16/50 [00:02<00:03,  9.19it/s]
 34%|███▍      | 17/50 [00:02<00:03,  9.22it/s]
 36%|███▌      | 18/50 [00:02<00:03,  9.26it/s]
 38%|███▊      | 19/50 [00:02<00:03,  9.28it/s]
 40%|████      | 20/50 [00:02<00:03,  9.30it/s]
 42%|████▏     | 21/50 [00:02<00:03,  9.33it/s]
 44%|████▍     | 22/50 [00:03<00:03,  9.27it/s]
 46%|████▌     | 23/50 [00:03<00:02,  9.29it/s]
 48%|████▊     | 24/50 [00:03<00:02,  9.32it/s]
 50%|█████     | 25/50 [00:03<00:02,  9.31it/s]
 52%|█████▏    | 26/50 [00:03<00:02,  9.32it/s]
 54%|█████▍    | 27/50 [00:03<00:02,  9.33it/s]
 56%|█████▌    | 28/50 [00:03<00:02,  9.31it/s]
 58%|█████▊    | 29/50 [00:03<00:02,  9.30it/s]
 60%|██████    | 30/50 [00:03<00:02,  9.25it/s]
 62%|██████▏   | 31/50 [00:04<00:02,  9.26it/s]
 64%|██████▍   | 32/50 [00:04<00:01,  9.28it/s]
 66%|██████▌   | 33/50 [00:04<00:01,  9.28it/s]
 68%|██████▊   | 34/50 [00:04<00:01,  9.28it/s]
 70%|███████   | 35/50 [00:04<00:01,  9.29it/s]
 72%|███████▏  | 36/50 [00:04<00:01,  9.29it/s]
 74%|███████▍  | 37/50 [00:04<00:01,  9.24it/s]
 76%|███████▌  | 38/50 [00:04<00:01,  9.23it/s]
 78%|███████▊  | 39/50 [00:04<00:01,  9.24it/s]
 80%|████████  | 40/50 [00:04<00:01,  9.26it/s]
 82%|████████▏ | 41/50 [00:05<00:00,  9.27it/s]
 84%|████████▍ | 42/50 [00:05<00:00,  9.26it/s]
 86%|████████▌ | 43/50 [00:05<00:00,  9.26it/s]
 88%|████████▊ | 44/50 [00:05<00:00,  9.27it/s]
 90%|█████████ | 45/50 [00:05<00:00,  9.28it/s]
 92%|█████████▏| 46/50 [00:05<00:00,  9.29it/s]
 94%|█████████▍| 47/50 [00:05<00:00,  9.29it/s]
 96%|█████████▌| 48/50 [00:05<00:00,  9.25it/s]
 98%|█████████▊| 49/50 [00:05<00:00,  9.25it/s]
100%|██████████| 50/50 [00:06<00:00,  9.25it/s]
100%|██████████| 50/50 [00:06<00:00,  8.24it/s]
Token indices sequence length is longer than the specified maximum sequence length for this model (86 > 77). Running this sequence through the model will result in indexing errors
The following part of your input was truncated because CLIP can only handle sequences up to 77 tokens: ['k. in the style of eveningdressdf']
  0%|          | 0/15 [00:00<?, ?it/s]
  7%|▋         | 1/15 [00:00<00:01,  9.75it/s]
 20%|██        | 3/15 [00:00<00:00, 13.17it/s]
 33%|███▎      | 5/15 [00:00<00:00, 14.04it/s]
 47%|████▋     | 7/15 [00:00<00:00, 14.38it/s]
 60%|██████    | 9/15 [00:00<00:00, 14.59it/s]
 73%|███████▎  | 11/15 [00:00<00:00, 14.72it/s]
 87%|████████▋ | 13/15 [00:00<00:00, 14.81it/s]
100%|██████████| 15/15 [00:01<00:00, 14.85it/s]
100%|██████████| 15/15 [00:01<00:00, 14.44it/s]

This output was created using a different version of the model, omniedgeio/aquaaibase:59583f62.

Examples

View more examples

Run time and cost

This model runs on Nvidia A100 (80GB) GPU hardware. We don't yet have enough runs of this model to provide performance information.

Readme

This model doesn't have a readme.