zhouzhengjun/realistic – Run with an API on Replicate

zhouzhengjun / realistic

观照AI

Cold

Public
5.1K runs
T4

Run with an API

Playground API Examples README Versions

Input

prompt

string

Shift + Return to add a new line

(((masterpiece))),(((bestquality))),((ultra-detailed)),(illustration),((anextremelydelicateandbeautiful)),dynamicangle,floating,(beautifuldetailedeyes),(detailedlight) (1girl), solo , floating_hair,glowingeyes,green hair,greeneyes <1>, twintails, halterdress,(((masterpiece))),(((bestquality))),((ultra-detailed)),(illustration),((anextremelydelicateandbeautiful)),dynamicangle,floating,(beautifuldetailedeyes),(detailedlight) (1girl), solo , floating_hair,glowingeyes,green hair,greeneyes <1>, twintails, halterdress,

Input prompt. Use <1>, <2>, <3>, etc., to specify LoRA concepts

Default: "a photo of <1> riding a horse on mars"

negative_prompt

string

Shift + Return to add a new line

multiple head, lowres, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, watermark, blurry, multiple girls, multiple faces, canvas frame, cartoon, ((multiple head)), ((bad art)), ((extra limbs)), ((b&w)), wierd colors, (((duplicate))), ((morbid)), ((mutilated)), extra fingers, mutated hands, ((poorly drawn hands)), ((poorly drawn face)), (((mutation))), (((deformed))), ((ugly)), ((bad anatomy)), (((bad proportions))), cloned face, (((disfigured))), out of frame, gross proportions, (malformed limbs), ((missing arms)), ((missing legs)), (((extra arms))), (((extra legs))), (fused fingers), (too many fingers), (((long neck))), video game, tiling, poorly drawn feet, mutated, cross-eye, body out of frame, Humpbacked, shadow, nude, naked, NSFW, bad quality, low quality, fused fingers, poorly drawn face, too many fingersmultiple head, lowres, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, watermark, blurry, multiple girls, multiple faces, canvas frame, cartoon, ((multiple head)), ((bad art)), ((extra limbs)), ((b&w)), wierd colors, (((duplicate))), ((morbid)), ((mutilated)), extra fingers, mutated hands, ((poorly drawn hands)), ((poorly drawn face)), (((mutation))), (((deformed))), ((ugly)), ((bad anatomy)), (((bad proportions))), cloned face, (((disfigured))), out of frame, gross proportions, (malformed limbs), ((missing arms)), ((missing legs)), (((extra arms))), (((extra legs))), (fused fingers), (too many fingers), (((long neck))), video game, tiling, poorly drawn feet, mutated, cross-eye, body out of frame, Humpbacked, shadow, nude, naked, NSFW, bad quality, low quality, fused fingers, poorly drawn face, too many fingers

Specify things to not see in the output

Default: ""

width

integer

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

Default: 512

height

integer

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

Default: 512

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

image

file

(Img2Img) Inital image to generate variations of. If this is not none, Img2Img will be invoked.

prompt_strength

number

(Img2Img) Prompt strength when providing the image. 1.0 corresponds to full destruction of information in init image

Default: 0.8

scheduler

string

Choose a scheduler.

Default: "DPMSolverMultistep"

lora_urls

string

Shift + Return to add a new line

https://replicate.delivery/pbxt/Mf7QBwNXrehQ3k6GwMPpi8bqy0cer9x1NqogXVWylWC9l6YhA/tmp28kwa2ceclexz5tc90001zun1iy5b8x3wzip.safetensorshttps://replicate.delivery/pbxt/Mf7QBwNXrehQ3k6GwMPpi8bqy0cer9x1NqogXVWylWC9l6YhA/tmp28kwa2ceclexz5tc90001zun1iy5b8x3wzip.safetensors

List of urls for safetensors of lora models, seperated with | .

Default: ""

lora_scales

string

Shift + Return to add a new line

List of scales for safetensors of lora models, seperated with |

Default: "0.5"

seed

integer

Random seed. Leave blank to randomize the seed

adapter_condition_image

file

(T2I-adapter) Adapter Condition Image to gain extra control over generation. If this is not none, T2I adapter will be invoked. Width, Height of this image must match the above parameter, or dimension of the Img2Img image.

adapter_type

string

(T2I-adapter) Choose an adapter type for the additional condition.

Default: "sketch"

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

npx create-replicate --model=zhouzhengjun/realistic

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

const output = await replicate.run(
  "zhouzhengjun/realistic:9475aa3102d1be01bbf84cd88cc4ac5c85d037b5ff37e7a0f973ebbf81f409d7",
  {
    input: {
      width: 768,
      height: 768,
      prompt: "(((masterpiece))),(((bestquality))),((ultra-detailed)),(illustration),((anextremelydelicateandbeautiful)),dynamicangle,floating,(beautifuldetailedeyes),(detailedlight) (1girl), solo , floating_hair,glowingeyes,green hair,greeneyes <1>, twintails, halterdress,",
      lora_urls: "https://replicate.delivery/pbxt/Mf7QBwNXrehQ3k6GwMPpi8bqy0cer9x1NqogXVWylWC9l6YhA/tmp28kwa2ceclexz5tc90001zun1iy5b8x3wzip.safetensors",
      scheduler: "K_EULER_ANCESTRAL",
      lora_scales: "0.8",
      num_outputs: 1,
      adapter_type: "sketch",
      guidance_scale: 3.62,
      negative_prompt: "multiple head, lowres, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, watermark, blurry, multiple girls, multiple faces, canvas frame, cartoon, ((multiple head)), ((bad art)), ((extra limbs)), ((b&w)), wierd colors, (((duplicate))), ((morbid)), ((mutilated)), extra fingers, mutated hands, ((poorly drawn hands)), ((poorly drawn face)), (((mutation))), (((deformed))), ((ugly)), ((bad anatomy)), (((bad proportions))), cloned face, (((disfigured))), out of frame, gross proportions, (malformed limbs), ((missing arms)), ((missing legs)), (((extra arms))), (((extra legs))), (fused fingers), (too many fingers), (((long neck))), video game, tiling, poorly drawn feet, mutated, cross-eye, body out of frame, Humpbacked, shadow, nude, naked, NSFW, bad quality, low quality, fused fingers, poorly drawn face, too many fingers",
      prompt_strength: 0.8,
      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 zhouzhengjun/realistic using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "zhouzhengjun/realistic:9475aa3102d1be01bbf84cd88cc4ac5c85d037b5ff37e7a0f973ebbf81f409d7",
    input={
        "width": 768,
        "height": 768,
        "prompt": "(((masterpiece))),(((bestquality))),((ultra-detailed)),(illustration),((anextremelydelicateandbeautiful)),dynamicangle,floating,(beautifuldetailedeyes),(detailedlight) (1girl), solo , floating_hair,glowingeyes,green hair,greeneyes <1>, twintails, halterdress,",
        "lora_urls": "https://replicate.delivery/pbxt/Mf7QBwNXrehQ3k6GwMPpi8bqy0cer9x1NqogXVWylWC9l6YhA/tmp28kwa2ceclexz5tc90001zun1iy5b8x3wzip.safetensors",
        "scheduler": "K_EULER_ANCESTRAL",
        "lora_scales": "0.8",
        "num_outputs": 1,
        "adapter_type": "sketch",
        "guidance_scale": 3.62,
        "negative_prompt": "multiple head, lowres, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, watermark, blurry, multiple girls, multiple faces, canvas frame, cartoon, ((multiple head)), ((bad art)), ((extra limbs)), ((b&w)), wierd colors, (((duplicate))), ((morbid)), ((mutilated)), extra fingers, mutated hands, ((poorly drawn hands)), ((poorly drawn face)), (((mutation))), (((deformed))), ((ugly)), ((bad anatomy)), (((bad proportions))), cloned face, (((disfigured))), out of frame, gross proportions, (malformed limbs), ((missing arms)), ((missing legs)), (((extra arms))), (((extra legs))), (fused fingers), (too many fingers), (((long neck))), video game, tiling, poorly drawn feet, mutated, cross-eye, body out of frame, Humpbacked, shadow, nude, naked, NSFW, bad quality, low quality, fused fingers, poorly drawn face, too many fingers",
        "prompt_strength": 0.8,
        "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 zhouzhengjun/realistic 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": "9475aa3102d1be01bbf84cd88cc4ac5c85d037b5ff37e7a0f973ebbf81f409d7",
    "input": {
      "width": 768,
      "height": 768,
      "prompt": "(((masterpiece))),(((bestquality))),((ultra-detailed)),(illustration),((anextremelydelicateandbeautiful)),dynamicangle,floating,(beautifuldetailedeyes),(detailedlight) (1girl), solo , floating_hair,glowingeyes,green hair,greeneyes <1>, twintails, halterdress,",
      "lora_urls": "https://replicate.delivery/pbxt/Mf7QBwNXrehQ3k6GwMPpi8bqy0cer9x1NqogXVWylWC9l6YhA/tmp28kwa2ceclexz5tc90001zun1iy5b8x3wzip.safetensors",
      "scheduler": "K_EULER_ANCESTRAL",
      "lora_scales": "0.8",
      "num_outputs": 1,
      "adapter_type": "sketch",
      "guidance_scale": 3.62,
      "negative_prompt": "multiple head, lowres, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, watermark, blurry, multiple girls, multiple faces, canvas frame, cartoon, ((multiple head)), ((bad art)), ((extra limbs)), ((b&w)), wierd colors, (((duplicate))), ((morbid)), ((mutilated)), extra fingers, mutated hands, ((poorly drawn hands)), ((poorly drawn face)), (((mutation))), (((deformed))), ((ugly)), ((bad anatomy)), (((bad proportions))), cloned face, (((disfigured))), out of frame, gross proportions, (malformed limbs), ((missing arms)), ((missing legs)), (((extra arms))), (((extra legs))), (fused fingers), (too many fingers), (((long neck))), video game, tiling, poorly drawn feet, mutated, cross-eye, body out of frame, Humpbacked, shadow, nude, naked, NSFW, bad quality, low quality, fused fingers, poorly drawn face, too many fingers",
      "prompt_strength": 0.8,
      "num_inference_steps": 40
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2023-04-19T08:33:37.319096Z",
  "created_at": "2023-04-19T08:33:25.891534Z",
  "data_removed": false,
  "error": null,
  "id": "lf6m7k4tc5eupnvxjkb37iet7q",
  "input": {
    "width": 768,
    "height": 768,
    "prompt": "(((masterpiece))),(((bestquality))),((ultra-detailed)),(illustration),((anextremelydelicateandbeautiful)),dynamicangle,floating,(beautifuldetailedeyes),(detailedlight) (1girl), solo , floating_hair,glowingeyes,green hair,greeneyes <1>, twintails, halterdress,",
    "lora_urls": "https://replicate.delivery/pbxt/Mf7QBwNXrehQ3k6GwMPpi8bqy0cer9x1NqogXVWylWC9l6YhA/tmp28kwa2ceclexz5tc90001zun1iy5b8x3wzip.safetensors",
    "scheduler": "K_EULER_ANCESTRAL",
    "lora_scales": "0.8",
    "num_outputs": 1,
    "adapter_type": "sketch",
    "guidance_scale": 3.62,
    "negative_prompt": "multiple head, lowres, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, watermark, blurry, multiple girls, multiple faces, canvas frame, cartoon, ((multiple head)), ((bad art)), ((extra limbs)), ((b&w)), wierd colors, (((duplicate))), ((morbid)), ((mutilated)), extra fingers, mutated hands, ((poorly drawn hands)), ((poorly drawn face)), (((mutation))), (((deformed))), ((ugly)), ((bad anatomy)), (((bad proportions))), cloned face, (((disfigured))), out of frame, gross proportions, (malformed limbs), ((missing arms)), ((missing legs)), (((extra arms))), (((extra legs))), (fused fingers), (too many fingers), (((long neck))), video game, tiling, poorly drawn feet, mutated, cross-eye, body out of frame, Humpbacked, shadow, nude, naked, NSFW, bad quality, low quality, fused fingers, poorly drawn face, too many fingers",
    "prompt_strength": 0.8,
    "num_inference_steps": 40
  },
  "logs": "Using seed: 20786\nGenerating image of 768 x 768 with prompt: (((masterpiece))),(((bestquality))),((ultra-detailed)),(illustration),((anextremelydelicateandbeautiful)),dynamicangle,floating,(beautifuldetailedeyes),(detailedlight) (1girl), solo , floating_hair,glowingeyes,green hair,greeneyes <1>, twintails, halterdress,\nDownloading LoRA model... from https://replicate.delivery/pbxt/Mf7QBwNXrehQ3k6GwMPpi8bqy0cer9x1NqogXVWylWC9l6YhA/tmp28kwa2ceclexz5tc90001zun1iy5b8x3wzip.safetensors\nEmbedding <s1> replaced to <s0-0>\nEmbedding <s2> replaced to <s0-1>\n<s0-0>\n<s0-1>\nmerging time: 2.706554651260376\nToken indices sequence length is longer than the specified maximum sequence length for this model (84 > 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: ['twintails, halterdress,']\n  0%|          | 0/40 [00:00<?, ?it/s]\n  2%|▎         | 1/40 [00:01<01:05,  1.69s/it]\n  5%|▌         | 2/40 [00:01<00:29,  1.30it/s]\n  8%|▊         | 3/40 [00:01<00:17,  2.11it/s]\n 10%|█         | 4/40 [00:02<00:12,  2.97it/s]\n 12%|█▎        | 5/40 [00:02<00:09,  3.85it/s]\n 15%|█▌        | 6/40 [00:02<00:07,  4.69it/s]\n 18%|█▊        | 7/40 [00:02<00:06,  5.40it/s]\n 20%|██        | 8/40 [00:02<00:05,  6.01it/s]\n 22%|██▎       | 9/40 [00:02<00:04,  6.56it/s]\n 25%|██▌       | 10/40 [00:02<00:04,  6.96it/s]\n 28%|██▊       | 11/40 [00:02<00:03,  7.27it/s]\n 30%|███       | 12/40 [00:03<00:03,  7.47it/s]\n 32%|███▎      | 13/40 [00:03<00:03,  7.65it/s]\n 35%|███▌      | 14/40 [00:03<00:03,  7.81it/s]\n 38%|███▊      | 15/40 [00:03<00:03,  7.85it/s]\n 40%|████      | 16/40 [00:03<00:03,  7.95it/s]\n 42%|████▎     | 17/40 [00:03<00:02,  8.02it/s]\n 45%|████▌     | 18/40 [00:03<00:02,  8.05it/s]\n 48%|████▊     | 19/40 [00:03<00:02,  8.10it/s]\n 50%|█████     | 20/40 [00:04<00:02,  8.12it/s]\n 52%|█████▎    | 21/40 [00:04<00:02,  8.14it/s]\n 55%|█████▌    | 22/40 [00:04<00:02,  8.08it/s]\n 57%|█████▊    | 23/40 [00:04<00:02,  8.10it/s]\n 60%|██████    | 24/40 [00:04<00:01,  8.10it/s]\n 62%|██████▎   | 25/40 [00:04<00:01,  8.13it/s]\n 65%|██████▌   | 26/40 [00:04<00:01,  8.16it/s]\n 68%|██████▊   | 27/40 [00:04<00:01,  8.16it/s]\n 70%|███████   | 28/40 [00:05<00:01,  8.16it/s]\n 72%|███████▎  | 29/40 [00:05<00:01,  8.07it/s]\n 75%|███████▌  | 30/40 [00:05<00:01,  7.96it/s]\n 78%|███████▊  | 31/40 [00:05<00:01,  7.97it/s]\n 80%|████████  | 32/40 [00:05<00:01,  7.98it/s]\n 82%|████████▎ | 33/40 [00:05<00:00,  8.02it/s]\n 85%|████████▌ | 34/40 [00:05<00:00,  8.05it/s]\n 88%|████████▊ | 35/40 [00:05<00:00,  8.06it/s]\n 90%|█████████ | 36/40 [00:06<00:00,  8.03it/s]\n 92%|█████████▎| 37/40 [00:06<00:00,  7.99it/s]\n 95%|█████████▌| 38/40 [00:06<00:00,  7.93it/s]\n 98%|█████████▊| 39/40 [00:06<00:00,  7.94it/s]\n100%|██████████| 40/40 [00:06<00:00,  7.94it/s]\n100%|██████████| 40/40 [00:06<00:00,  6.12it/s]",
  "metrics": {
    "predict_time": 11.233206,
    "total_time": 11.427562
  },
  "output": [
    "https://replicate.delivery/pbxt/igi2ExxzRqq4B17INiaAdlYePZEzmumW3y4cLZH0ciZwyqZIA/out-0.png"
  ],
  "started_at": "2023-04-19T08:33:26.085890Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/lf6m7k4tc5eupnvxjkb37iet7q",
    "cancel": "https://api.replicate.com/v1/predictions/lf6m7k4tc5eupnvxjkb37iet7q/cancel"
  },
  "version": "9475aa3102d1be01bbf84cd88cc4ac5c85d037b5ff37e7a0f973ebbf81f409d7"
}

Generated in

11.2 seconds

Tweak itReport

Using seed: 20786
Generating image of 768 x 768 with prompt: (((masterpiece))),(((bestquality))),((ultra-detailed)),(illustration),((anextremelydelicateandbeautiful)),dynamicangle,floating,(beautifuldetailedeyes),(detailedlight) (1girl), solo , floating_hair,glowingeyes,green hair,greeneyes <1>, twintails, halterdress,
Downloading LoRA model... from https://replicate.delivery/pbxt/Mf7QBwNXrehQ3k6GwMPpi8bqy0cer9x1NqogXVWylWC9l6YhA/tmp28kwa2ceclexz5tc90001zun1iy5b8x3wzip.safetensors
Embedding <s1> replaced to <s0-0>
Embedding <s2> replaced to <s0-1>
<s0-0>
<s0-1>
merging time: 2.706554651260376
Token indices sequence length is longer than the specified maximum sequence length for this model (84 > 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: ['twintails, halterdress,']
  0%|          | 0/40 [00:00<?, ?it/s]
  2%|▎         | 1/40 [00:01<01:05,  1.69s/it]
  5%|▌         | 2/40 [00:01<00:29,  1.30it/s]
  8%|▊         | 3/40 [00:01<00:17,  2.11it/s]
 10%|█         | 4/40 [00:02<00:12,  2.97it/s]
 12%|█▎        | 5/40 [00:02<00:09,  3.85it/s]
 15%|█▌        | 6/40 [00:02<00:07,  4.69it/s]
 18%|█▊        | 7/40 [00:02<00:06,  5.40it/s]
 20%|██        | 8/40 [00:02<00:05,  6.01it/s]
 22%|██▎       | 9/40 [00:02<00:04,  6.56it/s]
 25%|██▌       | 10/40 [00:02<00:04,  6.96it/s]
 28%|██▊       | 11/40 [00:02<00:03,  7.27it/s]
 30%|███       | 12/40 [00:03<00:03,  7.47it/s]
 32%|███▎      | 13/40 [00:03<00:03,  7.65it/s]
 35%|███▌      | 14/40 [00:03<00:03,  7.81it/s]
 38%|███▊      | 15/40 [00:03<00:03,  7.85it/s]
 40%|████      | 16/40 [00:03<00:03,  7.95it/s]
 42%|████▎     | 17/40 [00:03<00:02,  8.02it/s]
 45%|████▌     | 18/40 [00:03<00:02,  8.05it/s]
 48%|████▊     | 19/40 [00:03<00:02,  8.10it/s]
 50%|█████     | 20/40 [00:04<00:02,  8.12it/s]
 52%|█████▎    | 21/40 [00:04<00:02,  8.14it/s]
 55%|█████▌    | 22/40 [00:04<00:02,  8.08it/s]
 57%|█████▊    | 23/40 [00:04<00:02,  8.10it/s]
 60%|██████    | 24/40 [00:04<00:01,  8.10it/s]
 62%|██████▎   | 25/40 [00:04<00:01,  8.13it/s]
 65%|██████▌   | 26/40 [00:04<00:01,  8.16it/s]
 68%|██████▊   | 27/40 [00:04<00:01,  8.16it/s]
 70%|███████   | 28/40 [00:05<00:01,  8.16it/s]
 72%|███████▎  | 29/40 [00:05<00:01,  8.07it/s]
 75%|███████▌  | 30/40 [00:05<00:01,  7.96it/s]
 78%|███████▊  | 31/40 [00:05<00:01,  7.97it/s]
 80%|████████  | 32/40 [00:05<00:01,  7.98it/s]
 82%|████████▎ | 33/40 [00:05<00:00,  8.02it/s]
 85%|████████▌ | 34/40 [00:05<00:00,  8.05it/s]
 88%|████████▊ | 35/40 [00:05<00:00,  8.06it/s]
 90%|█████████ | 36/40 [00:06<00:00,  8.03it/s]
 92%|█████████▎| 37/40 [00:06<00:00,  7.99it/s]
 95%|█████████▌| 38/40 [00:06<00:00,  7.93it/s]
 98%|█████████▊| 39/40 [00:06<00:00,  7.94it/s]
100%|██████████| 40/40 [00:06<00:00,  7.94it/s]
100%|██████████| 40/40 [00:06<00:00,  6.12it/s]

Examples

View more examples

Run time and cost

This model costs approximately $0.0021 to run on Replicate, or 476 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 10 seconds. The predict time for this model varies significantly based on the inputs.

Readme

…

Model description

…

Intended use

…

Ethical considerations

…

Caveats and recommendations

…