felixyifeiwang / dreamin-character

{
  "model": "dev",
  "prompt": "a TOK chibi character, Iron Man, empty background",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}

Install Replicate’s Node.js client library:

npm install replicate

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 felixyifeiwang/dreamin-character using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "felixyifeiwang/dreamin-character:b8afe418b34e5ee96c2d7848db65ef3276ec921f992555d65871a87fbd1b44aa",
  {
    input: {
      model: "dev",
      prompt: "a TOK chibi character, Iron Man, empty background",
      go_fast: false,
      lora_scale: 1,
      megapixels: "1",
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "webp",
      guidance_scale: 3,
      output_quality: 80,
      prompt_strength: 0.8,
      extra_lora_scale: 1,
      num_inference_steps: 28
    }
  }
);

// 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

Import the client:

import replicate

Run felixyifeiwang/dreamin-character using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "felixyifeiwang/dreamin-character:b8afe418b34e5ee96c2d7848db65ef3276ec921f992555d65871a87fbd1b44aa",
    input={
        "model": "dev",
        "prompt": "a TOK chibi character, Iron Man, empty background",
        "go_fast": False,
        "lora_scale": 1,
        "megapixels": "1",
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "webp",
        "guidance_scale": 3,
        "output_quality": 80,
        "prompt_strength": 0.8,
        "extra_lora_scale": 1,
        "num_inference_steps": 28
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run felixyifeiwang/dreamin-character 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": "felixyifeiwang/dreamin-character:b8afe418b34e5ee96c2d7848db65ef3276ec921f992555d65871a87fbd1b44aa",
    "input": {
      "model": "dev",
      "prompt": "a TOK chibi character, Iron Man, empty background",
      "go_fast": false,
      "lora_scale": 1,
      "megapixels": "1",
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "webp",
      "guidance_scale": 3,
      "output_quality": 80,
      "prompt_strength": 0.8,
      "extra_lora_scale": 1,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2025-01-21T00:17:12.678214Z",
  "created_at": "2025-01-21T00:17:04.140000Z",
  "data_removed": false,
  "error": null,
  "id": "qbfdt1jchhrmc0cmgrwaamh5ar",
  "input": {
    "model": "dev",
    "prompt": "a TOK chibi character, Iron Man, empty background",
    "go_fast": false,
    "lora_scale": 1,
    "megapixels": "1",
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "webp",
    "guidance_scale": 3,
    "output_quality": 80,
    "prompt_strength": 0.8,
    "extra_lora_scale": 1,
    "num_inference_steps": 28
  },
  "logs": "2025-01-21 00:17:04.314 | DEBUG    | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys\n2025-01-21 00:17:04.314 | DEBUG    | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted\nApplying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]\nApplying LoRA:  89%|████████▉ | 272/304 [00:00<00:00, 2709.90it/s]\nApplying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2615.76it/s]\n2025-01-21 00:17:04.431 | SUCCESS  | fp8.lora_loading:unload_loras:564 - LoRAs unloaded in 0.12s\nfree=29916624408576\nDownloading weights\n2025-01-21T00:17:04Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmp6y_hfpin/weights url=https://replicate.delivery/xezq/9kkUit44umIjJl1w7xxnseqPbjNd6NHA22QC8NeYeKOWxLOoA/trained_model.tar\n2025-01-21T00:17:06Z | INFO  | [ Complete ] dest=/tmp/tmp6y_hfpin/weights size=\"172 MB\" total_elapsed=1.913s url=https://replicate.delivery/xezq/9kkUit44umIjJl1w7xxnseqPbjNd6NHA22QC8NeYeKOWxLOoA/trained_model.tar\nDownloaded weights in 1.94s\n2025-01-21 00:17:06.369 | INFO     | fp8.lora_loading:convert_lora_weights:498 - Loading LoRA weights for /src/weights-cache/bc40ef69085e8969\n2025-01-21 00:17:06.439 | INFO     | fp8.lora_loading:convert_lora_weights:519 - LoRA weights loaded\n2025-01-21 00:17:06.439 | DEBUG    | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys\n2025-01-21 00:17:06.439 | DEBUG    | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted\nApplying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]\nApplying LoRA:  89%|████████▉ | 272/304 [00:00<00:00, 2712.73it/s]\nApplying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2618.20it/s]\n2025-01-21 00:17:06.556 | SUCCESS  | fp8.lora_loading:load_lora:539 - LoRA applied in 0.19s\nUsing seed: 2046\n0it [00:00, ?it/s]\n1it [00:00,  8.36it/s]\n2it [00:00,  5.86it/s]\n3it [00:00,  5.34it/s]\n4it [00:00,  5.12it/s]\n5it [00:00,  4.98it/s]\n6it [00:01,  4.89it/s]\n7it [00:01,  4.85it/s]\n8it [00:01,  4.84it/s]\n9it [00:01,  4.83it/s]\n10it [00:02,  4.79it/s]\n11it [00:02,  4.77it/s]\n12it [00:02,  4.78it/s]\n13it [00:02,  4.78it/s]\n14it [00:02,  4.77it/s]\n15it [00:03,  4.77it/s]\n16it [00:03,  4.76it/s]\n17it [00:03,  4.76it/s]\n18it [00:03,  4.76it/s]\n19it [00:03,  4.77it/s]\n20it [00:04,  4.77it/s]\n21it [00:04,  4.77it/s]\n22it [00:04,  4.77it/s]\n23it [00:04,  4.77it/s]\n24it [00:04,  4.76it/s]\n25it [00:05,  4.76it/s]\n26it [00:05,  4.76it/s]\n27it [00:05,  4.75it/s]\n28it [00:05,  4.76it/s]\n28it [00:05,  4.84it/s]\nTotal safe images: 1 out of 1",
  "metrics": {
    "predict_time": 8.362871512,
    "total_time": 8.538214
  },
  "output": [
    "https://replicate.delivery/xezq/sNP506a9DX6hLldE1Qt2kGOa8ONfvzRPAOfg3HnrFcAImJHUA/out-0.webp"
  ],
  "started_at": "2025-01-21T00:17:04.315342Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-cuk2vu667idtlykxtydj52rmisf5lzpvz2cv23tqmupucwjvog4q",
    "get": "https://api.replicate.com/v1/predictions/qbfdt1jchhrmc0cmgrwaamh5ar",
    "cancel": "https://api.replicate.com/v1/predictions/qbfdt1jchhrmc0cmgrwaamh5ar/cancel"
  },
  "version": "b8afe418b34e5ee96c2d7848db65ef3276ec921f992555d65871a87fbd1b44aa"
}

Generated in

8.4 seconds

Tweak it Share Report

2025-01-21 00:17:04.314 | DEBUG    | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys
2025-01-21 00:17:04.314 | DEBUG    | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted
Applying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]
Applying LoRA:  89%|████████▉ | 272/304 [00:00<00:00, 2709.90it/s]
Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2615.76it/s]
2025-01-21 00:17:04.431 | SUCCESS  | fp8.lora_loading:unload_loras:564 - LoRAs unloaded in 0.12s
free=29916624408576
Downloading weights
2025-01-21T00:17:04Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmp6y_hfpin/weights url=https://replicate.delivery/xezq/9kkUit44umIjJl1w7xxnseqPbjNd6NHA22QC8NeYeKOWxLOoA/trained_model.tar
2025-01-21T00:17:06Z | INFO  | [ Complete ] dest=/tmp/tmp6y_hfpin/weights size="172 MB" total_elapsed=1.913s url=https://replicate.delivery/xezq/9kkUit44umIjJl1w7xxnseqPbjNd6NHA22QC8NeYeKOWxLOoA/trained_model.tar
Downloaded weights in 1.94s
2025-01-21 00:17:06.369 | INFO     | fp8.lora_loading:convert_lora_weights:498 - Loading LoRA weights for /src/weights-cache/bc40ef69085e8969
2025-01-21 00:17:06.439 | INFO     | fp8.lora_loading:convert_lora_weights:519 - LoRA weights loaded
2025-01-21 00:17:06.439 | DEBUG    | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys
2025-01-21 00:17:06.439 | DEBUG    | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted
Applying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]
Applying LoRA:  89%|████████▉ | 272/304 [00:00<00:00, 2712.73it/s]
Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2618.20it/s]
2025-01-21 00:17:06.556 | SUCCESS  | fp8.lora_loading:load_lora:539 - LoRA applied in 0.19s
Using seed: 2046
0it [00:00, ?it/s]
1it [00:00,  8.36it/s]
2it [00:00,  5.86it/s]
3it [00:00,  5.34it/s]
4it [00:00,  5.12it/s]
5it [00:00,  4.98it/s]
6it [00:01,  4.89it/s]
7it [00:01,  4.85it/s]
8it [00:01,  4.84it/s]
9it [00:01,  4.83it/s]
10it [00:02,  4.79it/s]
11it [00:02,  4.77it/s]
12it [00:02,  4.78it/s]
13it [00:02,  4.78it/s]
14it [00:02,  4.77it/s]
15it [00:03,  4.77it/s]
16it [00:03,  4.76it/s]
17it [00:03,  4.76it/s]
18it [00:03,  4.76it/s]
19it [00:03,  4.77it/s]
20it [00:04,  4.77it/s]
21it [00:04,  4.77it/s]
22it [00:04,  4.77it/s]
23it [00:04,  4.77it/s]
24it [00:04,  4.76it/s]
25it [00:05,  4.76it/s]
26it [00:05,  4.76it/s]
27it [00:05,  4.75it/s]
28it [00:05,  4.76it/s]
28it [00:05,  4.84it/s]
Total safe images: 1 out of 1

Prediction

felixyifeiwang/dreamin-character:b8afe418b34e5ee96c2d7848db65ef3276ec921f992555d65871a87fbd1b44aa

Model

felixyifeiwang/dreamin-character:b8afe418

f3stxmp4ahrma0cmgrwvay9v0m

Status

Succeeded

Source

Web

Hardware

H100

Total duration

11.9s

Created

5 months ago

Input

model: dev
prompt: a TOK chibi character, a crazy scientist, empty background
go_fast
lora_scale: 1
megapixels: 1
num_outputs: 1
aspect_ratio: 1:1
output_format: webp
guidance_scale: 3
output_quality: 80
prompt_strength: 0.8
extra_lora_scale: 1
num_inference_steps: 28

{
  "model": "dev",
  "prompt": "a TOK chibi character, a crazy scientist, empty background",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}

Install Replicate’s Node.js client library:

npm install replicate

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 felixyifeiwang/dreamin-character using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "felixyifeiwang/dreamin-character:b8afe418b34e5ee96c2d7848db65ef3276ec921f992555d65871a87fbd1b44aa",
  {
    input: {
      model: "dev",
      prompt: "a TOK chibi character, a crazy scientist, empty background",
      go_fast: false,
      lora_scale: 1,
      megapixels: "1",
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "webp",
      guidance_scale: 3,
      output_quality: 80,
      prompt_strength: 0.8,
      extra_lora_scale: 1,
      num_inference_steps: 28
    }
  }
);

// 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

Import the client:

import replicate

Run felixyifeiwang/dreamin-character using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "felixyifeiwang/dreamin-character:b8afe418b34e5ee96c2d7848db65ef3276ec921f992555d65871a87fbd1b44aa",
    input={
        "model": "dev",
        "prompt": "a TOK chibi character, a crazy scientist, empty background",
        "go_fast": False,
        "lora_scale": 1,
        "megapixels": "1",
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "webp",
        "guidance_scale": 3,
        "output_quality": 80,
        "prompt_strength": 0.8,
        "extra_lora_scale": 1,
        "num_inference_steps": 28
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run felixyifeiwang/dreamin-character 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": "felixyifeiwang/dreamin-character:b8afe418b34e5ee96c2d7848db65ef3276ec921f992555d65871a87fbd1b44aa",
    "input": {
      "model": "dev",
      "prompt": "a TOK chibi character, a crazy scientist, empty background",
      "go_fast": false,
      "lora_scale": 1,
      "megapixels": "1",
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "webp",
      "guidance_scale": 3,
      "output_quality": 80,
      "prompt_strength": 0.8,
      "extra_lora_scale": 1,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2025-01-21T00:18:52.191087Z",
  "created_at": "2025-01-21T00:18:40.340000Z",
  "data_removed": false,
  "error": null,
  "id": "f3stxmp4ahrma0cmgrwvay9v0m",
  "input": {
    "model": "dev",
    "prompt": "a TOK chibi character, a crazy scientist, empty background",
    "go_fast": false,
    "lora_scale": 1,
    "megapixels": "1",
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "webp",
    "guidance_scale": 3,
    "output_quality": 80,
    "prompt_strength": 0.8,
    "extra_lora_scale": 1,
    "num_inference_steps": 28
  },
  "logs": "2025-01-21 00:18:45.710 | DEBUG    | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys\n2025-01-21 00:18:45.711 | DEBUG    | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted\nApplying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]\nApplying LoRA:  89%|████████▉ | 272/304 [00:00<00:00, 2711.57it/s]\nApplying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2617.52it/s]\n2025-01-21 00:18:45.827 | SUCCESS  | fp8.lora_loading:unload_loras:564 - LoRAs unloaded in 0.12s\n2025-01-21 00:18:45.829 | INFO     | fp8.lora_loading:convert_lora_weights:498 - Loading LoRA weights for /src/weights-cache/bc40ef69085e8969\n2025-01-21 00:18:45.940 | INFO     | fp8.lora_loading:convert_lora_weights:519 - LoRA weights loaded\n2025-01-21 00:18:45.940 | DEBUG    | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys\n2025-01-21 00:18:45.940 | DEBUG    | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted\nApplying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]\nApplying LoRA:  89%|████████▉ | 272/304 [00:00<00:00, 2715.68it/s]\nApplying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2620.79it/s]\n2025-01-21 00:18:46.057 | SUCCESS  | fp8.lora_loading:load_lora:539 - LoRA applied in 0.23s\nUsing seed: 1658\n0it [00:00, ?it/s]\n1it [00:00,  8.36it/s]\n2it [00:00,  5.85it/s]\n3it [00:00,  5.33it/s]\n4it [00:00,  5.11it/s]\n5it [00:00,  4.98it/s]\n6it [00:01,  4.88it/s]\n7it [00:01,  4.85it/s]\n8it [00:01,  4.83it/s]\n9it [00:01,  4.81it/s]\n10it [00:02,  4.78it/s]\n11it [00:02,  4.76it/s]\n12it [00:02,  4.77it/s]\n13it [00:02,  4.78it/s]\n14it [00:02,  4.78it/s]\n15it [00:03,  4.74it/s]\n16it [00:03,  4.75it/s]\n17it [00:03,  4.76it/s]\n18it [00:03,  4.77it/s]\n19it [00:03,  4.78it/s]\n20it [00:04,  4.76it/s]\n21it [00:04,  4.74it/s]\n22it [00:04,  4.76it/s]\n23it [00:04,  4.76it/s]\n24it [00:04,  4.77it/s]\n25it [00:05,  4.76it/s]\n26it [00:05,  4.76it/s]\n27it [00:05,  4.75it/s]\n28it [00:05,  4.76it/s]\n28it [00:05,  4.84it/s]\nTotal safe images: 1 out of 1",
  "metrics": {
    "predict_time": 6.479207739,
    "total_time": 11.851087
  },
  "output": [
    "https://replicate.delivery/xezq/jZL1M9NGEz6PKddohJiETbZAbWD0yaWYeDV75eodhfyYPTOoA/out-0.webp"
  ],
  "started_at": "2025-01-21T00:18:45.711879Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-tbx4kxgkpbesi3tc7ytfvcm6cgm73w4fhar2nji5fr6dcn5qqq4q",
    "get": "https://api.replicate.com/v1/predictions/f3stxmp4ahrma0cmgrwvay9v0m",
    "cancel": "https://api.replicate.com/v1/predictions/f3stxmp4ahrma0cmgrwvay9v0m/cancel"
  },
  "version": "b8afe418b34e5ee96c2d7848db65ef3276ec921f992555d65871a87fbd1b44aa"
}

Generated in

6.5 seconds

Tweak it Share Report

2025-01-21 00:18:45.710 | DEBUG    | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys
2025-01-21 00:18:45.711 | DEBUG    | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted
Applying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]
Applying LoRA:  89%|████████▉ | 272/304 [00:00<00:00, 2711.57it/s]
Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2617.52it/s]
2025-01-21 00:18:45.827 | SUCCESS  | fp8.lora_loading:unload_loras:564 - LoRAs unloaded in 0.12s
2025-01-21 00:18:45.829 | INFO     | fp8.lora_loading:convert_lora_weights:498 - Loading LoRA weights for /src/weights-cache/bc40ef69085e8969
2025-01-21 00:18:45.940 | INFO     | fp8.lora_loading:convert_lora_weights:519 - LoRA weights loaded
2025-01-21 00:18:45.940 | DEBUG    | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys
2025-01-21 00:18:45.940 | DEBUG    | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted
Applying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]
Applying LoRA:  89%|████████▉ | 272/304 [00:00<00:00, 2715.68it/s]
Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2620.79it/s]
2025-01-21 00:18:46.057 | SUCCESS  | fp8.lora_loading:load_lora:539 - LoRA applied in 0.23s
Using seed: 1658
0it [00:00, ?it/s]
1it [00:00,  8.36it/s]
2it [00:00,  5.85it/s]
3it [00:00,  5.33it/s]
4it [00:00,  5.11it/s]
5it [00:00,  4.98it/s]
6it [00:01,  4.88it/s]
7it [00:01,  4.85it/s]
8it [00:01,  4.83it/s]
9it [00:01,  4.81it/s]
10it [00:02,  4.78it/s]
11it [00:02,  4.76it/s]
12it [00:02,  4.77it/s]
13it [00:02,  4.78it/s]
14it [00:02,  4.78it/s]
15it [00:03,  4.74it/s]
16it [00:03,  4.75it/s]
17it [00:03,  4.76it/s]
18it [00:03,  4.77it/s]
19it [00:03,  4.78it/s]
20it [00:04,  4.76it/s]
21it [00:04,  4.74it/s]
22it [00:04,  4.76it/s]
23it [00:04,  4.76it/s]
24it [00:04,  4.77it/s]
25it [00:05,  4.76it/s]
26it [00:05,  4.76it/s]
27it [00:05,  4.75it/s]
28it [00:05,  4.76it/s]
28it [00:05,  4.84it/s]
Total safe images: 1 out of 1

Prediction

felixyifeiwang/dreamin-character:b8afe418b34e5ee96c2d7848db65ef3276ec921f992555d65871a87fbd1b44aa

Model

felixyifeiwang/dreamin-character:b8afe418

9gg3kdtkyhrme0cmgrx8z1xkmr

Status

Succeeded

Source

Web

Hardware

H100

Total duration

6.1s

Created

5 months ago

Input

model: dev
prompt: a TOK chibi character, the holy lord of blackhole, empty background
go_fast
lora_scale: 1
megapixels: 1
num_outputs: 1
aspect_ratio: 1:1
output_format: webp
guidance_scale: 3
output_quality: 80
prompt_strength: 0.8
extra_lora_scale: 1
num_inference_steps: 28

{
  "model": "dev",
  "prompt": "a TOK chibi character, the holy lord of blackhole, empty background",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}

Install Replicate’s Node.js client library:

npm install replicate

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 felixyifeiwang/dreamin-character using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "felixyifeiwang/dreamin-character:b8afe418b34e5ee96c2d7848db65ef3276ec921f992555d65871a87fbd1b44aa",
  {
    input: {
      model: "dev",
      prompt: "a TOK chibi character, the holy lord of blackhole, empty background",
      go_fast: false,
      lora_scale: 1,
      megapixels: "1",
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "webp",
      guidance_scale: 3,
      output_quality: 80,
      prompt_strength: 0.8,
      extra_lora_scale: 1,
      num_inference_steps: 28
    }
  }
);

// 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

Import the client:

import replicate

Run felixyifeiwang/dreamin-character using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "felixyifeiwang/dreamin-character:b8afe418b34e5ee96c2d7848db65ef3276ec921f992555d65871a87fbd1b44aa",
    input={
        "model": "dev",
        "prompt": "a TOK chibi character, the holy lord of blackhole, empty background",
        "go_fast": False,
        "lora_scale": 1,
        "megapixels": "1",
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "webp",
        "guidance_scale": 3,
        "output_quality": 80,
        "prompt_strength": 0.8,
        "extra_lora_scale": 1,
        "num_inference_steps": 28
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run felixyifeiwang/dreamin-character 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": "felixyifeiwang/dreamin-character:b8afe418b34e5ee96c2d7848db65ef3276ec921f992555d65871a87fbd1b44aa",
    "input": {
      "model": "dev",
      "prompt": "a TOK chibi character, the holy lord of blackhole, empty background",
      "go_fast": false,
      "lora_scale": 1,
      "megapixels": "1",
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "webp",
      "guidance_scale": 3,
      "output_quality": 80,
      "prompt_strength": 0.8,
      "extra_lora_scale": 1,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2025-01-21T00:19:23.196147Z",
  "created_at": "2025-01-21T00:19:17.108000Z",
  "data_removed": false,
  "error": null,
  "id": "9gg3kdtkyhrme0cmgrx8z1xkmr",
  "input": {
    "model": "dev",
    "prompt": "a TOK chibi character, the holy lord of blackhole, empty background",
    "go_fast": false,
    "lora_scale": 1,
    "megapixels": "1",
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "webp",
    "guidance_scale": 3,
    "output_quality": 80,
    "prompt_strength": 0.8,
    "extra_lora_scale": 1,
    "num_inference_steps": 28
  },
  "logs": "Lora https://replicate.delivery/xezq/9kkUit44umIjJl1w7xxnseqPbjNd6NHA22QC8NeYeKOWxLOoA/trained_model.tar already loaded\nUsing seed: 25982\n0it [00:00, ?it/s]\n1it [00:00,  8.36it/s]\n2it [00:00,  5.85it/s]\n3it [00:00,  5.33it/s]\n4it [00:00,  5.12it/s]\n5it [00:00,  4.97it/s]\n6it [00:01,  4.87it/s]\n7it [00:01,  4.84it/s]\n8it [00:01,  4.83it/s]\n9it [00:01,  4.83it/s]\n10it [00:02,  4.81it/s]\n11it [00:02,  4.78it/s]\n12it [00:02,  4.78it/s]\n13it [00:02,  4.78it/s]\n14it [00:02,  4.78it/s]\n15it [00:03,  4.77it/s]\n16it [00:03,  4.76it/s]\n17it [00:03,  4.76it/s]\n18it [00:03,  4.77it/s]\n19it [00:03,  4.78it/s]\n20it [00:04,  4.78it/s]\n21it [00:04,  4.76it/s]\n22it [00:04,  4.77it/s]\n23it [00:04,  4.77it/s]\n24it [00:04,  4.78it/s]\n25it [00:05,  4.76it/s]\n26it [00:05,  4.76it/s]\n27it [00:05,  4.76it/s]\n28it [00:05,  4.77it/s]\n28it [00:05,  4.85it/s]\nTotal safe images: 1 out of 1",
  "metrics": {
    "predict_time": 6.081697387,
    "total_time": 6.088147
  },
  "output": [
    "https://replicate.delivery/xezq/5HK34yDFkSJQNZOdALqeNt7bZOAI7CFoU4Kj0oPZtomF0kDKA/out-0.webp"
  ],
  "started_at": "2025-01-21T00:19:17.114449Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-jadsdguxnlkui7uusyhe5wzc34eljjsklmrsxfstu5j4tsp6bjca",
    "get": "https://api.replicate.com/v1/predictions/9gg3kdtkyhrme0cmgrx8z1xkmr",
    "cancel": "https://api.replicate.com/v1/predictions/9gg3kdtkyhrme0cmgrx8z1xkmr/cancel"
  },
  "version": "b8afe418b34e5ee96c2d7848db65ef3276ec921f992555d65871a87fbd1b44aa"
}

Generated in

6.1 seconds

Tweak it Share Report

Prediction

felixyifeiwang/dreamin-character:b8afe418b34e5ee96c2d7848db65ef3276ec921f992555d65871a87fbd1b44aa

Model

felixyifeiwang/dreamin-character:b8afe418

d4natvev51rme0cmgrxa2vy0j8

Status

Succeeded

Source

Web

Hardware

H100

Total duration

7.4s

Created

5 months ago

Input

model: dev
prompt: a TOK chibi character, the holy divine angel, empty background
go_fast
lora_scale: 1
megapixels: 1
num_outputs: 1
aspect_ratio: 1:1
output_format: webp
guidance_scale: 3
output_quality: 80
prompt_strength: 0.8
extra_lora_scale: 1
num_inference_steps: 28

{
  "model": "dev",
  "prompt": "a TOK chibi character, the holy divine angel, empty background",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}

Install Replicate’s Node.js client library:

npm install replicate

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 felixyifeiwang/dreamin-character using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "felixyifeiwang/dreamin-character:b8afe418b34e5ee96c2d7848db65ef3276ec921f992555d65871a87fbd1b44aa",
  {
    input: {
      model: "dev",
      prompt: "a TOK chibi character, the holy divine angel, empty background",
      go_fast: false,
      lora_scale: 1,
      megapixels: "1",
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "webp",
      guidance_scale: 3,
      output_quality: 80,
      prompt_strength: 0.8,
      extra_lora_scale: 1,
      num_inference_steps: 28
    }
  }
);

// 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

Import the client:

import replicate

Run felixyifeiwang/dreamin-character using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "felixyifeiwang/dreamin-character:b8afe418b34e5ee96c2d7848db65ef3276ec921f992555d65871a87fbd1b44aa",
    input={
        "model": "dev",
        "prompt": "a TOK chibi character, the holy divine angel, empty background",
        "go_fast": False,
        "lora_scale": 1,
        "megapixels": "1",
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "webp",
        "guidance_scale": 3,
        "output_quality": 80,
        "prompt_strength": 0.8,
        "extra_lora_scale": 1,
        "num_inference_steps": 28
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run felixyifeiwang/dreamin-character 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": "felixyifeiwang/dreamin-character:b8afe418b34e5ee96c2d7848db65ef3276ec921f992555d65871a87fbd1b44aa",
    "input": {
      "model": "dev",
      "prompt": "a TOK chibi character, the holy divine angel, empty background",
      "go_fast": false,
      "lora_scale": 1,
      "megapixels": "1",
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "webp",
      "guidance_scale": 3,
      "output_quality": 80,
      "prompt_strength": 0.8,
      "extra_lora_scale": 1,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2025-01-21T00:19:59.130623Z",
  "created_at": "2025-01-21T00:19:51.720000Z",
  "data_removed": false,
  "error": null,
  "id": "d4natvev51rme0cmgrxa2vy0j8",
  "input": {
    "model": "dev",
    "prompt": "a TOK chibi character, the holy divine angel, empty background",
    "go_fast": false,
    "lora_scale": 1,
    "megapixels": "1",
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "webp",
    "guidance_scale": 3,
    "output_quality": 80,
    "prompt_strength": 0.8,
    "extra_lora_scale": 1,
    "num_inference_steps": 28
  },
  "logs": "2025-01-21 00:19:51.729 | DEBUG    | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys\n2025-01-21 00:19:51.729 | DEBUG    | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted\nApplying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]\nApplying LoRA:  92%|█████████▏| 281/304 [00:00<00:00, 2797.93it/s]\nApplying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2656.05it/s]\n2025-01-21 00:19:51.844 | SUCCESS  | fp8.lora_loading:unload_loras:564 - LoRAs unloaded in 0.12s\nfree=29801191206912\nDownloading weights\n2025-01-21T00:19:51Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpfnqykfix/weights url=https://replicate.delivery/xezq/9kkUit44umIjJl1w7xxnseqPbjNd6NHA22QC8NeYeKOWxLOoA/trained_model.tar\n2025-01-21T00:19:52Z | INFO  | [ Complete ] dest=/tmp/tmpfnqykfix/weights size=\"172 MB\" total_elapsed=0.935s url=https://replicate.delivery/xezq/9kkUit44umIjJl1w7xxnseqPbjNd6NHA22QC8NeYeKOWxLOoA/trained_model.tar\nDownloaded weights in 0.96s\n2025-01-21 00:19:52.805 | INFO     | fp8.lora_loading:convert_lora_weights:498 - Loading LoRA weights for /src/weights-cache/bc40ef69085e8969\n2025-01-21 00:19:52.877 | INFO     | fp8.lora_loading:convert_lora_weights:519 - LoRA weights loaded\n2025-01-21 00:19:52.877 | DEBUG    | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys\n2025-01-21 00:19:52.878 | DEBUG    | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted\nApplying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]\nApplying LoRA:  92%|█████████▏| 281/304 [00:00<00:00, 2801.16it/s]\nApplying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2658.43it/s]\n2025-01-21 00:19:52.992 | SUCCESS  | fp8.lora_loading:load_lora:539 - LoRA applied in 0.19s\nUsing seed: 19522\n0it [00:00, ?it/s]\n1it [00:00,  8.37it/s]\n2it [00:00,  5.83it/s]\n3it [00:00,  5.31it/s]\n4it [00:00,  5.10it/s]\n5it [00:00,  4.94it/s]\n6it [00:01,  4.87it/s]\n7it [00:01,  4.84it/s]\n8it [00:01,  4.83it/s]\n9it [00:01,  4.81it/s]\n10it [00:02,  4.79it/s]\n11it [00:02,  4.77it/s]\n12it [00:02,  4.77it/s]\n13it [00:02,  4.78it/s]\n14it [00:02,  4.77it/s]\n15it [00:03,  4.77it/s]\n16it [00:03,  4.76it/s]\n17it [00:03,  4.76it/s]\n18it [00:03,  4.76it/s]\n19it [00:03,  4.75it/s]\n20it [00:04,  4.75it/s]\n21it [00:04,  4.75it/s]\n22it [00:04,  4.75it/s]\n23it [00:04,  4.76it/s]\n24it [00:04,  4.76it/s]\n25it [00:05,  4.76it/s]\n26it [00:05,  4.76it/s]\n27it [00:05,  4.76it/s]\n28it [00:05,  4.76it/s]\n28it [00:05,  4.84it/s]\nTotal safe images: 1 out of 1",
  "metrics": {
    "predict_time": 7.400375664,
    "total_time": 7.410623
  },
  "output": [
    "https://replicate.delivery/xezq/OWxGQj5nnr7zPVuV6taBEoG584kVzf5J6NcsEE4PHslX0kDKA/out-0.webp"
  ],
  "started_at": "2025-01-21T00:19:51.730247Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-cbal2li53jp76ybnfou62susy5onizjbzqbnwfzkvtpnqgont6hq",
    "get": "https://api.replicate.com/v1/predictions/d4natvev51rme0cmgrxa2vy0j8",
    "cancel": "https://api.replicate.com/v1/predictions/d4natvev51rme0cmgrxa2vy0j8/cancel"
  },
  "version": "b8afe418b34e5ee96c2d7848db65ef3276ec921f992555d65871a87fbd1b44aa"
}

Generated in

7.4 seconds

Tweak it Share Report

2025-01-21 00:19:51.729 | DEBUG    | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys
2025-01-21 00:19:51.729 | DEBUG    | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted
Applying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]
Applying LoRA:  92%|█████████▏| 281/304 [00:00<00:00, 2797.93it/s]
Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2656.05it/s]
2025-01-21 00:19:51.844 | SUCCESS  | fp8.lora_loading:unload_loras:564 - LoRAs unloaded in 0.12s
free=29801191206912
Downloading weights
2025-01-21T00:19:51Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpfnqykfix/weights url=https://replicate.delivery/xezq/9kkUit44umIjJl1w7xxnseqPbjNd6NHA22QC8NeYeKOWxLOoA/trained_model.tar
2025-01-21T00:19:52Z | INFO  | [ Complete ] dest=/tmp/tmpfnqykfix/weights size="172 MB" total_elapsed=0.935s url=https://replicate.delivery/xezq/9kkUit44umIjJl1w7xxnseqPbjNd6NHA22QC8NeYeKOWxLOoA/trained_model.tar
Downloaded weights in 0.96s
2025-01-21 00:19:52.805 | INFO     | fp8.lora_loading:convert_lora_weights:498 - Loading LoRA weights for /src/weights-cache/bc40ef69085e8969
2025-01-21 00:19:52.877 | INFO     | fp8.lora_loading:convert_lora_weights:519 - LoRA weights loaded
2025-01-21 00:19:52.877 | DEBUG    | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys
2025-01-21 00:19:52.878 | DEBUG    | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted
Applying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]
Applying LoRA:  92%|█████████▏| 281/304 [00:00<00:00, 2801.16it/s]
Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2658.43it/s]
2025-01-21 00:19:52.992 | SUCCESS  | fp8.lora_loading:load_lora:539 - LoRA applied in 0.19s
Using seed: 19522
0it [00:00, ?it/s]
1it [00:00,  8.37it/s]
2it [00:00,  5.83it/s]
3it [00:00,  5.31it/s]
4it [00:00,  5.10it/s]
5it [00:00,  4.94it/s]
6it [00:01,  4.87it/s]
7it [00:01,  4.84it/s]
8it [00:01,  4.83it/s]
9it [00:01,  4.81it/s]
10it [00:02,  4.79it/s]
11it [00:02,  4.77it/s]
12it [00:02,  4.77it/s]
13it [00:02,  4.78it/s]
14it [00:02,  4.77it/s]
15it [00:03,  4.77it/s]
16it [00:03,  4.76it/s]
17it [00:03,  4.76it/s]
18it [00:03,  4.76it/s]
19it [00:03,  4.75it/s]
20it [00:04,  4.75it/s]
21it [00:04,  4.75it/s]
22it [00:04,  4.75it/s]
23it [00:04,  4.76it/s]
24it [00:04,  4.76it/s]
25it [00:05,  4.76it/s]
26it [00:05,  4.76it/s]
27it [00:05,  4.76it/s]
28it [00:05,  4.76it/s]
28it [00:05,  4.84it/s]
Total safe images: 1 out of 1

Prediction

felixyifeiwang/dreamin-character:b8afe418b34e5ee96c2d7848db65ef3276ec921f992555d65871a87fbd1b44aa

Model

felixyifeiwang/dreamin-character:b8afe418

gxqxx9bfehrmc0cmgrxs31tmjw

Status

Succeeded

Source

Web

Hardware

H100

Total duration

6.1s

Created

5 months ago

Input

model: dev
prompt: a TOK chibi character, a psycho serial killer, empty background
go_fast
lora_scale: 1
megapixels: 1
num_outputs: 1
aspect_ratio: 1:1
output_format: webp
guidance_scale: 3
output_quality: 80
prompt_strength: 0.8
extra_lora_scale: 1
num_inference_steps: 28

{
  "model": "dev",
  "prompt": "a TOK chibi character, a psycho serial killer, empty background",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}

Install Replicate’s Node.js client library:

npm install replicate

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 felixyifeiwang/dreamin-character using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "felixyifeiwang/dreamin-character:b8afe418b34e5ee96c2d7848db65ef3276ec921f992555d65871a87fbd1b44aa",
  {
    input: {
      model: "dev",
      prompt: "a TOK chibi character, a psycho serial killer, empty background",
      go_fast: false,
      lora_scale: 1,
      megapixels: "1",
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "webp",
      guidance_scale: 3,
      output_quality: 80,
      prompt_strength: 0.8,
      extra_lora_scale: 1,
      num_inference_steps: 28
    }
  }
);

// 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

Import the client:

import replicate

Run felixyifeiwang/dreamin-character using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "felixyifeiwang/dreamin-character:b8afe418b34e5ee96c2d7848db65ef3276ec921f992555d65871a87fbd1b44aa",
    input={
        "model": "dev",
        "prompt": "a TOK chibi character, a psycho serial killer, empty background",
        "go_fast": False,
        "lora_scale": 1,
        "megapixels": "1",
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "webp",
        "guidance_scale": 3,
        "output_quality": 80,
        "prompt_strength": 0.8,
        "extra_lora_scale": 1,
        "num_inference_steps": 28
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run felixyifeiwang/dreamin-character 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": "felixyifeiwang/dreamin-character:b8afe418b34e5ee96c2d7848db65ef3276ec921f992555d65871a87fbd1b44aa",
    "input": {
      "model": "dev",
      "prompt": "a TOK chibi character, a psycho serial killer, empty background",
      "go_fast": false,
      "lora_scale": 1,
      "megapixels": "1",
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "webp",
      "guidance_scale": 3,
      "output_quality": 80,
      "prompt_strength": 0.8,
      "extra_lora_scale": 1,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2025-01-21T00:20:35.800232Z",
  "created_at": "2025-01-21T00:20:29.684000Z",
  "data_removed": false,
  "error": null,
  "id": "gxqxx9bfehrmc0cmgrxs31tmjw",
  "input": {
    "model": "dev",
    "prompt": "a TOK chibi character, a psycho serial killer, empty background",
    "go_fast": false,
    "lora_scale": 1,
    "megapixels": "1",
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "webp",
    "guidance_scale": 3,
    "output_quality": 80,
    "prompt_strength": 0.8,
    "extra_lora_scale": 1,
    "num_inference_steps": 28
  },
  "logs": "Lora https://replicate.delivery/xezq/9kkUit44umIjJl1w7xxnseqPbjNd6NHA22QC8NeYeKOWxLOoA/trained_model.tar already loaded\nUsing seed: 61243\n0it [00:00, ?it/s]\n1it [00:00,  8.34it/s]\n2it [00:00,  5.82it/s]\n3it [00:00,  5.28it/s]\n4it [00:00,  5.05it/s]\n5it [00:00,  4.93it/s]\n6it [00:01,  4.86it/s]\n7it [00:01,  4.82it/s]\n8it [00:01,  4.80it/s]\n9it [00:01,  4.78it/s]\n10it [00:02,  4.77it/s]\n11it [00:02,  4.76it/s]\n12it [00:02,  4.75it/s]\n13it [00:02,  4.75it/s]\n14it [00:02,  4.74it/s]\n15it [00:03,  4.74it/s]\n16it [00:03,  4.74it/s]\n17it [00:03,  4.74it/s]\n18it [00:03,  4.75it/s]\n19it [00:03,  4.75it/s]\n20it [00:04,  4.75it/s]\n21it [00:04,  4.75it/s]\n22it [00:04,  4.76it/s]\n23it [00:04,  4.77it/s]\n24it [00:04,  4.76it/s]\n25it [00:05,  4.77it/s]\n26it [00:05,  4.76it/s]\n27it [00:05,  4.76it/s]\n28it [00:05,  4.76it/s]\n28it [00:05,  4.83it/s]\nTotal safe images: 1 out of 1",
  "metrics": {
    "predict_time": 6.109457876,
    "total_time": 6.116232
  },
  "output": [
    "https://replicate.delivery/xezq/AE3OxXui3UrDLdfHTe1l2C6adngWifSNA5d9edPeCpBbKN5gC/out-0.webp"
  ],
  "started_at": "2025-01-21T00:20:29.690774Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-33qcuby5hldhhixytu7pz5m5pac6a3xqlfcpwmtge7otfmeap65a",
    "get": "https://api.replicate.com/v1/predictions/gxqxx9bfehrmc0cmgrxs31tmjw",
    "cancel": "https://api.replicate.com/v1/predictions/gxqxx9bfehrmc0cmgrxs31tmjw/cancel"
  },
  "version": "b8afe418b34e5ee96c2d7848db65ef3276ec921f992555d65871a87fbd1b44aa"
}

Generated in

6.1 seconds

Tweak it Share Report

Prediction

felixyifeiwang/dreamin-character:b8afe418b34e5ee96c2d7848db65ef3276ec921f992555d65871a87fbd1b44aa

Model

felixyifeiwang/dreamin-character:b8afe418

s8q3w6q93hrme0cmgrxrh4w2sm

Status

Succeeded

Source

Web

Hardware

H100

Total duration

8.8s

Created

5 months ago

Input

model: dev
prompt: a TOK chibi character, an angry orc fighter, empty background
go_fast
lora_scale: 1
megapixels: 1
num_outputs: 1
aspect_ratio: 1:1
output_format: webp
guidance_scale: 3
output_quality: 80
prompt_strength: 0.8
extra_lora_scale: 1
num_inference_steps: 28

{
  "model": "dev",
  "prompt": "a TOK chibi character, an angry orc fighter, empty background",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}

Install Replicate’s Node.js client library:

npm install replicate

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 felixyifeiwang/dreamin-character using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "felixyifeiwang/dreamin-character:b8afe418b34e5ee96c2d7848db65ef3276ec921f992555d65871a87fbd1b44aa",
  {
    input: {
      model: "dev",
      prompt: "a TOK chibi character, an angry orc fighter, empty background",
      go_fast: false,
      lora_scale: 1,
      megapixels: "1",
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "webp",
      guidance_scale: 3,
      output_quality: 80,
      prompt_strength: 0.8,
      extra_lora_scale: 1,
      num_inference_steps: 28
    }
  }
);

// 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

Import the client:

import replicate

Run felixyifeiwang/dreamin-character using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "felixyifeiwang/dreamin-character:b8afe418b34e5ee96c2d7848db65ef3276ec921f992555d65871a87fbd1b44aa",
    input={
        "model": "dev",
        "prompt": "a TOK chibi character, an angry orc fighter, empty background",
        "go_fast": False,
        "lora_scale": 1,
        "megapixels": "1",
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "webp",
        "guidance_scale": 3,
        "output_quality": 80,
        "prompt_strength": 0.8,
        "extra_lora_scale": 1,
        "num_inference_steps": 28
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run felixyifeiwang/dreamin-character 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": "felixyifeiwang/dreamin-character:b8afe418b34e5ee96c2d7848db65ef3276ec921f992555d65871a87fbd1b44aa",
    "input": {
      "model": "dev",
      "prompt": "a TOK chibi character, an angry orc fighter, empty background",
      "go_fast": false,
      "lora_scale": 1,
      "megapixels": "1",
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "webp",
      "guidance_scale": 3,
      "output_quality": 80,
      "prompt_strength": 0.8,
      "extra_lora_scale": 1,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2025-01-21T00:21:09.637168Z",
  "created_at": "2025-01-21T00:21:00.828000Z",
  "data_removed": false,
  "error": null,
  "id": "s8q3w6q93hrme0cmgrxrh4w2sm",
  "input": {
    "model": "dev",
    "prompt": "a TOK chibi character, an angry orc fighter, empty background",
    "go_fast": false,
    "lora_scale": 1,
    "megapixels": "1",
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "webp",
    "guidance_scale": 3,
    "output_quality": 80,
    "prompt_strength": 0.8,
    "extra_lora_scale": 1,
    "num_inference_steps": 28
  },
  "logs": "2025-01-21 00:21:01.073 | DEBUG    | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys\n2025-01-21 00:21:01.073 | DEBUG    | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted\nApplying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]\nApplying LoRA:  91%|█████████ | 276/304 [00:00<00:00, 2755.54it/s]\nApplying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2632.71it/s]\n2025-01-21 00:21:01.189 | SUCCESS  | fp8.lora_loading:unload_loras:564 - LoRAs unloaded in 0.12s\nfree=29748613378048\nDownloading weights\n2025-01-21T00:21:01Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpkswydjz0/weights url=https://replicate.delivery/xezq/9kkUit44umIjJl1w7xxnseqPbjNd6NHA22QC8NeYeKOWxLOoA/trained_model.tar\n2025-01-21T00:21:03Z | INFO  | [ Complete ] dest=/tmp/tmpkswydjz0/weights size=\"172 MB\" total_elapsed=2.055s url=https://replicate.delivery/xezq/9kkUit44umIjJl1w7xxnseqPbjNd6NHA22QC8NeYeKOWxLOoA/trained_model.tar\nDownloaded weights in 2.10s\n2025-01-21 00:21:03.292 | INFO     | fp8.lora_loading:convert_lora_weights:498 - Loading LoRA weights for /src/weights-cache/bc40ef69085e8969\n2025-01-21 00:21:03.418 | INFO     | fp8.lora_loading:convert_lora_weights:519 - LoRA weights loaded\n2025-01-21 00:21:03.418 | DEBUG    | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys\n2025-01-21 00:21:03.419 | DEBUG    | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted\nApplying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]\nApplying LoRA:  91%|█████████ | 276/304 [00:00<00:00, 2756.13it/s]\nApplying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2636.31it/s]\n2025-01-21 00:21:03.535 | SUCCESS  | fp8.lora_loading:load_lora:539 - LoRA applied in 0.24s\nUsing seed: 3375\n0it [00:00, ?it/s]\n1it [00:00,  8.18it/s]\n2it [00:00,  5.77it/s]\n3it [00:00,  5.26it/s]\n4it [00:00,  5.06it/s]\n5it [00:00,  4.95it/s]\n6it [00:01,  4.91it/s]\n7it [00:01,  4.86it/s]\n8it [00:01,  4.85it/s]\n9it [00:01,  4.85it/s]\n10it [00:01,  4.84it/s]\n11it [00:02,  4.83it/s]\n12it [00:02,  4.83it/s]\n13it [00:02,  4.82it/s]\n14it [00:02,  4.82it/s]\n15it [00:03,  4.82it/s]\n16it [00:03,  4.82it/s]\n17it [00:03,  4.83it/s]\n18it [00:03,  4.82it/s]\n19it [00:03,  4.82it/s]\n20it [00:04,  4.82it/s]\n21it [00:04,  4.82it/s]\n22it [00:04,  4.82it/s]\n23it [00:04,  4.82it/s]\n24it [00:04,  4.82it/s]\n25it [00:05,  4.82it/s]\n26it [00:05,  4.82it/s]\n27it [00:05,  4.83it/s]\n28it [00:05,  4.83it/s]\n28it [00:05,  4.89it/s]\nTotal safe images: 1 out of 1",
  "metrics": {
    "predict_time": 8.562805636,
    "total_time": 8.809168
  },
  "output": [
    "https://replicate.delivery/xezq/zwFSG1LE4aaqAlWIovxv82fM2MfetoauP1SIy3hKdqcrTTOoA/out-0.webp"
  ],
  "started_at": "2025-01-21T00:21:01.074362Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-utpdtelqt73dnrnvvshu7l3yi3om4tamfctyvess45hk4q72hpvq",
    "get": "https://api.replicate.com/v1/predictions/s8q3w6q93hrme0cmgrxrh4w2sm",
    "cancel": "https://api.replicate.com/v1/predictions/s8q3w6q93hrme0cmgrxrh4w2sm/cancel"
  },
  "version": "b8afe418b34e5ee96c2d7848db65ef3276ec921f992555d65871a87fbd1b44aa"
}

Generated in

8.6 seconds

Tweak it Share Report

2025-01-21 00:21:01.073 | DEBUG    | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys
2025-01-21 00:21:01.073 | DEBUG    | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted
Applying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]
Applying LoRA:  91%|█████████ | 276/304 [00:00<00:00, 2755.54it/s]
Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2632.71it/s]
2025-01-21 00:21:01.189 | SUCCESS  | fp8.lora_loading:unload_loras:564 - LoRAs unloaded in 0.12s
free=29748613378048
Downloading weights
2025-01-21T00:21:01Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpkswydjz0/weights url=https://replicate.delivery/xezq/9kkUit44umIjJl1w7xxnseqPbjNd6NHA22QC8NeYeKOWxLOoA/trained_model.tar
2025-01-21T00:21:03Z | INFO  | [ Complete ] dest=/tmp/tmpkswydjz0/weights size="172 MB" total_elapsed=2.055s url=https://replicate.delivery/xezq/9kkUit44umIjJl1w7xxnseqPbjNd6NHA22QC8NeYeKOWxLOoA/trained_model.tar
Downloaded weights in 2.10s
2025-01-21 00:21:03.292 | INFO     | fp8.lora_loading:convert_lora_weights:498 - Loading LoRA weights for /src/weights-cache/bc40ef69085e8969
2025-01-21 00:21:03.418 | INFO     | fp8.lora_loading:convert_lora_weights:519 - LoRA weights loaded
2025-01-21 00:21:03.418 | DEBUG    | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys
2025-01-21 00:21:03.419 | DEBUG    | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted
Applying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]
Applying LoRA:  91%|█████████ | 276/304 [00:00<00:00, 2756.13it/s]
Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2636.31it/s]
2025-01-21 00:21:03.535 | SUCCESS  | fp8.lora_loading:load_lora:539 - LoRA applied in 0.24s
Using seed: 3375
0it [00:00, ?it/s]
1it [00:00,  8.18it/s]
2it [00:00,  5.77it/s]
3it [00:00,  5.26it/s]
4it [00:00,  5.06it/s]
5it [00:00,  4.95it/s]
6it [00:01,  4.91it/s]
7it [00:01,  4.86it/s]
8it [00:01,  4.85it/s]
9it [00:01,  4.85it/s]
10it [00:01,  4.84it/s]
11it [00:02,  4.83it/s]
12it [00:02,  4.83it/s]
13it [00:02,  4.82it/s]
14it [00:02,  4.82it/s]
15it [00:03,  4.82it/s]
16it [00:03,  4.82it/s]
17it [00:03,  4.83it/s]
18it [00:03,  4.82it/s]
19it [00:03,  4.82it/s]
20it [00:04,  4.82it/s]
21it [00:04,  4.82it/s]
22it [00:04,  4.82it/s]
23it [00:04,  4.82it/s]
24it [00:04,  4.82it/s]
25it [00:05,  4.82it/s]
26it [00:05,  4.82it/s]
27it [00:05,  4.83it/s]
28it [00:05,  4.83it/s]
28it [00:05,  4.89it/s]
Total safe images: 1 out of 1

Prediction

felixyifeiwang/dreamin-character:b8afe418b34e5ee96c2d7848db65ef3276ec921f992555d65871a87fbd1b44aa

Model

felixyifeiwang/dreamin-character:b8afe418

pzwgvqvjsxrma0cmgrybgm18kr

Status

Succeeded

Source

Web

Hardware

H100

Total duration

6.8s

Created

5 months ago

Input

model: dev
prompt: a TOK chibi character, a mysterious tiefling mage, empty background
go_fast
lora_scale: 1
megapixels: 1
num_outputs: 1
aspect_ratio: 1:1
output_format: webp
guidance_scale: 3
output_quality: 80
prompt_strength: 0.8
extra_lora_scale: 1
num_inference_steps: 28

{
  "model": "dev",
  "prompt": "a TOK chibi character, a mysterious tiefling mage, empty background",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}

Install Replicate’s Node.js client library:

npm install replicate

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 felixyifeiwang/dreamin-character using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "felixyifeiwang/dreamin-character:b8afe418b34e5ee96c2d7848db65ef3276ec921f992555d65871a87fbd1b44aa",
  {
    input: {
      model: "dev",
      prompt: "a TOK chibi character, a mysterious tiefling mage, empty background",
      go_fast: false,
      lora_scale: 1,
      megapixels: "1",
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "webp",
      guidance_scale: 3,
      output_quality: 80,
      prompt_strength: 0.8,
      extra_lora_scale: 1,
      num_inference_steps: 28
    }
  }
);

// 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

Import the client:

import replicate

Run felixyifeiwang/dreamin-character using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "felixyifeiwang/dreamin-character:b8afe418b34e5ee96c2d7848db65ef3276ec921f992555d65871a87fbd1b44aa",
    input={
        "model": "dev",
        "prompt": "a TOK chibi character, a mysterious tiefling mage, empty background",
        "go_fast": False,
        "lora_scale": 1,
        "megapixels": "1",
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "webp",
        "guidance_scale": 3,
        "output_quality": 80,
        "prompt_strength": 0.8,
        "extra_lora_scale": 1,
        "num_inference_steps": 28
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run felixyifeiwang/dreamin-character 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": "felixyifeiwang/dreamin-character:b8afe418b34e5ee96c2d7848db65ef3276ec921f992555d65871a87fbd1b44aa",
    "input": {
      "model": "dev",
      "prompt": "a TOK chibi character, a mysterious tiefling mage, empty background",
      "go_fast": false,
      "lora_scale": 1,
      "megapixels": "1",
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "webp",
      "guidance_scale": 3,
      "output_quality": 80,
      "prompt_strength": 0.8,
      "extra_lora_scale": 1,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2025-01-21T00:21:42.819228Z",
  "created_at": "2025-01-21T00:21:36.079000Z",
  "data_removed": false,
  "error": null,
  "id": "pzwgvqvjsxrma0cmgrybgm18kr",
  "input": {
    "model": "dev",
    "prompt": "a TOK chibi character, a mysterious tiefling mage, empty background",
    "go_fast": false,
    "lora_scale": 1,
    "megapixels": "1",
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "webp",
    "guidance_scale": 3,
    "output_quality": 80,
    "prompt_strength": 0.8,
    "extra_lora_scale": 1,
    "num_inference_steps": 28
  },
  "logs": "2025-01-21 00:21:36.225 | DEBUG    | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys\n2025-01-21 00:21:36.226 | DEBUG    | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted\nApplying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]\nApplying LoRA:  93%|█████████▎| 283/304 [00:00<00:00, 2824.76it/s]\nApplying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2701.12it/s]\n2025-01-21 00:21:36.338 | DEBUG    | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys\n2025-01-21 00:21:36.339 | DEBUG    | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted\nApplying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]\nApplying LoRA:  60%|█████▉    | 181/304 [00:00<00:00, 1801.43it/s]\nApplying LoRA: 100%|██████████| 304/304 [00:00<00:00, 1744.41it/s]\n2025-01-21 00:21:36.513 | SUCCESS  | fp8.lora_loading:unload_loras:564 - LoRAs unloaded in 0.29s\n2025-01-21 00:21:36.515 | INFO     | fp8.lora_loading:convert_lora_weights:498 - Loading LoRA weights for /src/weights-cache/bc40ef69085e8969\n2025-01-21 00:21:36.627 | INFO     | fp8.lora_loading:convert_lora_weights:519 - LoRA weights loaded\n2025-01-21 00:21:36.627 | DEBUG    | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys\n2025-01-21 00:21:36.627 | DEBUG    | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted\nApplying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]\nApplying LoRA:  91%|█████████ | 276/304 [00:00<00:00, 2746.15it/s]\nApplying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2581.11it/s]\n2025-01-21 00:21:36.745 | SUCCESS  | fp8.lora_loading:load_lora:539 - LoRA applied in 0.23s\nUsing seed: 8460\n0it [00:00, ?it/s]\n1it [00:00,  8.38it/s]\n2it [00:00,  5.85it/s]\n3it [00:00,  5.34it/s]\n4it [00:00,  5.13it/s]\n5it [00:00,  5.01it/s]\n6it [00:01,  4.93it/s]\n7it [00:01,  4.88it/s]\n8it [00:01,  4.86it/s]\n9it [00:01,  4.84it/s]\n10it [00:01,  4.83it/s]\n11it [00:02,  4.81it/s]\n12it [00:02,  4.81it/s]\n13it [00:02,  4.81it/s]\n14it [00:02,  4.81it/s]\n15it [00:03,  4.81it/s]\n16it [00:03,  4.81it/s]\n17it [00:03,  4.80it/s]\n18it [00:03,  4.80it/s]\n19it [00:03,  4.81it/s]\n20it [00:04,  4.81it/s]\n21it [00:04,  4.80it/s]\n22it [00:04,  4.80it/s]\n23it [00:04,  4.81it/s]\n24it [00:04,  4.81it/s]\n25it [00:05,  4.81it/s]\n26it [00:05,  4.81it/s]\n27it [00:05,  4.81it/s]\n28it [00:05,  4.81it/s]\n28it [00:05,  4.88it/s]\nTotal safe images: 1 out of 1",
  "metrics": {
    "predict_time": 6.592686466,
    "total_time": 6.740228
  },
  "output": [
    "https://replicate.delivery/xezq/Y7vHhIoFpG5HBhaNAuDqIe0D4ATZs34KLWWebjZMtgyWqJHUA/out-0.webp"
  ],
  "started_at": "2025-01-21T00:21:36.226541Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-xalozp45nhii6ukgykzpgvvsvfqdmqsba5anlf5l7qqx4qfnlp3a",
    "get": "https://api.replicate.com/v1/predictions/pzwgvqvjsxrma0cmgrybgm18kr",
    "cancel": "https://api.replicate.com/v1/predictions/pzwgvqvjsxrma0cmgrybgm18kr/cancel"
  },
  "version": "b8afe418b34e5ee96c2d7848db65ef3276ec921f992555d65871a87fbd1b44aa"
}

Generated in

6.6 seconds

Tweak it Share Report

2025-01-21 00:21:36.225 | DEBUG    | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys
2025-01-21 00:21:36.226 | DEBUG    | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted
Applying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]
Applying LoRA:  93%|█████████▎| 283/304 [00:00<00:00, 2824.76it/s]
Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2701.12it/s]
2025-01-21 00:21:36.338 | DEBUG    | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys
2025-01-21 00:21:36.339 | DEBUG    | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted
Applying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]
Applying LoRA:  60%|█████▉    | 181/304 [00:00<00:00, 1801.43it/s]
Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 1744.41it/s]
2025-01-21 00:21:36.513 | SUCCESS  | fp8.lora_loading:unload_loras:564 - LoRAs unloaded in 0.29s
2025-01-21 00:21:36.515 | INFO     | fp8.lora_loading:convert_lora_weights:498 - Loading LoRA weights for /src/weights-cache/bc40ef69085e8969
2025-01-21 00:21:36.627 | INFO     | fp8.lora_loading:convert_lora_weights:519 - LoRA weights loaded
2025-01-21 00:21:36.627 | DEBUG    | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys
2025-01-21 00:21:36.627 | DEBUG    | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted
Applying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]
Applying LoRA:  91%|█████████ | 276/304 [00:00<00:00, 2746.15it/s]
Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2581.11it/s]
2025-01-21 00:21:36.745 | SUCCESS  | fp8.lora_loading:load_lora:539 - LoRA applied in 0.23s
Using seed: 8460
0it [00:00, ?it/s]
1it [00:00,  8.38it/s]
2it [00:00,  5.85it/s]
3it [00:00,  5.34it/s]
4it [00:00,  5.13it/s]
5it [00:00,  5.01it/s]
6it [00:01,  4.93it/s]
7it [00:01,  4.88it/s]
8it [00:01,  4.86it/s]
9it [00:01,  4.84it/s]
10it [00:01,  4.83it/s]
11it [00:02,  4.81it/s]
12it [00:02,  4.81it/s]
13it [00:02,  4.81it/s]
14it [00:02,  4.81it/s]
15it [00:03,  4.81it/s]
16it [00:03,  4.81it/s]
17it [00:03,  4.80it/s]
18it [00:03,  4.80it/s]
19it [00:03,  4.81it/s]
20it [00:04,  4.81it/s]
21it [00:04,  4.80it/s]
22it [00:04,  4.80it/s]
23it [00:04,  4.81it/s]
24it [00:04,  4.81it/s]
25it [00:05,  4.81it/s]
26it [00:05,  4.81it/s]
27it [00:05,  4.81it/s]
28it [00:05,  4.81it/s]
28it [00:05,  4.88it/s]
Total safe images: 1 out of 1

Want to make some of these yourself?

Run this model