lailamasiqbal/pcece 🖼️🔢❓📝✓ → 🖼️

▶️ 37 runs 📅 Feb 2025 ⚙️ Cog 0.13.7

About

Example Output

Prompt:

"a photo of PCECE, a Chinese girl, age 8, studying attentively in the study room, wearing red Chinese cloth, her eyes are on the book, hands on the book, in front of her is a book and computer, hyper realistic, dim light, lighting GODOX led"

Output

Performance Metrics

35.74s Prediction Time

35.85s Total Time

All Input Parameters

{
  "model": "dev",
  "prompt": "a photo of PCECE, a Chinese girl, age 8, studying attentively in the study room, wearing red Chinese cloth, her eyes are on the book, hands on the book, in front of her is a book and computer, hyper realistic, dim light, lighting GODOX led",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 4,
  "aspect_ratio": "16:9",
  "output_format": "jpg",
  "guidance_scale": 3.5,
  "output_quality": 100,
  "prompt_strength": 0.72,
  "extra_lora_scale": 1,
  "num_inference_steps": 34
}

Input Parameters

mask Type: string: Image mask for image inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored.
seed Type: integer: Random seed. Set for reproducible generation
image Type: string: Input image for image to image or inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored.
model Default: dev: Which model to run inference with. The dev model performs best with around 28 inference steps but the schnell model only needs 4 steps.
width Type: integerRange: 256 - 1440: Width of generated image. Only works if `aspect_ratio` is set to custom. Will be rounded to nearest multiple of 16. Incompatible with fast generation
height Type: integerRange: 256 - 1440: Height of generated image. Only works if `aspect_ratio` is set to custom. Will be rounded to nearest multiple of 16. Incompatible with fast generation
prompt (required) Type: string: Prompt for generated image. If you include the `trigger_word` used in the training process you are more likely to activate the trained object, style, or concept in the resulting image.
go_fast Type: booleanDefault: false: Run faster predictions with model optimized for speed (currently fp8 quantized); disable to run in original bf16
extra_lora Type: string: Load LoRA weights. Supports Replicate models in the format <owner>/<username> or <owner>/<username>/<version>, HuggingFace URLs in the format huggingface.co/<owner>/<model-name>, CivitAI URLs in the format civitai.com/models/<id>[/<model-name>], or arbitrary .safetensors URLs from the Internet. For example, 'fofr/flux-pixar-cars'
lora_scale Type: numberDefault: 1Range: -1 - 3: Determines how strongly the main LoRA should be applied. Sane results between 0 and 1 for base inference. For go_fast we apply a 1.5x multiplier to this value; we've generally seen good performance when scaling the base value by that amount. You may still need to experiment to find the best value for your particular lora.
megapixels Default: 1: Approximate number of megapixels for generated image
num_outputs Type: integerDefault: 1Range: 1 - 4: Number of outputs to generate
aspect_ratio Default: 1:1: Aspect ratio for the generated image. If custom is selected, uses height and width below & will run in bf16 mode
output_format Default: webp: Format of the output images
guidance_scale Type: numberDefault: 3Range: 0 - 10: Guidance scale for the diffusion process. Lower values can give more realistic images. Good values to try are 2, 2.5, 3 and 3.5
output_quality Type: integerDefault: 80Range: 0 - 100: Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs
prompt_strength Type: numberDefault: 0.8Range: 0 - 1: Prompt strength when using img2img. 1.0 corresponds to full destruction of information in image
extra_lora_scale Type: numberDefault: 1Range: -1 - 3: Determines how strongly the extra LoRA should be applied. Sane results between 0 and 1 for base inference. For go_fast we apply a 1.5x multiplier to this value; we've generally seen good performance when scaling the base value by that amount. You may still need to experiment to find the best value for your particular lora.
replicate_weights Type: string: Load LoRA weights. Supports Replicate models in the format <owner>/<username> or <owner>/<username>/<version>, HuggingFace URLs in the format huggingface.co/<owner>/<model-name>, CivitAI URLs in the format civitai.com/models/<id>[/<model-name>], or arbitrary .safetensors URLs from the Internet. For example, 'fofr/flux-pixar-cars'
num_inference_steps Type: integerDefault: 28Range: 1 - 50: Number of denoising steps. More steps can give more detailed images, but take longer.
disable_safety_checker Type: booleanDefault: false: Disable safety checker for generated images.

Output Schema

Output

Type: array • Items Type: string • Items Format: uri

Example Execution Logs

free=28987521327104
Downloading weights
2025-02-05T01:14:45Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpdbu388_k/weights url=https://replicate.delivery/xezq/ZCfu7gPofPhD3EzBap8UpKZE195SsKF2eIu0DZznD7NIwKYoA/trained_model.tar
2025-02-05T01:14:47Z | INFO  | [ Complete ] dest=/tmp/tmpdbu388_k/weights size="644 MB" total_elapsed=2.184s url=https://replicate.delivery/xezq/ZCfu7gPofPhD3EzBap8UpKZE195SsKF2eIu0DZznD7NIwKYoA/trained_model.tar
Downloaded weights in 2.22s
Loaded LoRAs in 2.88s
Using seed: 20311
Prompt: a photo of PCECE, a Chinese girl, age 8, studying attentively in the study room, wearing red Chinese cloth, her eyes are on the book, hands on the book, in front of her is a book and computer, hyper realistic, dim light, lighting GODOX led
[!] txt2img mode
  0%|          | 0/34 [00:00<?, ?it/s]
  3%|▎         | 1/34 [00:00<00:31,  1.06it/s]
  6%|▌         | 2/34 [00:01<00:26,  1.21it/s]
  9%|▉         | 3/34 [00:02<00:27,  1.14it/s]
 12%|█▏        | 4/34 [00:03<00:27,  1.10it/s]
 15%|█▍        | 5/34 [00:04<00:26,  1.08it/s]
 18%|█▊        | 6/34 [00:05<00:26,  1.07it/s]
 21%|██        | 7/34 [00:06<00:25,  1.07it/s]
 24%|██▎       | 8/34 [00:07<00:24,  1.06it/s]
 26%|██▋       | 9/34 [00:08<00:23,  1.06it/s]
 29%|██▉       | 10/34 [00:09<00:22,  1.06it/s]
 32%|███▏      | 11/34 [00:10<00:21,  1.06it/s]
 35%|███▌      | 12/34 [00:11<00:20,  1.06it/s]
 38%|███▊      | 13/34 [00:12<00:19,  1.06it/s]
 41%|████      | 14/34 [00:13<00:18,  1.05it/s]
 44%|████▍     | 15/34 [00:14<00:18,  1.06it/s]
 47%|████▋     | 16/34 [00:14<00:17,  1.05it/s]
 50%|█████     | 17/34 [00:15<00:16,  1.05it/s]
 53%|█████▎    | 18/34 [00:16<00:15,  1.05it/s]
 56%|█████▌    | 19/34 [00:17<00:14,  1.05it/s]
 59%|█████▉    | 20/34 [00:18<00:13,  1.05it/s]
 62%|██████▏   | 21/34 [00:19<00:12,  1.05it/s]
 65%|██████▍   | 22/34 [00:20<00:11,  1.05it/s]
 68%|██████▊   | 23/34 [00:21<00:10,  1.05it/s]
 71%|███████   | 24/34 [00:22<00:09,  1.05it/s]
 74%|███████▎  | 25/34 [00:23<00:08,  1.05it/s]
 76%|███████▋  | 26/34 [00:24<00:07,  1.05it/s]
 79%|███████▉  | 27/34 [00:25<00:06,  1.05it/s]
 82%|████████▏ | 28/34 [00:26<00:05,  1.05it/s]
 85%|████████▌ | 29/34 [00:27<00:04,  1.05it/s]
 88%|████████▊ | 30/34 [00:28<00:03,  1.05it/s]
 91%|█████████ | 31/34 [00:29<00:02,  1.05it/s]
 94%|█████████▍| 32/34 [00:30<00:01,  1.05it/s]
 97%|█████████▋| 33/34 [00:31<00:00,  1.05it/s]
100%|██████████| 34/34 [00:32<00:00,  1.05it/s]
100%|██████████| 34/34 [00:32<00:00,  1.06it/s]
Total safe images: 4 out of 4

Version Details

Version ID: 3ae02905d20482bb10b24e3b70f81f290c4e6b212d85c7e384f48944a8023b74
Version Created: February 4, 2025

Run on Replicate →