digital-prairie-labs/catholic-prayers-v2.1 🖼️🔢❓📝✓ → 🖼️

▶️ 70 runs 📅 Aug 2025 ⚙️ Cog 0.13.6

About

Example Output

Prompt:

"Dios te salve, María, llena eres de gracia; el Señor es contigo."

Output

Performance Metrics

3.91s Prediction Time

4.00s Total Time

All Input Parameters

{
  "model": "dev",
  "prompt": "Dios te salve, María, llena eres de gracia; el Señor es contigo.",
  "go_fast": true,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "9:16",
  "output_format": "png",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}

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

2025-08-08 23:40:51.992 | INFO     | fp8.lora_loading:restore_base_weights:600 - Unloaded 304 layers
2025-08-08 23:40:51.995 | SUCCESS  | fp8.lora_loading:unload_loras:571 - LoRAs unloaded in 0.026s
free=24836687204352
Downloading weights
2025-08-08T23:40:52Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmp5j8tozfw/weights url=https://replicate.delivery/xezq/O3xVDeFkhfvyYEcRUU0SKSHLIegK7N1c7GM5M3J7FkmFEHSqA/flux-lora.tar
2025-08-08T23:40:52Z | INFO  | [ Cache Service ] enabled=true scheme=http target=hermes.services.svc.cluster.local
2025-08-08T23:40:52Z | INFO  | [ Cache URL Rewrite ] enabled=true target_url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/O3xVDeFkhfvyYEcRUU0SKSHLIegK7N1c7GM5M3J7FkmFEHSqA/flux-lora.tar url=https://replicate.delivery/xezq/O3xVDeFkhfvyYEcRUU0SKSHLIegK7N1c7GM5M3J7FkmFEHSqA/flux-lora.tar
2025-08-08T23:40:52Z | INFO  | [ Redirect ] redirect_url=http://r8-east4-loras-ric1.cwlota.com/b5f1af286c854706123f3523a854c18db46d3bb6a8e4d3ecfb2d18735ad0b979?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Checksum-Mode=ENABLED&X-Amz-Credential=CWNZUVKLDHXVHEZN%2F20250808%2FUS-EAST-04A%2Fs3%2Faws4_request&X-Amz-Date=20250808T234052Z&X-Amz-Expires=600&X-Amz-SignedHeaders=host&x-id=GetObject&X-Amz-Signature=b5e1a6caa5eac90880be64d06ad458e4644cb5bc6863cc9de30f9a8722212fc1 url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/O3xVDeFkhfvyYEcRUU0SKSHLIegK7N1c7GM5M3J7FkmFEHSqA/flux-lora.tar
2025-08-08T23:40:52Z | INFO  | [ Complete ] dest=/tmp/tmp5j8tozfw/weights size="172 MB" total_elapsed=0.244s url=https://replicate.delivery/xezq/O3xVDeFkhfvyYEcRUU0SKSHLIegK7N1c7GM5M3J7FkmFEHSqA/flux-lora.tar
Downloaded weights in 0.30s
2025-08-08 23:40:52.299 | INFO     | fp8.lora_loading:convert_lora_weights:502 - Loading LoRA weights for /src/weights-cache/3bc843d1d927a93d
2025-08-08 23:40:52.373 | INFO     | fp8.lora_loading:convert_lora_weights:523 - LoRA weights loaded
2025-08-08 23:40:52.373 | DEBUG    | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:610 - Extracting keys
2025-08-08 23:40:52.373 | DEBUG    | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:617 - Keys extracted
Applying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]
Applying LoRA:  43%|████▎     | 131/304 [00:00<00:00, 1301.98it/s]
Applying LoRA:  86%|████████▌ | 262/304 [00:00<00:00, 1040.80it/s]
Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 1059.70it/s]
2025-08-08 23:40:52.660 | INFO     | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:669 - Loading LoRA in fp8
2025-08-08 23:40:52.661 | SUCCESS  | fp8.lora_loading:load_lora:547 - LoRA applied in 0.36s
running quantized prediction
Using seed: 3911864408
  0%|          | 0/28 [00:00<?, ?it/s]
  7%|▋         | 2/28 [00:00<00:01, 19.92it/s]
 14%|█▍        | 4/28 [00:00<00:01, 13.17it/s]
 21%|██▏       | 6/28 [00:00<00:01, 11.90it/s]
 29%|██▊       | 8/28 [00:00<00:01, 11.36it/s]
 36%|███▌      | 10/28 [00:00<00:01, 10.97it/s]
 43%|████▎     | 12/28 [00:01<00:01, 10.66it/s]
 50%|█████     | 14/28 [00:01<00:01, 10.61it/s]
 57%|█████▋    | 16/28 [00:01<00:01, 10.59it/s]
 64%|██████▍   | 18/28 [00:01<00:00, 10.62it/s]
 71%|███████▏  | 20/28 [00:01<00:00, 10.52it/s]
 79%|███████▊  | 22/28 [00:02<00:00, 10.40it/s]
 86%|████████▌ | 24/28 [00:02<00:00, 10.38it/s]
 93%|█████████▎| 26/28 [00:02<00:00, 10.42it/s]
100%|██████████| 28/28 [00:02<00:00, 10.47it/s]
100%|██████████| 28/28 [00:02<00:00, 10.82it/s]
Total safe images: 1 out of 1

Version Details

Version ID: a433703fe1b6e92369fa6917878472ae703a3663f726c6da89a063ca78208f43
Version Created: August 8, 2025

Run on Replicate →