parkjaewoo-1/cat_rudy_v2 🖼️🔢❓📝✓ → 🖼️

▶️ 54 runs 📅 Oct 2025 ⚙️ Cog 0.15.3

About

Example Output

Prompt:

"Ultra-photorealistic studio photograph of CATRUDY, a moderately plump ginger domestic short-haired cat with round soft cheeks, golden-green eyes, small rounded ears, and a soft pink nose. CATRUDY is sitting upright behind a warm wooden table, black seamless background, cinematic soft lighting (key light 45 degrees, fill light -1 stop), 85mm lens, shallow depth of field, realistic fur texture with fine micro-strands, 8k RAW photo look."

Output

Performance Metrics

41.90s Prediction Time

41.93s Total Time

All Input Parameters

{
  "seed": 1001,
  "model": "dev",
  "prompt": "Ultra-photorealistic studio photograph of CATRUDY, a moderately plump ginger domestic short-haired cat with round soft cheeks, golden-green eyes, small rounded ears, and a soft pink nose. CATRUDY is sitting upright behind a warm wooden table, black seamless background, cinematic soft lighting (key light 45 degrees, fill light -1 stop), 85mm lens, shallow depth of field, realistic fur texture with fine micro-strands, 8k RAW photo look.",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 4,
  "aspect_ratio": "1:1",
  "output_format": "png",
  "guidance_scale": 2,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 40
}

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=23550006898688
Downloading weights
2025-10-09T17:48:11Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpi1ac6iin/weights url=https://replicate.delivery/xezq/UpfuT4bjCP3NBKfxy3n0V6XQ530HPRdIOvLOBR08dhghfz6qA/trained_model.tar
2025-10-09T17:48:11Z | INFO  | [ Cache Service ] enabled=true scheme=http target=hermes.services.svc.cluster.local
2025-10-09T17:48:11Z | INFO  | [ Cache URL Rewrite ] enabled=true target_url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/UpfuT4bjCP3NBKfxy3n0V6XQ530HPRdIOvLOBR08dhghfz6qA/trained_model.tar url=https://replicate.delivery/xezq/UpfuT4bjCP3NBKfxy3n0V6XQ530HPRdIOvLOBR08dhghfz6qA/trained_model.tar
2025-10-09T17:48:11Z | INFO  | [ Redirect ] redirect_url=http://r8-east4-loras-ric1.cwlota.com/8aecc8cda0734766fb55a7f577d0fc2b1015b317529274c808b1968c9b3a7676?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Checksum-Mode=ENABLED&X-Amz-Credential=CWNZUVKLDHXVHEZN%2F20251009%2FUS-EAST-04A%2Fs3%2Faws4_request&X-Amz-Date=20251009T174811Z&X-Amz-Expires=600&X-Amz-SignedHeaders=host&x-id=GetObject&X-Amz-Signature=2cee4d2719e1f2970a742d3e6972587ce7550b3a764fec31a6d3344480a1c5e8 url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/UpfuT4bjCP3NBKfxy3n0V6XQ530HPRdIOvLOBR08dhghfz6qA/trained_model.tar
2025-10-09T17:48:12Z | INFO  | [ Complete ] dest=/tmp/tmpi1ac6iin/weights size="688 MB" total_elapsed=0.748s url=https://replicate.delivery/xezq/UpfuT4bjCP3NBKfxy3n0V6XQ530HPRdIOvLOBR08dhghfz6qA/trained_model.tar
Downloaded weights in 0.82s
Loaded LoRAs in 1.49s
Using seed: 1001
Prompt: Ultra-photorealistic studio photograph of CATRUDY, a moderately plump ginger domestic short-haired cat with round soft cheeks, golden-green eyes, small rounded ears, and a soft pink nose. CATRUDY is sitting upright behind a warm wooden table, black seamless background, cinematic soft lighting (key light 45 degrees, fill light -1 stop), 85mm lens, shallow depth of field, realistic fur texture with fine micro-strands, 8k RAW photo look.
[!] txt2img mode
  0%|          | 0/40 [00:00<?, ?it/s]
  2%|▎         | 1/40 [00:00<00:37,  1.03it/s]
  5%|▌         | 2/40 [00:01<00:32,  1.16it/s]
  8%|▊         | 3/40 [00:02<00:33,  1.10it/s]
 10%|█         | 4/40 [00:03<00:33,  1.07it/s]
 12%|█▎        | 5/40 [00:04<00:33,  1.05it/s]
 15%|█▌        | 6/40 [00:05<00:32,  1.04it/s]
 18%|█▊        | 7/40 [00:06<00:31,  1.04it/s]
 20%|██        | 8/40 [00:07<00:30,  1.04it/s]
 22%|██▎       | 9/40 [00:08<00:29,  1.03it/s]
 25%|██▌       | 10/40 [00:09<00:29,  1.03it/s]
 28%|██▊       | 11/40 [00:10<00:28,  1.03it/s]
 30%|███       | 12/40 [00:11<00:27,  1.03it/s]
 32%|███▎      | 13/40 [00:12<00:26,  1.03it/s]
 35%|███▌      | 14/40 [00:13<00:25,  1.03it/s]
 38%|███▊      | 15/40 [00:14<00:24,  1.03it/s]
 40%|████      | 16/40 [00:15<00:23,  1.03it/s]
 42%|████▎     | 17/40 [00:16<00:22,  1.03it/s]
 45%|████▌     | 18/40 [00:17<00:21,  1.03it/s]
 48%|████▊     | 19/40 [00:18<00:20,  1.03it/s]
 50%|█████     | 20/40 [00:19<00:19,  1.03it/s]
 52%|█████▎    | 21/40 [00:20<00:18,  1.03it/s]
 55%|█████▌    | 22/40 [00:21<00:17,  1.03it/s]
 57%|█████▊    | 23/40 [00:22<00:16,  1.03it/s]
 60%|██████    | 24/40 [00:23<00:15,  1.03it/s]
 62%|██████▎   | 25/40 [00:24<00:14,  1.03it/s]
 65%|██████▌   | 26/40 [00:25<00:13,  1.03it/s]
 68%|██████▊   | 27/40 [00:26<00:12,  1.03it/s]
 70%|███████   | 28/40 [00:27<00:11,  1.03it/s]
 72%|███████▎  | 29/40 [00:28<00:10,  1.03it/s]
 75%|███████▌  | 30/40 [00:28<00:09,  1.03it/s]
 78%|███████▊  | 31/40 [00:29<00:08,  1.03it/s]
 80%|████████  | 32/40 [00:30<00:07,  1.03it/s]
 82%|████████▎ | 33/40 [00:31<00:06,  1.03it/s]
 85%|████████▌ | 34/40 [00:32<00:05,  1.03it/s]
 88%|████████▊ | 35/40 [00:33<00:04,  1.03it/s]
 90%|█████████ | 36/40 [00:34<00:03,  1.03it/s]
 92%|█████████▎| 37/40 [00:35<00:02,  1.03it/s]
 95%|█████████▌| 38/40 [00:36<00:01,  1.03it/s]
 98%|█████████▊| 39/40 [00:37<00:00,  1.03it/s]
100%|██████████| 40/40 [00:38<00:00,  1.03it/s]
100%|██████████| 40/40 [00:38<00:00,  1.03it/s]
Total safe images: 4 out of 4

Version Details

Version ID: 08ea3dfde168eed9cdc4956ba0e9a506f56c9f74f96c0809a3250d10a9c77986
Version Created: October 9, 2025

Run on Replicate →