baoliwaters/sector_mvtdetectorphoto 🖼️🔢❓📝✓ → 🖼️

▶️ 172 runs 📅 May 2025 ⚙️ Cog 0.14.3

About

Example Output

Prompt:

A high-end commercial-style photo of a luxurious living room at night. The space features white walls, elegant built-in lighting, and refined furnishings: a dark designer couch, a sculptural floor lamp, a minimalist coffee table, and a potted plant in a ceramic planter. Soft warm light creates moody contrast without obscuring details.
In the doorway, a man dressed in black holds a flashlight, his beam illuminating part of the room. He appears focused, scanning the area.
sectorMvtDetectorPhoto motion detectors are Mounted discreetly in the upper corner of the walls and above the door. From it, a precise glowing red thin laser beam scans the space, visibly locking onto the man’s chest. The laser glow adds tension, suggesting detection.
The entire scene is sharp, realistic, and composed like a premium security system advertisement — with cinematic contrast, soft shadows, and no exaggerated action.

cinematic, KODAK VISION3 500T Film style, 52197219 cinematic style

Output

Performance Metrics

43.70s Prediction Time

43.72s Total Time

All Input Parameters

{
  "model": "dev",
  "prompt": "A high-end commercial-style photo of a luxurious living room at night. The space features white walls, elegant built-in lighting, and refined furnishings: a dark designer couch, a sculptural floor lamp, a minimalist coffee table, and a potted plant in a ceramic planter. Soft warm light creates moody contrast without obscuring details.\nIn the doorway, a man dressed in black holds a flashlight, his beam illuminating part of the room. He appears focused, scanning the area.\nsectorMvtDetectorPhoto motion detectors are Mounted discreetly in the upper corner of the walls and above the door. From it, a precise glowing red thin laser beam scans the space, visibly locking onto the man’s chest. The laser glow adds tension, suggesting detection.\nThe entire scene is sharp, realistic, and composed like a premium security system advertisement — with cinematic contrast, soft shadows, and no exaggerated action.\n\n\ncinematic, KODAK VISION3 500T Film style, 52197219 cinematic style",
  "go_fast": false,
  "extra_lora": "https://civitai.com/api/download/models/1659875?type=Model&format=SafeTensor&token=a71d847ee43d71bb00b7ed11cad1d126",
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 4,
  "aspect_ratio": "5:4",
  "output_format": "png",
  "guidance_scale": 3,
  "output_quality": 100,
  "prompt_strength": 0.85,
  "extra_lora_scale": 0.95,
  "num_inference_steps": 35
}

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=28332474703872
Downloading weights
2025-05-16T21:34:28Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmptl4bqv5t/weights url=https://replicate.delivery/xezq/HB6DrTDL8XI4CN0l6JueKmnfE4uAwE8Tu9c8diL9jE2nyusUA/trained_model.tar
2025-05-16T21:34:28Z | INFO  | [ Cache Service ] enabled=true scheme=http target=hermes.services.svc.cluster.local
2025-05-16T21:34:31Z | INFO  | [ Complete ] dest=/tmp/tmptl4bqv5t/weights size="172 MB" total_elapsed=2.723s url=https://replicate.delivery/xezq/HB6DrTDL8XI4CN0l6JueKmnfE4uAwE8Tu9c8diL9jE2nyusUA/trained_model.tar
Downloaded weights in 2.74s
free=28332303380480
Downloading weights
2025-05-16T21:34:31Z | INFO  | [ Initiating ] chunk_size=150M dest=/src/weights-cache/9e9f2bb282345ace url=https://civitai.com/api/download/models/1659875?type=Model&format=SafeTensor&token=a71d847ee43d71bb00b7ed11cad1d126
2025-05-16T21:34:31Z | INFO  | [ Cache Service ] enabled=true scheme=http target=hermes.services.svc.cluster.local
2025-05-16T21:34:32Z | INFO  | [ Redirect ] redirect_url=https://civitai-delivery-worker-prod.5ac0637cfd0766c97916cefa3764fbdf.r2.cloudflarestorage.com/model/1269491/cinematic20shadow20pattern.OarS.safetensors?X-Amz-Expires=86400&response-content-disposition=attachment%3B%20filename%3D%22cinematic%20shadow%20pattern%20style%20v1%20-%20cucoloris%20v2.safetensors%22&X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=e01358d793ad6966166af8b3064953ad/20250516/us-east-1/s3/aws4_request&X-Amz-Date=20250516T213432Z&X-Amz-SignedHeaders=host&X-Amz-Signature=9684733f62dde0b0e8c9a6c938e0c721f08044651e14e77155dc5c5d73899f60 url=https://civitai.com/api/download/models/1659875?type=Model&format=SafeTensor&token=a71d847ee43d71bb00b7ed11cad1d126
2025-05-16T21:34:34Z | INFO  | [ Complete ] dest=/src/weights-cache/9e9f2bb282345ace size="306 MB" total_elapsed=2.759s url=https://civitai.com/api/download/models/1659875?type=Model&format=SafeTensor&token=a71d847ee43d71bb00b7ed11cad1d126
Downloaded weights in 2.78s
Loaded LoRAs in 6.83s
Using seed: 64679
Prompt: A high-end commercial-style photo of a luxurious living room at night. The space features white walls, elegant built-in lighting, and refined furnishings: a dark designer couch, a sculptural floor lamp, a minimalist coffee table, and a potted plant in a ceramic planter. Soft warm light creates moody contrast without obscuring details.
In the doorway, a man dressed in black holds a flashlight, his beam illuminating part of the room. He appears focused, scanning the area.
sectorMvtDetectorPhoto motion detectors are Mounted discreetly in the upper corner of the walls and above the door. From it, a precise glowing red thin laser beam scans the space, visibly locking onto the man’s chest. The laser glow adds tension, suggesting detection.
The entire scene is sharp, realistic, and composed like a premium security system advertisement — with cinematic contrast, soft shadows, and no exaggerated action.
cinematic, KODAK VISION3 500T Film style, 52197219 cinematic style
[!] txt2img mode
  0%|          | 0/35 [00:00<?, ?it/s]
  3%|▎         | 1/35 [00:01<00:36,  1.07s/it]
  6%|▌         | 2/35 [00:01<00:31,  1.05it/s]
  9%|▊         | 3/35 [00:02<00:31,  1.03it/s]
 11%|█▏        | 4/35 [00:03<00:30,  1.02it/s]
 14%|█▍        | 5/35 [00:04<00:29,  1.01it/s]
 17%|█▋        | 6/35 [00:05<00:28,  1.01it/s]
 20%|██        | 7/35 [00:06<00:27,  1.00it/s]
 23%|██▎       | 8/35 [00:07<00:26,  1.00it/s]
 26%|██▌       | 9/35 [00:08<00:26,  1.00s/it]
 29%|██▊       | 10/35 [00:09<00:25,  1.00s/it]
 31%|███▏      | 11/35 [00:10<00:24,  1.00s/it]
 34%|███▍      | 12/35 [00:11<00:23,  1.00s/it]
 37%|███▋      | 13/35 [00:12<00:22,  1.00s/it]
 40%|████      | 14/35 [00:13<00:21,  1.00s/it]
 43%|████▎     | 15/35 [00:14<00:20,  1.00s/it]
 46%|████▌     | 16/35 [00:15<00:19,  1.00s/it]
 49%|████▊     | 17/35 [00:16<00:18,  1.00s/it]
 51%|█████▏    | 18/35 [00:17<00:17,  1.00s/it]
 54%|█████▍    | 19/35 [00:19<00:16,  1.00s/it]
 57%|█████▋    | 20/35 [00:20<00:15,  1.00s/it]
 60%|██████    | 21/35 [00:21<00:14,  1.01s/it]
 63%|██████▎   | 22/35 [00:22<00:13,  1.01s/it]
 66%|██████▌   | 23/35 [00:23<00:12,  1.01s/it]
 69%|██████▊   | 24/35 [00:24<00:11,  1.01s/it]
 71%|███████▏  | 25/35 [00:25<00:10,  1.00s/it]
 74%|███████▍  | 26/35 [00:26<00:09,  1.01s/it]
 77%|███████▋  | 27/35 [00:27<00:08,  1.01s/it]
 80%|████████  | 28/35 [00:28<00:07,  1.01s/it]
 83%|████████▎ | 29/35 [00:29<00:06,  1.01s/it]
 86%|████████▌ | 30/35 [00:30<00:05,  1.01s/it]
 89%|████████▊ | 31/35 [00:31<00:04,  1.01s/it]
 91%|█████████▏| 32/35 [00:32<00:03,  1.01s/it]
 94%|█████████▍| 33/35 [00:33<00:02,  1.01s/it]
 97%|█████████▋| 34/35 [00:34<00:01,  1.01s/it]
100%|██████████| 35/35 [00:35<00:00,  1.01s/it]
100%|██████████| 35/35 [00:35<00:00,  1.00s/it]
Total safe images: 4 out of 4

Version Details

Version ID: 842cda14d324d0ba02fd06f0238b6f6568040ba5d5bc6081b8d860dfdc80136e
Version Created: May 15, 2025

Run on Replicate →