biggpt1/irtv-mosque 🖼️🔢❓📝✓ → 🖼️

▶️ 56 runs 📅 Mar 2025 ⚙️ Cog 0.13.7

About

Example Output

Prompt:

A breathtaking aerial view of Vladikavkaz, Russia, featuring the historic Mukhtarov Mosque as the focal point. The mosque, with its distinctive twin minarets and intricate Oriental-style detailing, stands gracefully among the city's architectural blend of old and modern buildings. The Terek River winds through the city, reflecting the golden sunlight and flanked by lush, tree-lined streets.

In the background, the majestic Ossetian mountains rise, their rugged peaks standing tall against a brilliant blue sky. Soft clouds hover near the summits, adding depth to the composition. The city's streets bustle with activity, with visible parks, bridges, and classic European-style facades complementing the modern urban structures.

Above the city, several aerostats float gently in the distance, their soft, rounded forms contrasting with the rigid geometry of the mosque and cityscape. The sunlight casts a warm glow over the entire scene, enhancing the rich colors of the buildings and natural elements. The atmosphere is serene yet dynamic, capturing the harmony between Vladikavkaz's historical heritage and its evolving modernity

Output

Performance Metrics

36.83s Prediction Time

36.95s Total Time

All Input Parameters

{
  "model": "dev",
  "prompt": "A breathtaking aerial view of Vladikavkaz, Russia, featuring the historic Mukhtarov Mosque as the focal point. The mosque, with its distinctive twin minarets and intricate Oriental-style detailing, stands gracefully among the city's architectural blend of old and modern buildings. The Terek River winds through the city, reflecting the golden sunlight and flanked by lush, tree-lined streets.\n\nIn the background, the majestic Ossetian mountains rise, their rugged peaks standing tall against a brilliant blue sky. Soft clouds hover near the summits, adding depth to the composition. The city's streets bustle with activity, with visible parks, bridges, and classic European-style facades complementing the modern urban structures.\n\nAbove the city, several aerostats float gently in the distance, their soft, rounded forms contrasting with the rigid geometry of the mosque and cityscape. The sunlight casts a warm glow over the entire scene, enhancing the rich colors of the buildings and natural elements. The atmosphere is serene yet dynamic, capturing the harmony between Vladikavkaz's historical heritage and its evolving modernity",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 4,
  "aspect_ratio": "21:9",
  "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

free=28233142050816
Downloading weights
2025-03-05T19:18:49Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmp9n_o9xb0/weights url=https://replicate.delivery/xezq/3eE9l6fB4KvNVkpOOEn88wPVvfyGvWQzvmLlcuCTJIi1WKroA/trained_model.tar
2025-03-05T19:18:54Z | INFO  | [ Complete ] dest=/tmp/tmp9n_o9xb0/weights size="344 MB" total_elapsed=5.061s url=https://replicate.delivery/xezq/3eE9l6fB4KvNVkpOOEn88wPVvfyGvWQzvmLlcuCTJIi1WKroA/trained_model.tar
Downloaded weights in 5.09s
Loaded LoRAs in 7.74s
Using seed: 48447
Prompt: A breathtaking aerial view of Vladikavkaz, Russia, featuring the historic Mukhtarov Mosque as the focal point. The mosque, with its distinctive twin minarets and intricate Oriental-style detailing, stands gracefully among the city's architectural blend of old and modern buildings. The Terek River winds through the city, reflecting the golden sunlight and flanked by lush, tree-lined streets.
In the background, the majestic Ossetian mountains rise, their rugged peaks standing tall against a brilliant blue sky. Soft clouds hover near the summits, adding depth to the composition. The city's streets bustle with activity, with visible parks, bridges, and classic European-style facades complementing the modern urban structures.
Above the city, several aerostats float gently in the distance, their soft, rounded forms contrasting with the rigid geometry of the mosque and cityscape. The sunlight casts a warm glow over the entire scene, enhancing the rich colors of the buildings and natural elements. The atmosphere is serene yet dynamic, capturing the harmony between Vladikavkaz's historical heritage and its evolving modernity
[!] txt2img mode
  0%|          | 0/28 [00:00<?, ?it/s]
  4%|▎         | 1/28 [00:01<00:39,  1.47s/it]
  7%|▋         | 2/28 [00:02<00:26,  1.03s/it]
 11%|█         | 3/28 [00:03<00:24,  1.04it/s]
 14%|█▍        | 4/28 [00:03<00:22,  1.08it/s]
 18%|█▊        | 5/28 [00:04<00:20,  1.10it/s]
 21%|██▏       | 6/28 [00:05<00:19,  1.11it/s]
 25%|██▌       | 7/28 [00:06<00:18,  1.12it/s]
 29%|██▊       | 8/28 [00:07<00:17,  1.13it/s]
 32%|███▏      | 9/28 [00:08<00:16,  1.13it/s]
 36%|███▌      | 10/28 [00:09<00:15,  1.13it/s]
 39%|███▉      | 11/28 [00:10<00:14,  1.13it/s]
 43%|████▎     | 12/28 [00:10<00:14,  1.13it/s]
 46%|████▋     | 13/28 [00:11<00:13,  1.14it/s]
 50%|█████     | 14/28 [00:12<00:12,  1.14it/s]
 54%|█████▎    | 15/28 [00:13<00:11,  1.14it/s]
 57%|█████▋    | 16/28 [00:14<00:10,  1.14it/s]
 61%|██████    | 17/28 [00:15<00:09,  1.14it/s]
 64%|██████▍   | 18/28 [00:16<00:08,  1.14it/s]
 68%|██████▊   | 19/28 [00:17<00:07,  1.14it/s]
 71%|███████▏  | 20/28 [00:18<00:07,  1.14it/s]
 75%|███████▌  | 21/28 [00:18<00:06,  1.14it/s]
 79%|███████▊  | 22/28 [00:19<00:05,  1.14it/s]
 82%|████████▏ | 23/28 [00:20<00:04,  1.14it/s]
 86%|████████▌ | 24/28 [00:21<00:03,  1.14it/s]
 89%|████████▉ | 25/28 [00:22<00:02,  1.14it/s]
 93%|█████████▎| 26/28 [00:23<00:01,  1.14it/s]
 96%|█████████▋| 27/28 [00:24<00:00,  1.14it/s]
100%|██████████| 28/28 [00:25<00:00,  1.14it/s]
100%|██████████| 28/28 [00:25<00:00,  1.12it/s]
Total safe images: 4 out of 4

Version Details

Version ID: c5d4b8730f71a23a0a101fccc210579dc0a1f8ea495b7b917f8afb0a0c45ea4b
Version Created: March 5, 2025

Run on Replicate →