biggpt1/irtv-prospect 🖼️🔢❓📝✓ → 🖼️
About
Example Output
Prompt:
"
Aerial views of Prospekt Mira, the central pedestrian avenue of Vladikavkaz, lined with historic buildings, lush tree canopies, and modern infrastructure. The Ossetian mountains rise majestically in the background, their snow-capped peaks contrasting with the vibrant cityscape below.
In the distance, massive aerostats float gracefully above the city, their sleek, futuristic forms hovering silently in the clear blue sky. These advanced airships, possibly used for surveillance, transport, or communication, add a futuristic touch to the timeless beauty of Vladikavkaz, symbolizing a world where innovation and history coexist in harmony.
"Output
Performance Metrics
34.42s
Prediction Time
37.09s
Total Time
All Input Parameters
{
"model": "dev",
"prompt": "Aerial views of Prospekt Mira, the central pedestrian avenue of Vladikavkaz, lined with historic buildings, lush tree canopies, and modern infrastructure. The Ossetian mountains rise majestically in the background, their snow-capped peaks contrasting with the vibrant cityscape below.\n\nIn the distance, massive aerostats float gracefully above the city, their sleek, futuristic forms hovering silently in the clear blue sky. These advanced airships, possibly used for surveillance, transport, or communication, add a futuristic touch to the timeless beauty of Vladikavkaz, symbolizing a world where innovation and history coexist in harmony. ",
"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": 30
}
Input Parameters
- mask
- Image mask for image inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored.
- seed
- Random seed. Set for reproducible generation
- image
- Input image for image to image or inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored.
- model
- 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
- 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
- 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)
- 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
- Run faster predictions with model optimized for speed (currently fp8 quantized); disable to run in original bf16
- extra_lora
- 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
- 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
- Approximate number of megapixels for generated image
- num_outputs
- Number of outputs to generate
- aspect_ratio
- Aspect ratio for the generated image. If custom is selected, uses height and width below & will run in bf16 mode
- output_format
- Format of the output images
- guidance_scale
- 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
- 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
- Prompt strength when using img2img. 1.0 corresponds to full destruction of information in image
- extra_lora_scale
- 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
- 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
- Number of denoising steps. More steps can give more detailed images, but take longer.
- disable_safety_checker
- Disable safety checker for generated images.
Output Schema
Output
Example Execution Logs
free=28282225717248 Downloading weights 2025-03-05T19:18:24Z | INFO | [ Initiating ] chunk_size=150M dest=/tmp/tmpc3mw0lr8/weights url=https://replicate.delivery/xezq/ZORL4kJC2SL4ElyI80TCee7aU4HU2vw7YAubwEW0DMsYTlVUA/trained_model.tar 2025-03-05T19:18:27Z | INFO | [ Complete ] dest=/tmp/tmpc3mw0lr8/weights size="344 MB" total_elapsed=3.380s url=https://replicate.delivery/xezq/ZORL4kJC2SL4ElyI80TCee7aU4HU2vw7YAubwEW0DMsYTlVUA/trained_model.tar Downloaded weights in 3.41s Loaded LoRAs in 4.02s Using seed: 56346 Prompt: Aerial views of Prospekt Mira, the central pedestrian avenue of Vladikavkaz, lined with historic buildings, lush tree canopies, and modern infrastructure. The Ossetian mountains rise majestically in the background, their snow-capped peaks contrasting with the vibrant cityscape below. In the distance, massive aerostats float gracefully above the city, their sleek, futuristic forms hovering silently in the clear blue sky. These advanced airships, possibly used for surveillance, transport, or communication, add a futuristic touch to the timeless beauty of Vladikavkaz, symbolizing a world where innovation and history coexist in harmony. [!] txt2img mode 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:01<00:42, 1.45s/it] 7%|▋ | 2/30 [00:02<00:28, 1.02s/it] 10%|█ | 3/30 [00:03<00:25, 1.05it/s] 13%|█▎ | 4/30 [00:03<00:23, 1.09it/s] 17%|█▋ | 5/30 [00:04<00:22, 1.11it/s] 20%|██ | 6/30 [00:05<00:21, 1.12it/s] 23%|██▎ | 7/30 [00:06<00:20, 1.13it/s] 27%|██▋ | 8/30 [00:07<00:19, 1.14it/s] 30%|███ | 9/30 [00:08<00:18, 1.14it/s] 33%|███▎ | 10/30 [00:09<00:17, 1.14it/s] 37%|███▋ | 11/30 [00:09<00:16, 1.14it/s] 40%|████ | 12/30 [00:10<00:15, 1.14it/s] 43%|████▎ | 13/30 [00:11<00:14, 1.14it/s] 47%|████▋ | 14/30 [00:12<00:13, 1.14it/s] 50%|█████ | 15/30 [00:13<00:13, 1.15it/s] 53%|█████▎ | 16/30 [00:14<00:12, 1.15it/s] 57%|█████▋ | 17/30 [00:15<00:11, 1.15it/s] 60%|██████ | 18/30 [00:16<00:10, 1.15it/s] 63%|██████▎ | 19/30 [00:16<00:09, 1.15it/s] 67%|██████▋ | 20/30 [00:17<00:08, 1.15it/s] 70%|███████ | 21/30 [00:18<00:07, 1.15it/s] 73%|███████▎ | 22/30 [00:19<00:06, 1.15it/s] 77%|███████▋ | 23/30 [00:20<00:06, 1.15it/s] 80%|████████ | 24/30 [00:21<00:05, 1.15it/s] 83%|████████▎ | 25/30 [00:22<00:04, 1.15it/s] 87%|████████▋ | 26/30 [00:23<00:03, 1.15it/s] 90%|█████████ | 27/30 [00:23<00:02, 1.15it/s] 93%|█████████▎| 28/30 [00:24<00:01, 1.15it/s] 97%|█████████▋| 29/30 [00:25<00:00, 1.15it/s] 100%|██████████| 30/30 [00:26<00:00, 1.15it/s] 100%|██████████| 30/30 [00:26<00:00, 1.13it/s] Total safe images: 4 out of 4
Version Details
- Version ID
3070171958e2ebf14afd23fa061e285c3e1ab289d203c53de0a70220f4821441- Version Created
- March 5, 2025