adtechnacityai/amz_driver 🖼️🔢❓📝✓ → 🖼️

▶️ 21 runs 📅 Feb 2025 ⚙️ Cog 0.13.7

About

Example Output

Prompt:

"In a spacious warehouse setting, a man stands confidently in front of a sleek, modern delivery van. The van is painted in a metallic gray with a large, prominent "Prime" logo featuring the recognizable Amazon smile icon in blue. The van\'s side door is open, revealing a well-organized interior with shelves and compartments, suggesting it is equipped for efficient package delivery. The man is wearing a high-visibility orange vest over a dark sweater and black pants, indicating he is likely a delivery driver or a warehouse worker. His arms are outstretched, possibly to emphasize the size or capacity of the van. The warehouse has a high ceiling with large windows, allowing natural light to flood the space, and there are other vehicles and equipment visible in the background. The overall scene conveys a sense of efficiency and readiness for delivery operations"

Output

Performance Metrics

22.20s Prediction Time

22.23s Total Time

All Input Parameters

{
  "model": "dev",
  "prompt": "In a spacious warehouse setting, a man stands confidently in front of a sleek, modern delivery van. The van is painted in a metallic gray with a large, prominent \"Prime\" logo featuring the recognizable Amazon smile icon in blue. The van\\'s side door is open, revealing a well-organized interior with shelves and compartments, suggesting it is equipped for efficient package delivery. The man is wearing a high-visibility orange vest over a dark sweater and black pants, indicating he is likely a delivery driver or a warehouse worker. His arms are outstretched, possibly to emphasize the size or capacity of the van. The warehouse has a high ceiling with large windows, allowing natural light to flood the space, and there are other vehicles and equipment visible in the background. The overall scene conveys a sense of efficiency and readiness for delivery operations",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 2,
  "aspect_ratio": "16:9",
  "output_format": "webp",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.88,
  "extra_lora_scale": 1,
  "num_inference_steps": 38
}

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=29588910219264
Downloading weights
2025-02-18T20:09:37Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmp4fweoxct/weights url=https://replicate.delivery/xezq/1a7iHakeQixUfEegKlQDmAyjuf8yUgcf6Uh4sEwcmOw0LzyhC/trained_model.tar
2025-02-18T20:09:39Z | INFO  | [ Complete ] dest=/tmp/tmp4fweoxct/weights size="226 MB" total_elapsed=1.722s url=https://replicate.delivery/xezq/1a7iHakeQixUfEegKlQDmAyjuf8yUgcf6Uh4sEwcmOw0LzyhC/trained_model.tar
Downloaded weights in 1.75s
Loaded LoRAs in 2.32s
Using seed: 52609
Prompt: In a spacious warehouse setting, a man stands confidently in front of a sleek, modern delivery van. The van is painted in a metallic gray with a large, prominent "Prime" logo featuring the recognizable Amazon smile icon in blue. The van\'s side door is open, revealing a well-organized interior with shelves and compartments, suggesting it is equipped for efficient package delivery. The man is wearing a high-visibility orange vest over a dark sweater and black pants, indicating he is likely a delivery driver or a warehouse worker. His arms are outstretched, possibly to emphasize the size or capacity of the van. The warehouse has a high ceiling with large windows, allowing natural light to flood the space, and there are other vehicles and equipment visible in the background. The overall scene conveys a sense of efficiency and readiness for delivery operations
[!] txt2img mode
  0%|          | 0/38 [00:00<?, ?it/s]
  3%|▎         | 1/38 [00:00<00:18,  1.95it/s]
  5%|▌         | 2/38 [00:00<00:16,  2.21it/s]
  8%|▊         | 3/38 [00:01<00:16,  2.09it/s]
 11%|█         | 4/38 [00:01<00:16,  2.03it/s]
 13%|█▎        | 5/38 [00:02<00:16,  2.01it/s]
 16%|█▌        | 6/38 [00:02<00:16,  1.99it/s]
 18%|█▊        | 7/38 [00:03<00:15,  1.98it/s]
 21%|██        | 8/38 [00:03<00:15,  1.97it/s]
 24%|██▎       | 9/38 [00:04<00:14,  1.97it/s]
 26%|██▋       | 10/38 [00:05<00:14,  1.96it/s]
 29%|██▉       | 11/38 [00:05<00:13,  1.96it/s]
 32%|███▏      | 12/38 [00:06<00:13,  1.96it/s]
 34%|███▍      | 13/38 [00:06<00:12,  1.96it/s]
 37%|███▋      | 14/38 [00:07<00:12,  1.96it/s]
 39%|███▉      | 15/38 [00:07<00:11,  1.96it/s]
 42%|████▏     | 16/38 [00:08<00:11,  1.96it/s]
 45%|████▍     | 17/38 [00:08<00:10,  1.96it/s]
 47%|████▋     | 18/38 [00:09<00:10,  1.96it/s]
 50%|█████     | 19/38 [00:09<00:09,  1.96it/s]
 53%|█████▎    | 20/38 [00:10<00:09,  1.96it/s]
 55%|█████▌    | 21/38 [00:10<00:08,  1.96it/s]
 58%|█████▊    | 22/38 [00:11<00:08,  1.96it/s]
 61%|██████    | 23/38 [00:11<00:07,  1.96it/s]
 63%|██████▎   | 24/38 [00:12<00:07,  1.95it/s]
 66%|██████▌   | 25/38 [00:12<00:06,  1.96it/s]
 68%|██████▊   | 26/38 [00:13<00:06,  1.96it/s]
 71%|███████   | 27/38 [00:13<00:05,  1.96it/s]
 74%|███████▎  | 28/38 [00:14<00:05,  1.96it/s]
 76%|███████▋  | 29/38 [00:14<00:04,  1.95it/s]
 79%|███████▉  | 30/38 [00:15<00:04,  1.95it/s]
 82%|████████▏ | 31/38 [00:15<00:03,  1.95it/s]
 84%|████████▍ | 32/38 [00:16<00:03,  1.95it/s]
 87%|████████▋ | 33/38 [00:16<00:02,  1.95it/s]
 89%|████████▉ | 34/38 [00:17<00:02,  1.95it/s]
 92%|█████████▏| 35/38 [00:17<00:01,  1.95it/s]
 95%|█████████▍| 36/38 [00:18<00:01,  1.95it/s]
 97%|█████████▋| 37/38 [00:18<00:00,  1.95it/s]
100%|██████████| 38/38 [00:19<00:00,  1.95it/s]
100%|██████████| 38/38 [00:19<00:00,  1.96it/s]
Total safe images: 2 out of 2

Version Details

Version ID: 6687ce5f57a4723740af4725e3f9720a934195a3e2d71b817800100db321deab
Version Created: February 11, 2025

Run on Replicate →