uxspider/rayban 🖼️🔢❓📝✓ → 🖼️

▶️ 39 runs 📅 Sep 2024 ⚙️ Cog 0.9.23
image-inpainting lora sunglasses text-to-image

About

Example Output

Prompt:

"High-end fashion photoshoot with lens focusing on sunglasses resting on a sleek white marble surface. Around the sunglasses, there are scattered Sicilian lemons, with a serene pool view as the backdrop. The attention is on the intricate details of the sunglasses, while the fresh citrus and ocean setting create a luxurious, summery atmosphere. rayban01"

Output

Example output

Performance Metrics

16.64s Prediction Time
16.65s Total Time
All Input Parameters 
{
  "model": "dev",
  "prompt": "High-end fashion photoshoot with lens focusing on sunglasses resting on a sleek white marble surface. Around the sunglasses, there are scattered Sicilian lemons, with a serene pool view as the backdrop. The attention is on the intricate details of the sunglasses, while the fresh citrus and ocean setting create a luxurious, summery atmosphere. rayban01",
  "lora_scale": 1,
  "num_outputs": 1,
  "aspect_ratio": "2:3",
  "output_format": "png",
  "guidance_scale": 2.77,
  "output_quality": 100,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 26
}
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 
Using seed: 62912
Prompt: High-end fashion photoshoot with lens focusing on sunglasses resting on a sleek white marble surface. Around the sunglasses, there are scattered Sicilian lemons, with a serene pool view as the backdrop. The attention is on the intricate details of the sunglasses, while the fresh citrus and ocean setting create a luxurious, summery atmosphere. rayban01
[!] txt2img mode
Using dev model
Loaded LoRAs in 1.79s
  0%|          | 0/26 [00:00<?, ?it/s]
  4%|▍         | 1/26 [00:00<00:13,  1.87it/s]
  8%|▊         | 2/26 [00:00<00:11,  2.15it/s]
 12%|█▏        | 3/26 [00:01<00:11,  2.01it/s]
 15%|█▌        | 4/26 [00:02<00:11,  1.95it/s]
 19%|█▉        | 5/26 [00:02<00:10,  1.92it/s]
 23%|██▎       | 6/26 [00:03<00:10,  1.90it/s]
 27%|██▋       | 7/26 [00:03<00:10,  1.88it/s]
 31%|███       | 8/26 [00:04<00:09,  1.87it/s]
 35%|███▍      | 9/26 [00:04<00:09,  1.87it/s]
 38%|███▊      | 10/26 [00:05<00:08,  1.86it/s]
 42%|████▏     | 11/26 [00:05<00:08,  1.86it/s]
 46%|████▌     | 12/26 [00:06<00:07,  1.86it/s]
 50%|█████     | 13/26 [00:06<00:06,  1.86it/s]
 54%|█████▍    | 14/26 [00:07<00:06,  1.86it/s]
 58%|█████▊    | 15/26 [00:07<00:05,  1.86it/s]
 62%|██████▏   | 16/26 [00:08<00:05,  1.86it/s]
 65%|██████▌   | 17/26 [00:09<00:04,  1.86it/s]
 69%|██████▉   | 18/26 [00:09<00:04,  1.86it/s]
 73%|███████▎  | 19/26 [00:10<00:03,  1.86it/s]
 77%|███████▋  | 20/26 [00:10<00:03,  1.86it/s]
 81%|████████  | 21/26 [00:11<00:02,  1.86it/s]
 85%|████████▍ | 22/26 [00:11<00:02,  1.86it/s]
 88%|████████▊ | 23/26 [00:12<00:01,  1.86it/s]
 92%|█████████▏| 24/26 [00:12<00:01,  1.86it/s]
 96%|█████████▌| 25/26 [00:13<00:00,  1.86it/s]
100%|██████████| 26/26 [00:13<00:00,  1.86it/s]
100%|██████████| 26/26 [00:13<00:00,  1.87it/s]
Version Details
Version ID
e2938ca8064bff58ea888d6595df68154f23d103c54bd428e48725a179e6d2dc
Version Created
September 26, 2024
Run on Replicate →