brandnexus/metarb 🖼️🔢❓📝✓ → 🖼️

▶️ 73 runs 📅 Sep 2024 ⚙️ Cog 0.9.23

About

Example Output

Prompt:

MetaRB reate a photorealistic image of MetaRB glasses resting on a smooth rock at the top of Corcovado Mountain in Rio de Janeiro, with the Christ the Redeemer statue visible in the background. The sunglasses, with sleek black frames and reflective lenses, are positioned at an angle that captures the panoramic view of the cityscape and the distant coastline reflected on the lenses. The sunlight glints off the frames, highlighting their elegant design, while the lush greenery surrounding the rock adds a touch of natural beauty.

The image is taken using a Canon EOS R6 with a 35mm f/1.4 lens, set to f/4.0 for a balanced depth of field, ISO 100, and a shutter speed of 1/1000 sec. The focus is sharp on the sunglasses, with the iconic statue and sweeping view of Rio slightly blurred in the background, emphasizing the product while still showcasing the stunning location.

Output

Performance Metrics

20.98s Prediction Time

26.44s Total Time

All Input Parameters

{
  "model": "dev",
  "prompt": "MetaRB reate a photorealistic image of MetaRB glasses resting on a smooth rock at the top of Corcovado Mountain in Rio de Janeiro, with the Christ the Redeemer statue visible in the background. The sunglasses, with sleek black frames and reflective lenses, are positioned at an angle that captures the panoramic view of the cityscape and the distant coastline reflected on the lenses. The sunlight glints off the frames, highlighting their elegant design, while the lush greenery surrounding the rock adds a touch of natural beauty.\n\nThe image is taken using a Canon EOS R6 with a 35mm f/1.4 lens, set to f/4.0 for a balanced depth of field, ISO 100, and a shutter speed of 1/1000 sec. The focus is sharp on the sunglasses, with the iconic statue and sweeping view of Rio slightly blurred in the background, emphasizing the product while still showcasing the stunning location.",
  "lora_scale": 1,
  "num_outputs": 1,
  "aspect_ratio": "3:4",
  "output_format": "webp",
  "guidance_scale": 3.5,
  "output_quality": 90,
  "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

Using seed: 38556
Prompt: MetaRB reate a photorealistic image of MetaRB glasses resting on a smooth rock at the top of Corcovado Mountain in Rio de Janeiro, with the Christ the Redeemer statue visible in the background. The sunglasses, with sleek black frames and reflective lenses, are positioned at an angle that captures the panoramic view of the cityscape and the distant coastline reflected on the lenses. The sunlight glints off the frames, highlighting their elegant design, while the lush greenery surrounding the rock adds a touch of natural beauty.
The image is taken using a Canon EOS R6 with a 35mm f/1.4 lens, set to f/4.0 for a balanced depth of field, ISO 100, and a shutter speed of 1/1000 sec. The focus is sharp on the sunglasses, with the iconic statue and sweeping view of Rio slightly blurred in the background, emphasizing the product while still showcasing the stunning location.
[!] txt2img mode
Using dev model
free=3151374938112
Downloading weights
2024-09-28T18:43:08Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpjgedxqkl/weights url=https://replicate.delivery/yhqm/jmBu80LIIv7vOZoTlPfA32IBfG93HUB9AfSw0ofAosTN96FOB/trained_model.tar
2024-09-28T18:43:10Z | INFO  | [ Complete ] dest=/tmp/tmpjgedxqkl/weights size="172 MB" total_elapsed=1.542s url=https://replicate.delivery/yhqm/jmBu80LIIv7vOZoTlPfA32IBfG93HUB9AfSw0ofAosTN96FOB/trained_model.tar
Downloaded weights in 1.57s
Loaded LoRAs in 2.42s
  0%|          | 0/28 [00:00<?, ?it/s]
  4%|▎         | 1/28 [00:00<00:17,  1.56it/s]
  7%|▋         | 2/28 [00:01<00:14,  1.76it/s]
 11%|█         | 3/28 [00:01<00:15,  1.66it/s]
 14%|█▍        | 4/28 [00:02<00:14,  1.62it/s]
 18%|█▊        | 5/28 [00:03<00:14,  1.60it/s]
 21%|██▏       | 6/28 [00:03<00:13,  1.59it/s]
 25%|██▌       | 7/28 [00:04<00:13,  1.58it/s]
 29%|██▊       | 8/28 [00:04<00:12,  1.57it/s]
 32%|███▏      | 9/28 [00:05<00:12,  1.57it/s]
 36%|███▌      | 10/28 [00:06<00:11,  1.57it/s]
 39%|███▉      | 11/28 [00:06<00:10,  1.56it/s]
 43%|████▎     | 12/28 [00:07<00:10,  1.56it/s]
 46%|████▋     | 13/28 [00:08<00:09,  1.56it/s]
 50%|█████     | 14/28 [00:08<00:08,  1.56it/s]
 54%|█████▎    | 15/28 [00:09<00:08,  1.56it/s]
 57%|█████▋    | 16/28 [00:10<00:07,  1.56it/s]
 61%|██████    | 17/28 [00:10<00:07,  1.56it/s]
 64%|██████▍   | 18/28 [00:11<00:06,  1.56it/s]
 68%|██████▊   | 19/28 [00:12<00:05,  1.56it/s]
 71%|███████▏  | 20/28 [00:12<00:05,  1.56it/s]
 75%|███████▌  | 21/28 [00:13<00:04,  1.56it/s]
 79%|███████▊  | 22/28 [00:13<00:03,  1.56it/s]
 82%|████████▏ | 23/28 [00:14<00:03,  1.56it/s]
 86%|████████▌ | 24/28 [00:15<00:02,  1.56it/s]
 89%|████████▉ | 25/28 [00:15<00:01,  1.56it/s]
 93%|█████████▎| 26/28 [00:16<00:01,  1.56it/s]
 96%|█████████▋| 27/28 [00:17<00:00,  1.56it/s]
100%|██████████| 28/28 [00:17<00:00,  1.56it/s]
100%|██████████| 28/28 [00:17<00:00,  1.57it/s]

Version Details

Version ID: e29cc674090af7fb63eb12920984958de0e6ffa8ddb2da934748bfbc49f45bf0
Version Created: September 28, 2024

Run on Replicate →