basilisk256/cygnetbottle3_21 🖼️🔢❓📝✓ → 🖼️

▶️ 90 runs 📅 Mar 2025 ⚙️ Cog 0.13.7

About

Example Output

Prompt:

"A bottle of CYG and a glass of whiskey on a glass table, with an ocean view in the background. The evening light casts a warm glow, creating an editorial photography-style scene. the setting is a gothic mansion on the scottish coastline. In the distance we can see a balcony and the ocean. This iconic photo, in the style of hasselblad, features a shallow depth of field, giving it a cinematic feel"

Output

Performance Metrics

12.52s Prediction Time

12.52s Total Time

All Input Parameters

{
  "model": "dev",
  "width": 1375,
  "height": 900,
  "prompt": "A bottle of CYG and a glass of whiskey on a glass table, with an ocean view in the background. The evening light casts a warm glow, creating an editorial photography-style scene. the setting is a gothic mansion on the scottish coastline. In the distance we can see a balcony and the ocean. This iconic photo, in the style of hasselblad, features a shallow depth of field, giving it a cinematic feel",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "custom",
  "output_format": "png",
  "guidance_scale": 3.5,
  "output_quality": 80,
  "prompt_strength": 0.6,
  "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

Weights already loaded
Loaded LoRAs in 0.03s
Using seed: 29995
Prompt: A bottle of CYG and a glass of whiskey on a glass table, with an ocean view in the background. The evening light casts a warm glow, creating an editorial photography-style scene. the setting is a gothic mansion on the scottish coastline. In the distance we can see a balcony and the ocean. This iconic photo, in the style of hasselblad, features a shallow depth of field, giving it a cinematic feel
[!] txt2img mode
  0%|          | 0/38 [00:00<?, ?it/s]
  3%|▎         | 1/38 [00:00<00:11,  3.19it/s]
  5%|▌         | 2/38 [00:00<00:09,  3.60it/s]
  8%|▊         | 3/38 [00:00<00:10,  3.40it/s]
 11%|█         | 4/38 [00:01<00:10,  3.30it/s]
 13%|█▎        | 5/38 [00:01<00:10,  3.26it/s]
 16%|█▌        | 6/38 [00:01<00:09,  3.23it/s]
 18%|█▊        | 7/38 [00:02<00:09,  3.21it/s]
 21%|██        | 8/38 [00:02<00:09,  3.20it/s]
 24%|██▎       | 9/38 [00:02<00:09,  3.19it/s]
 26%|██▋       | 10/38 [00:03<00:08,  3.18it/s]
 29%|██▉       | 11/38 [00:03<00:08,  3.18it/s]
 32%|███▏      | 12/38 [00:03<00:08,  3.18it/s]
 34%|███▍      | 13/38 [00:04<00:07,  3.18it/s]
 37%|███▋      | 14/38 [00:04<00:07,  3.18it/s]
 39%|███▉      | 15/38 [00:04<00:07,  3.18it/s]
 42%|████▏     | 16/38 [00:04<00:06,  3.17it/s]
 45%|████▍     | 17/38 [00:05<00:06,  3.18it/s]
 47%|████▋     | 18/38 [00:05<00:06,  3.18it/s]
 50%|█████     | 19/38 [00:05<00:05,  3.17it/s]
 53%|█████▎    | 20/38 [00:06<00:05,  3.18it/s]
 55%|█████▌    | 21/38 [00:06<00:05,  3.18it/s]
 58%|█████▊    | 22/38 [00:06<00:05,  3.18it/s]
 61%|██████    | 23/38 [00:07<00:04,  3.18it/s]
 63%|██████▎   | 24/38 [00:07<00:04,  3.17it/s]
 66%|██████▌   | 25/38 [00:07<00:04,  3.17it/s]
 68%|██████▊   | 26/38 [00:08<00:03,  3.17it/s]
 71%|███████   | 27/38 [00:08<00:03,  3.17it/s]
 74%|███████▎  | 28/38 [00:08<00:03,  3.17it/s]
 76%|███████▋  | 29/38 [00:09<00:02,  3.16it/s]
 79%|███████▉  | 30/38 [00:09<00:02,  3.16it/s]
 82%|████████▏ | 31/38 [00:09<00:02,  3.17it/s]
 84%|████████▍ | 32/38 [00:10<00:01,  3.17it/s]
 87%|████████▋ | 33/38 [00:10<00:01,  3.17it/s]
 89%|████████▉ | 34/38 [00:10<00:01,  3.17it/s]
 92%|█████████▏| 35/38 [00:10<00:00,  3.17it/s]
 95%|█████████▍| 36/38 [00:11<00:00,  3.17it/s]
 97%|█████████▋| 37/38 [00:11<00:00,  3.17it/s]
100%|██████████| 38/38 [00:11<00:00,  3.17it/s]
100%|██████████| 38/38 [00:11<00:00,  3.19it/s]
Total safe images: 1 out of 1

Version Details

Version ID: 637a6b4e76676f9f8da328f9917bce1b327af03d31c5a474cadb824bff03e5e0
Version Created: March 22, 2025

Run on Replicate →