emibob/testinggg-59898 🖼️🔢❓📝✓ → 🖼️

▶️ 51 runs 📅 Feb 2025 ⚙️ Cog 0.13.7

About

A fine-tuned portrait model

Example Output

Prompt:

HARDYHAR: A heartwarming, close-up moment of a couple in their mid-30s, Bavis and Baylor, in the midst of a joyous engagement. The focus is on their faces, full of raw emotion—Bavis, a tall man with slightly scruffy facial hair, is kneeling with an open ring box, his eyes locked onto Baylor’s with a mix of excitement, love, and nervous anticipation. Baylor, a radiant woman with expressive eyes and a playful energy, stands before him, her hands trembling near her mouth, her eyes wide and glistening with joyful surprise. A tear might be welling up in the corner of her eye, her lips slightly parted in a stunned smile as she processes the moment.

The engagement ring is prominently displayed, its delicate band catching the warm glow of the surrounding lights. Bavis’s hands are steady but show the slightest tension, as if holding his breath for her response. Baylor’s fingers instinctively reach toward the ring, almost hesitant to believe it’s real. The background is warm, adding to the warmth and intimacy of the moment. Their expressions radiate pure love and excitement, capturing the magic of a holiday proposal frozen in time.

Output

Performance Metrics

11.64s Prediction Time

11.82s Total Time

All Input Parameters

{
  "image": "https://replicate.delivery/pbxt/MZj8jBl0PpmeukxsTRj9xUCcBtPZVmcUBi2CaCUeXhfZXjum/Screenshot%202025-02-27%20at%205.55.11%E2%80%AFPM.png",
  "model": "dev",
  "prompt": "HARDYHAR: A heartwarming, close-up moment of a couple in their mid-30s, Bavis and Baylor, in the midst of a joyous engagement. The focus is on their faces, full of raw emotion—Bavis, a tall man with slightly scruffy facial hair, is kneeling with an open ring box, his eyes locked onto Baylor’s with a mix of excitement, love, and nervous anticipation. Baylor, a radiant woman with expressive eyes and a playful energy, stands before him, her hands trembling near her mouth, her eyes wide and glistening with joyful surprise. A tear might be welling up in the corner of her eye, her lips slightly parted in a stunned smile as she processes the moment.\n\nThe engagement ring is prominently displayed, its delicate band catching the warm glow of the surrounding lights. Bavis’s hands are steady but show the slightest tension, as if holding his breath for her response. Baylor’s fingers instinctively reach toward the ring, almost hesitant to believe it’s real. The background is warm, adding to the warmth and intimacy of the moment. Their expressions radiate pure love and excitement, capturing the magic of a holiday proposal frozen in time.",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 3,
  "output_quality": 80,
  "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

Loaded LoRAs in 2.49s
Using seed: 35043
Prompt: HARDYHAR: A heartwarming, close-up moment of a couple in their mid-30s, Bavis and Baylor, in the midst of a joyous engagement. The focus is on their faces, full of raw emotion—Bavis, a tall man with slightly scruffy facial hair, is kneeling with an open ring box, his eyes locked onto Baylor’s with a mix of excitement, love, and nervous anticipation. Baylor, a radiant woman with expressive eyes and a playful energy, stands before him, her hands trembling near her mouth, her eyes wide and glistening with joyful surprise. A tear might be welling up in the corner of her eye, her lips slightly parted in a stunned smile as she processes the moment.
The engagement ring is prominently displayed, its delicate band catching the warm glow of the surrounding lights. Bavis’s hands are steady but show the slightest tension, as if holding his breath for her response. Baylor’s fingers instinctively reach toward the ring, almost hesitant to believe it’s real. The background is warm, adding to the warmth and intimacy of the moment. Their expressions radiate pure love and excitement, capturing the magic of a holiday proposal frozen in time.
Input image size: 1822x1360
[!] Resizing input image from 1822x1360 to 1440x1088
[!] img2img mode
  0%|          | 0/23 [00:00<?, ?it/s]
  4%|▍         | 1/23 [00:00<00:06,  3.48it/s]
  9%|▊         | 2/23 [00:00<00:06,  3.04it/s]
 13%|█▎        | 3/23 [00:01<00:06,  2.90it/s]
 17%|█▋        | 4/23 [00:01<00:06,  2.85it/s]
 22%|██▏       | 5/23 [00:01<00:06,  2.82it/s]
 26%|██▌       | 6/23 [00:02<00:06,  2.81it/s]
 30%|███       | 7/23 [00:02<00:05,  2.79it/s]
 35%|███▍      | 8/23 [00:02<00:05,  2.79it/s]
 39%|███▉      | 9/23 [00:03<00:05,  2.78it/s]
 43%|████▎     | 10/23 [00:03<00:04,  2.78it/s]
 48%|████▊     | 11/23 [00:03<00:04,  2.77it/s]
 52%|█████▏    | 12/23 [00:04<00:03,  2.77it/s]
 57%|█████▋    | 13/23 [00:04<00:03,  2.77it/s]
 61%|██████    | 14/23 [00:04<00:03,  2.77it/s]
 65%|██████▌   | 15/23 [00:05<00:02,  2.77it/s]
 70%|██████▉   | 16/23 [00:05<00:02,  2.77it/s]
 74%|███████▍  | 17/23 [00:06<00:02,  2.78it/s]
 78%|███████▊  | 18/23 [00:06<00:01,  2.78it/s]
 83%|████████▎ | 19/23 [00:06<00:01,  2.77it/s]
 87%|████████▋ | 20/23 [00:07<00:01,  2.78it/s]
 91%|█████████▏| 21/23 [00:07<00:00,  2.78it/s]
 96%|█████████▌| 22/23 [00:07<00:00,  2.77it/s]
100%|██████████| 23/23 [00:08<00:00,  2.77it/s]
100%|██████████| 23/23 [00:08<00:00,  2.80it/s]
Total safe images: 1 out of 1

Version Details

Version ID: 3dab668a676b65396256110f877920825f3d9ad3cc95d43697fae11b69d0dc64
Version Created: February 28, 2025

Run on Replicate →