nathsaranee/nath1 🖼️🔢❓📝✓ → 🖼️

▶️ 37 runs 📅 May 2025 ⚙️ Cog 0.14.3

About

Example Output

Prompt:

"nath1 studio portrait of a modestly dressed woman in a crisp white blouse, exuding calm elegance, captured in a close-up shot. Her expression is serene and graceful, with soft facial features and neatly long styled hair. Set against a warm beige-brown studio backdrop, the colors create a gentle, harmonious contrast with her white attire. The background is softly blurred to maintain focus on her face and upper shoulders. Subtle side lighting adds dimension to her features, with a soft glow enhancing her natural complexion. Drawn with: fashion editorial studio photography, cinematic close-up, soft lighting, Canon EOS R6, 85mm lens, aperture f/2.2, ISO 100, shutter speed 1/125s, ultra-high resolution, depth of field, realistic skin tone rendering."

Output

Performance Metrics

12.09s Prediction Time

14.83s Total Time

All Input Parameters

{
  "model": "dev",
  "prompt": "nath1  studio portrait of a modestly dressed woman in a crisp white blouse, exuding calm elegance, captured in a close-up shot. Her expression is serene and graceful, with soft facial features and neatly long styled hair. Set against a warm beige-brown studio backdrop, the colors create a gentle, harmonious contrast with her white attire. The background is softly blurred to maintain focus on her face and upper shoulders. Subtle side lighting adds dimension to her features, with a soft glow enhancing her natural complexion. Drawn with: fashion editorial studio photography, cinematic close-up, soft lighting, Canon EOS R6, 85mm lens, aperture f/2.2, ISO 100, shutter speed 1/125s, ultra-high resolution, depth of field, realistic skin tone rendering.",
  "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": 1,
  "extra_lora_scale": 1,
  "num_inference_steps": 34
}

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=28810607935488
Downloading weights
2025-05-10T09:33:17Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmp0ahs7c3m/weights url=https://replicate.delivery/xezq/pJewxs4SAw3vJCdvBnleuyePCLarHUyau8inp7WvgosMHYWpA/trained_model.tar
2025-05-10T09:33:17Z | INFO  | [ Cache Service ] enabled=true scheme=http target=hermes.services.svc.cluster.local
2025-05-10T09:33:20Z | INFO  | [ Complete ] dest=/tmp/tmp0ahs7c3m/weights size="172 MB" total_elapsed=2.431s url=https://replicate.delivery/xezq/pJewxs4SAw3vJCdvBnleuyePCLarHUyau8inp7WvgosMHYWpA/trained_model.tar
Downloaded weights in 2.45s
Loaded LoRAs in 3.02s
Using seed: 7403
Prompt: nath1  studio portrait of a modestly dressed woman in a crisp white blouse, exuding calm elegance, captured in a close-up shot. Her expression is serene and graceful, with soft facial features and neatly long styled hair. Set against a warm beige-brown studio backdrop, the colors create a gentle, harmonious contrast with her white attire. The background is softly blurred to maintain focus on her face and upper shoulders. Subtle side lighting adds dimension to her features, with a soft glow enhancing her natural complexion. Drawn with: fashion editorial studio photography, cinematic close-up, soft lighting, Canon EOS R6, 85mm lens, aperture f/2.2, ISO 100, shutter speed 1/125s, ultra-high resolution, depth of field, realistic skin tone rendering.
[!] txt2img mode
  0%|          | 0/34 [00:00<?, ?it/s]
  3%|▎         | 1/34 [00:00<00:08,  3.83it/s]
  6%|▌         | 2/34 [00:00<00:07,  4.34it/s]
  9%|▉         | 3/34 [00:00<00:07,  4.10it/s]
 12%|█▏        | 4/34 [00:00<00:07,  3.99it/s]
 15%|█▍        | 5/34 [00:01<00:07,  3.93it/s]
 18%|█▊        | 6/34 [00:01<00:07,  3.90it/s]
 21%|██        | 7/34 [00:01<00:06,  3.88it/s]
 24%|██▎       | 8/34 [00:02<00:06,  3.87it/s]
 26%|██▋       | 9/34 [00:02<00:06,  3.86it/s]
 29%|██▉       | 10/34 [00:02<00:06,  3.85it/s]
 32%|███▏      | 11/34 [00:02<00:05,  3.85it/s]
 35%|███▌      | 12/34 [00:03<00:05,  3.85it/s]
 38%|███▊      | 13/34 [00:03<00:05,  3.84it/s]
 41%|████      | 14/34 [00:03<00:05,  3.84it/s]
 44%|████▍     | 15/34 [00:03<00:04,  3.84it/s]
 47%|████▋     | 16/34 [00:04<00:04,  3.83it/s]
 50%|█████     | 17/34 [00:04<00:04,  3.83it/s]
 53%|█████▎    | 18/34 [00:04<00:04,  3.84it/s]
 56%|█████▌    | 19/34 [00:04<00:03,  3.84it/s]
 59%|█████▉    | 20/34 [00:05<00:03,  3.84it/s]
 62%|██████▏   | 21/34 [00:05<00:03,  3.84it/s]
 65%|██████▍   | 22/34 [00:05<00:03,  3.84it/s]
 68%|██████▊   | 23/34 [00:05<00:02,  3.83it/s]
 71%|███████   | 24/34 [00:06<00:02,  3.84it/s]
 74%|███████▎  | 25/34 [00:06<00:02,  3.84it/s]
 76%|███████▋  | 26/34 [00:06<00:02,  3.84it/s]
 79%|███████▉  | 27/34 [00:06<00:01,  3.84it/s]
 82%|████████▏ | 28/34 [00:07<00:01,  3.83it/s]
 85%|████████▌ | 29/34 [00:07<00:01,  3.84it/s]
 88%|████████▊ | 30/34 [00:07<00:01,  3.84it/s]
 91%|█████████ | 31/34 [00:08<00:00,  3.83it/s]
 94%|█████████▍| 32/34 [00:08<00:00,  3.83it/s]
 97%|█████████▋| 33/34 [00:08<00:00,  3.83it/s]
100%|██████████| 34/34 [00:08<00:00,  3.83it/s]
100%|██████████| 34/34 [00:08<00:00,  3.86it/s]
Total safe images: 1 out of 1

Version Details

Version ID: d0b28da1e1e9b35c4095bffeb44a08064b462d2d55822afdad8050308a9e4846
Version Created: May 10, 2025

Run on Replicate →