rrsimmonds/xshnx3500 🖼️🔢❓📝✓ → 🖼️

▶️ 1.5K runs 📅 Sep 2024 ⚙️ Cog 0.9.23

About

Example Output

Prompt:

"The image shows a XshnX woman, possibly in her late thirties or early forties , with brown hair. She appears to be lounging back legs bent on a sofa looking directly at viewer, alone in a brightly lit dive hotel room. The woman is wearing an extra loose fitting men’s long sleeved button down dress shirt that is fully unbuttoned and completely open in the front to expose her cleavage but still covering her nipples and lace thong panties. The woman seems to be of Caucasian race, with a potentially upper-middle-class income, possibly between $50,000 and $100,000 per year. Her religious beliefs and political affiliations are difficult to ascertain from just an image. She appears calm and content, possibly slightly playful, in the image. Her clothing suggests a relaxed and comfortable demeanor, although her makeup is rather precise and suggests an interest in beauty and style. Some potential interests include fashion, makeup, and photography, and, potentially, online gaming or social media, shopping, and excessive screen time. She seems serene and stylish, radiating an aura of quiet confidence. We can target her with beauty products, luxury items and subscription boxes, such as Sephora collections, Glossier skincare, and Stitch Fix styling services, and other similar premium goods."

Output

Performance Metrics

12.60s Prediction Time

43.87s Total Time

All Input Parameters

{
"model": "dev",
"width": 1024,
"height": 768,
"prompt": "The image shows a XshnX woman, possibly in her late thirties or early forties , with brown hair. She appears to be lounging back legs bent on a sofa looking directly at viewer, alone in a brightly lit dive hotel room. The woman is wearing an extra loose fitting men’s long sleeved button down dress shirt that is fully unbuttoned and completely open in the front to expose her cleavage but still covering her nipples and lace thong panties. The woman seems to be of Caucasian race, with a potentially upper-middle-class income, possibly between $50,000 and $100,000 per year. Her religious beliefs and political affiliations are difficult to ascertain from just an image. She appears calm and content, possibly slightly playful, in the image. Her clothing suggests a relaxed and comfortable demeanor, although her makeup is rather precise and suggests an interest in beauty and style. Some potential interests include fashion, makeup, and photography, and, potentially, online gaming or social media, shopping, and excessive screen time. She seems serene and stylish, radiating an aura of quiet confidence. We can target her with beauty products, luxury items and subscription boxes, such as Sephora collections, Glossier skincare, and Stitch Fix styling services, and other similar premium goods.",
"go_fast": false,
"lora_scale": 1,
"megapixels": "1",
"num_outputs": 1,
"aspect_ratio": "custom",
"output_format": "png",
"guidance_scale": 3,
"output_quality": 100,
"prompt_strength": 0.8,
"extra_lora_scale": 1,
"num_inference_steps": 46
}

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=28687820267520
Downloading weights
2025-02-26T02:03:02Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmp4refc_3_/weights url=https://replicate.delivery/yhqm/kmBESBF5PuoWP9wTlfXYa6P7ieuVJsnYHk6wpzNPB4lfId5mA/trained_model.tar
2025-02-26T02:03:04Z | INFO  | [ Complete ] dest=/tmp/tmp4refc_3_/weights size="172 MB" total_elapsed=1.569s url=https://replicate.delivery/yhqm/kmBESBF5PuoWP9wTlfXYa6P7ieuVJsnYHk6wpzNPB4lfId5mA/trained_model.tar
Downloaded weights in 1.60s
Loaded LoRAs in 2.15s
Using seed: 53005
Prompt: The image shows a XshnX woman, possibly in her late thirties or early forties , with brown hair. She appears to be lounging back legs bent on a sofa looking directly at viewer, alone in a brightly lit dive hotel room. The woman is wearing an extra loose fitting men’s long sleeved button down dress shirt that is fully unbuttoned and completely open in the front to expose her cleavage but still covering her nipples and lace thong panties. The woman seems to be of Caucasian race, with a potentially upper-middle-class income, possibly between $50,000 and $100,000 per year. Her religious beliefs and political affiliations are difficult to ascertain from just an image. She appears calm and content, possibly slightly playful, in the image. Her clothing suggests a relaxed and comfortable demeanor, although her makeup is rather precise and suggests an interest in beauty and style. Some potential interests include fashion, makeup, and photography, and, potentially, online gaming or social media, shopping, and excessive screen time. She seems serene and stylish, radiating an aura of quiet confidence. We can target her with beauty products, luxury items and subscription boxes, such as Sephora collections, Glossier skincare, and Stitch Fix styling services, and other similar premium goods.
[!] txt2img mode
  0%|          | 0/46 [00:00<?, ?it/s]
  2%|▏         | 1/46 [00:00<00:38,  1.17it/s]
  4%|▍         | 2/46 [00:01<00:19,  2.25it/s]
  7%|▋         | 3/46 [00:01<00:14,  3.03it/s]
  9%|▊         | 4/46 [00:01<00:11,  3.63it/s]
 11%|█         | 5/46 [00:01<00:10,  4.07it/s]
 13%|█▎        | 6/46 [00:01<00:09,  4.40it/s]
 15%|█▌        | 7/46 [00:01<00:08,  4.63it/s]
 17%|█▋        | 8/46 [00:02<00:07,  4.80it/s]
 20%|█▉        | 9/46 [00:02<00:07,  4.92it/s]
 22%|██▏       | 10/46 [00:02<00:07,  4.99it/s]
 24%|██▍       | 11/46 [00:02<00:06,  5.05it/s]
 26%|██▌       | 12/46 [00:02<00:06,  5.10it/s]
 28%|██▊       | 13/46 [00:03<00:06,  5.12it/s]
 30%|███       | 14/46 [00:03<00:06,  5.14it/s]
 33%|███▎      | 15/46 [00:03<00:06,  5.16it/s]
 35%|███▍      | 16/46 [00:03<00:05,  5.17it/s]
 37%|███▋      | 17/46 [00:03<00:05,  5.18it/s]
 39%|███▉      | 18/46 [00:04<00:05,  5.18it/s]
 41%|████▏     | 19/46 [00:04<00:05,  5.19it/s]
 43%|████▎     | 20/46 [00:04<00:05,  5.19it/s]
 46%|████▌     | 21/46 [00:04<00:04,  5.19it/s]
 48%|████▊     | 22/46 [00:04<00:04,  5.19it/s]
 50%|█████     | 23/46 [00:05<00:04,  5.20it/s]
 52%|█████▏    | 24/46 [00:05<00:04,  5.20it/s]
 54%|█████▍    | 25/46 [00:05<00:04,  5.19it/s]
 57%|█████▋    | 26/46 [00:05<00:03,  5.19it/s]
 59%|█████▊    | 27/46 [00:05<00:03,  5.19it/s]
 61%|██████    | 28/46 [00:06<00:03,  5.19it/s]
 63%|██████▎   | 29/46 [00:06<00:03,  5.20it/s]
 65%|██████▌   | 30/46 [00:06<00:03,  5.20it/s]
 67%|██████▋   | 31/46 [00:06<00:02,  5.19it/s]
 70%|██████▉   | 32/46 [00:06<00:02,  5.19it/s]
 72%|███████▏  | 33/46 [00:06<00:02,  5.19it/s]
 74%|███████▍  | 34/46 [00:07<00:02,  5.20it/s]
 76%|███████▌  | 35/46 [00:07<00:02,  5.19it/s]
 78%|███████▊  | 36/46 [00:07<00:01,  5.20it/s]
 80%|████████  | 37/46 [00:07<00:01,  5.20it/s]
 83%|████████▎ | 38/46 [00:07<00:01,  5.20it/s]
 85%|████████▍ | 39/46 [00:08<00:01,  5.20it/s]
 87%|████████▋ | 40/46 [00:08<00:01,  5.20it/s]
 89%|████████▉ | 41/46 [00:08<00:00,  5.19it/s]
 91%|█████████▏| 42/46 [00:08<00:00,  5.19it/s]
 93%|█████████▎| 43/46 [00:08<00:00,  5.19it/s]
 96%|█████████▌| 44/46 [00:09<00:00,  5.19it/s]
 98%|█████████▊| 45/46 [00:09<00:00,  5.20it/s]
100%|██████████| 46/46 [00:09<00:00,  5.19it/s]
100%|██████████| 46/46 [00:09<00:00,  4.85it/s]
Total safe images: 1 out of 1

Version Details

Version ID: aa221ab79870bd64c67c32292768597ab83d065233d054fc390f20db2fe46876
Version Created: September 14, 2024

Run on Replicate →