boonchie18/yasmin3 🖼️🔢❓📝✓ → 🖼️

▶️ 53 runs 📅 Oct 2025 ⚙️ Cog 0.13.6

About

Example Output

Prompt:

"Yas sitting on a modern desk. Holding a computer in her hand. It is professional. It looks like a professional photographer shot. She is fashionable. She is in a studio. No visible lights no background. There is a lot of money scattered around the floor. Closed in heels. "

Output

Performance Metrics

9.16s Prediction Time

9.19s Total Time

All Input Parameters

{
  "image": "https://replicate.delivery/pbxt/O2C1oNj8zUWvdRyyRAAAmbrK6Ejgy5Ddqc3tp7LqjSWDHFiA/IMG_5203.jpeg",
  "model": "dev",
  "prompt": "Yas sitting on a modern desk.  Holding a computer in her hand. It is professional. It looks like a professional photographer shot. She is fashionable. She is in a studio. No visible lights no background. There is  a lot of money scattered around the floor. Closed in heels. ",
  "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

free=23261411180544
Downloading weights
2025-11-09T22:47:50Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpswziblte/weights url=https://replicate.delivery/xezq/Zf8mi43yJepxvkZFRe0WG9ZtfI7hrB0CpWRLCfrfVf9jHnUxKA/flux-lora.tar
2025-11-09T22:47:50Z | INFO  | [ Cache Service ] enabled=true scheme=http target=hermes.services.svc.cluster.local
2025-11-09T22:47:50Z | INFO  | [ Cache URL Rewrite ] enabled=true target_url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/Zf8mi43yJepxvkZFRe0WG9ZtfI7hrB0CpWRLCfrfVf9jHnUxKA/flux-lora.tar url=https://replicate.delivery/xezq/Zf8mi43yJepxvkZFRe0WG9ZtfI7hrB0CpWRLCfrfVf9jHnUxKA/flux-lora.tar
2025-11-09T22:47:50Z | INFO  | [ Redirect ] redirect_url=http://r8-east4-loras-ric1.cwlota.com/7a02c166a2da0f0bc7bbc59bbd60696274fd77d750b0576068006956367fbd8a?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Checksum-Mode=ENABLED&X-Amz-Credential=CWNZUVKLDHXVHEZN%2F20251109%2FUS-EAST-04A%2Fs3%2Faws4_request&X-Amz-Date=20251109T224750Z&X-Amz-Expires=600&X-Amz-SignedHeaders=host&x-id=GetObject&X-Amz-Signature=f55340af33beca97c7fff52727895cf522773127fd7ea3a1f50ca412e6d3f029 url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/Zf8mi43yJepxvkZFRe0WG9ZtfI7hrB0CpWRLCfrfVf9jHnUxKA/flux-lora.tar
2025-11-09T22:47:50Z | INFO  | [ Complete ] dest=/tmp/tmpswziblte/weights size="172 MB" total_elapsed=0.311s url=https://replicate.delivery/xezq/Zf8mi43yJepxvkZFRe0WG9ZtfI7hrB0CpWRLCfrfVf9jHnUxKA/flux-lora.tar
Downloaded weights in 0.39s
Loaded LoRAs in 1.68s
Using seed: 46651
Prompt: Yas sitting on a modern desk.  Holding a computer in her hand. It is professional. It looks like a professional photographer shot. She is fashionable. She is in a studio. No visible lights no background. There is  a lot of money scattered around the floor. Closed in heels.
Input image size: 768x1408
[!] Resizing input image from 768x1408 to 768x1408
[!] img2img mode
  0%|          | 0/23 [00:00<?, ?it/s]
  4%|▍         | 1/23 [00:00<00:04,  4.61it/s]
  9%|▊         | 2/23 [00:00<00:05,  4.04it/s]
 13%|█▎        | 3/23 [00:00<00:05,  3.89it/s]
 17%|█▋        | 4/23 [00:01<00:04,  3.82it/s]
 22%|██▏       | 5/23 [00:01<00:04,  3.79it/s]
 26%|██▌       | 6/23 [00:01<00:04,  3.77it/s]
 30%|███       | 7/23 [00:01<00:04,  3.76it/s]
 35%|███▍      | 8/23 [00:02<00:04,  3.75it/s]
 39%|███▉      | 9/23 [00:02<00:03,  3.74it/s]
 43%|████▎     | 10/23 [00:02<00:03,  3.73it/s]
 48%|████▊     | 11/23 [00:02<00:03,  3.73it/s]
 52%|█████▏    | 12/23 [00:03<00:02,  3.73it/s]
 57%|█████▋    | 13/23 [00:03<00:02,  3.72it/s]
 61%|██████    | 14/23 [00:03<00:02,  3.72it/s]
 65%|██████▌   | 15/23 [00:03<00:02,  3.72it/s]
 70%|██████▉   | 16/23 [00:04<00:01,  3.72it/s]
 74%|███████▍  | 17/23 [00:04<00:01,  3.72it/s]
 78%|███████▊  | 18/23 [00:04<00:01,  3.72it/s]
 83%|████████▎ | 19/23 [00:05<00:01,  3.72it/s]
 87%|████████▋ | 20/23 [00:05<00:00,  3.72it/s]
 91%|█████████▏| 21/23 [00:05<00:00,  3.72it/s]
 96%|█████████▌| 22/23 [00:05<00:00,  3.72it/s]
100%|██████████| 23/23 [00:06<00:00,  3.72it/s]
100%|██████████| 23/23 [00:06<00:00,  3.75it/s]
Total safe images: 1 out of 1

Version Details

Version ID: a45360c43d4fe06e56904c6a7ecb1a3c6b78727ef61cf498d314be1011be0de9
Version Created: October 25, 2025

Run on Replicate →