lilianabazil/lili-bazil 🖼️🔢❓📝✓ → 🖼️

▶️ 179 runs 📅 Aug 2025 ⚙️ Cog 0.15.3
lora lora-person text-to-image

About

Example Output

Prompt:

"Lili Realistic portrait of a young woman with fair skin, serene expression and a slight smile, almond-shaped dark brown eyes, full and well-defined eyebrows, straight dark brown hair cut at chin length with blunt bangs in Dakota Johnson style, a few loose strands for a natural touch, wearing light makeup with subtle blush, soft eyeliner, and natural lip color, dressed in a light beige shirt made of lightweight fabric with a V-neck, background with a gradient sky from blue to pink at sunset, soft natural lighting, high-quality photographic style, focus on the face, calm and delicate atmosphere."

Output

Example output

Performance Metrics

6.84s Prediction Time
13.79s Total Time
All Input Parameters 
{
  "image": "https://replicate.delivery/pbxt/NWy7RQvZw36R0jk5ueDVzCLx5lJqMkQK0zzJqIvxm5GLAoN5/a.jpg",
  "model": "dev",
  "prompt": "Lili Realistic portrait of a young woman with fair skin, serene expression and a slight smile, almond-shaped dark brown eyes, full and well-defined eyebrows, straight dark brown hair cut at chin length with blunt bangs in Dakota Johnson style, a few loose strands for a natural touch, wearing light makeup with subtle blush, soft eyeliner, and natural lip color, dressed in a light beige shirt made of lightweight fabric with a V-neck, background with a gradient sky from blue to pink at sunset, soft natural lighting, high-quality photographic style, focus on the face, calm and delicate atmosphere.",
  "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=24635159801856
Downloading weights
2025-08-13T23:35:53Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpc27e0ofe/weights url=https://replicate.delivery/xezq/6ufCezzLGQjpPE5Ro0loxduWA999frF3Nh3sXQvbSaHhVaVqA/trained_model.tar
2025-08-13T23:35:53Z | INFO  | [ Cache Service ] enabled=true scheme=http target=hermes.services.svc.cluster.local
2025-08-13T23:35:53Z | INFO  | [ Cache URL Rewrite ] enabled=true target_url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/6ufCezzLGQjpPE5Ro0loxduWA999frF3Nh3sXQvbSaHhVaVqA/trained_model.tar url=https://replicate.delivery/xezq/6ufCezzLGQjpPE5Ro0loxduWA999frF3Nh3sXQvbSaHhVaVqA/trained_model.tar
2025-08-13T23:35:53Z | INFO  | [ Redirect ] redirect_url=http://r8-east4-loras-ric1.cwlota.com/16b2f5f0ea32efe81b8f08fbd1b2f683769ae1e955717c18c870560953062f2a?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Checksum-Mode=ENABLED&X-Amz-Credential=CWNZUVKLDHXVHEZN%2F20250813%2FUS-EAST-04A%2Fs3%2Faws4_request&X-Amz-Date=20250813T233553Z&X-Amz-Expires=600&X-Amz-SignedHeaders=host&x-id=GetObject&X-Amz-Signature=38fb6d9fd92273e106bce18e47a8e84f5369eeda0f8667f839e0c7891ed61080 url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/6ufCezzLGQjpPE5Ro0loxduWA999frF3Nh3sXQvbSaHhVaVqA/trained_model.tar
2025-08-13T23:35:53Z | INFO  | [ Complete ] dest=/tmp/tmpc27e0ofe/weights size="172 MB" total_elapsed=0.720s url=https://replicate.delivery/xezq/6ufCezzLGQjpPE5Ro0loxduWA999frF3Nh3sXQvbSaHhVaVqA/trained_model.tar
Downloaded weights in 0.78s
Loaded LoRAs in 1.72s
Using seed: 29105
Prompt: Lili Realistic portrait of a young woman with fair skin, serene expression and a slight smile, almond-shaped dark brown eyes, full and well-defined eyebrows, straight dark brown hair cut at chin length with blunt bangs in Dakota Johnson style, a few loose strands for a natural touch, wearing light makeup with subtle blush, soft eyeliner, and natural lip color, dressed in a light beige shirt made of lightweight fabric with a V-neck, background with a gradient sky from blue to pink at sunset, soft natural lighting, high-quality photographic style, focus on the face, calm and delicate atmosphere.
Input image size: 736x1104
[!] Resizing input image from 736x1104 to 736x1104
[!] img2img mode
  0%|          | 0/23 [00:00<?, ?it/s]
  4%|▍         | 1/23 [00:00<00:03,  5.90it/s]
  9%|▊         | 2/23 [00:00<00:04,  5.21it/s]
 13%|█▎        | 3/23 [00:00<00:03,  5.02it/s]
 17%|█▋        | 4/23 [00:00<00:03,  4.93it/s]
 22%|██▏       | 5/23 [00:01<00:03,  4.89it/s]
 26%|██▌       | 6/23 [00:01<00:03,  4.86it/s]
 30%|███       | 7/23 [00:01<00:03,  4.84it/s]
 35%|███▍      | 8/23 [00:01<00:03,  4.83it/s]
 39%|███▉      | 9/23 [00:01<00:02,  4.82it/s]
 43%|████▎     | 10/23 [00:02<00:02,  4.81it/s]
 48%|████▊     | 11/23 [00:02<00:02,  4.81it/s]
 52%|█████▏    | 12/23 [00:02<00:02,  4.80it/s]
 57%|█████▋    | 13/23 [00:02<00:02,  4.80it/s]
 61%|██████    | 14/23 [00:02<00:01,  4.80it/s]
 65%|██████▌   | 15/23 [00:03<00:01,  4.80it/s]
 70%|██████▉   | 16/23 [00:03<00:01,  4.79it/s]
 74%|███████▍  | 17/23 [00:03<00:01,  4.79it/s]
 78%|███████▊  | 18/23 [00:03<00:01,  4.80it/s]
 83%|████████▎ | 19/23 [00:03<00:00,  4.80it/s]
 87%|████████▋ | 20/23 [00:04<00:00,  4.80it/s]
 91%|█████████▏| 21/23 [00:04<00:00,  4.80it/s]
 96%|█████████▌| 22/23 [00:04<00:00,  4.80it/s]
100%|██████████| 23/23 [00:04<00:00,  4.80it/s]
100%|██████████| 23/23 [00:04<00:00,  4.84it/s]
Total safe images: 1 out of 1
Version Details
Version ID
3a2b9ef3fecbc6392e4c4432d2c96ce838cc2ac4e2aae588d68c0296358b2c2a
Version Created
August 13, 2025
Run on Replicate →