bnhomebr/sil 🖼️🔢❓📝✓ → 🖼️
About
Example Output
"SSERAF. A woman is seated in a softly lit, minimalist space with neutral tones. She is leaning slightly forward on a cream-colored sofa, in a thoughtful yet relaxed pose.
She appears to be in her early 40s, with a mature and composed presence that exudes confidence and self-awareness. She has slightly wavy chin-length hair in a light brown shade. The subtle grayish hues add depth and elegance, enhancing the refined, modern aesthetic of the portrait.
Her gaze is warm and steady, directed at the camera with natural poise. She is wearing a long-sleeved, off-white ribbed top that slightly reveals one shoulder, adding a touch of understated sensuality. Her nails are painted a glossy black, offering a striking visual contrast against the softness of her surroundings.
The atmosphere of the room is serene and contemporary, bathed in gentle natural light that enhances the intimate, composed character of the image."
Output
Performance Metrics
All Input Parameters
{
"image": "https://replicate.delivery/pbxt/NKPB6bQif2dKJFvfJiMVrUaAtD9ZjwuahhFPm9k25MWlsq79/leticianunesphoto__2025-06-03T150435.000Z.jpg",
"model": "dev",
"prompt": "SSERAF. A woman is seated in a softly lit, minimalist space with neutral tones. She is leaning slightly forward on a cream-colored sofa, in a thoughtful yet relaxed pose.\nShe appears to be in her early 40s, with a mature and composed presence that exudes confidence and self-awareness. She has slightly wavy chin-length hair in a light brown shade. The subtle grayish hues add depth and elegance, enhancing the refined, modern aesthetic of the portrait. \nHer gaze is warm and steady, directed at the camera with natural poise. She is wearing a long-sleeved, off-white ribbed top that slightly reveals one shoulder, adding a touch of understated sensuality. Her nails are painted a glossy black, offering a striking visual contrast against the softness of her surroundings.\nThe atmosphere of the room is serene and contemporary, bathed in gentle natural light that enhances the intimate, composed character of the image.",
"go_fast": false,
"lora_scale": 1,
"megapixels": "1",
"num_outputs": 1,
"aspect_ratio": "4:3",
"output_format": "jpg",
"guidance_scale": 3,
"output_quality": 80,
"prompt_strength": 0.8,
"extra_lora_scale": 1,
"num_inference_steps": 28
}
Input Parameters
- mask
- Image mask for image inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored.
- seed
- Random seed. Set for reproducible generation
- image
- Input image for image to image or inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored.
- model
- 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
- 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
- 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)
- 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
- Run faster predictions with model optimized for speed (currently fp8 quantized); disable to run in original bf16
- extra_lora
- 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
- 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
- Approximate number of megapixels for generated image
- num_outputs
- Number of outputs to generate
- aspect_ratio
- Aspect ratio for the generated image. If custom is selected, uses height and width below & will run in bf16 mode
- output_format
- Format of the output images
- guidance_scale
- 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
- 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
- Prompt strength when using img2img. 1.0 corresponds to full destruction of information in image
- extra_lora_scale
- 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
- 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
- Number of denoising steps. More steps can give more detailed images, but take longer.
- disable_safety_checker
- Disable safety checker for generated images.
Output Schema
Output
Example Execution Logs
free=25696515878912 Downloading weights 2025-07-09T14:07:27Z | INFO | [ Initiating ] chunk_size=150M dest=/tmp/tmpo0uq3sae/weights url=https://replicate.delivery/xezq/NKFLv81RmfXFTSYnBeAfTvbP4SIEIOWxJCPCGG80L0QEuEeTB/flux-lora.tar 2025-07-09T14:07:27Z | INFO | [ Cache Service ] enabled=true scheme=http target=hermes.services.svc.cluster.local 2025-07-09T14:07:27Z | INFO | [ Cache URL Rewrite ] enabled=true target_url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/NKFLv81RmfXFTSYnBeAfTvbP4SIEIOWxJCPCGG80L0QEuEeTB/flux-lora.tar url=https://replicate.delivery/xezq/NKFLv81RmfXFTSYnBeAfTvbP4SIEIOWxJCPCGG80L0QEuEeTB/flux-lora.tar 2025-07-09T14:07:27Z | INFO | [ Redirect ] redirect_url=http://r8-east4-loras-ric1.cwlota.com/a01ed1a828788fe82f9ea3b3a8d562d1dea53ea5d38a8b7f73bfd148aac5fe0a?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Checksum-Mode=ENABLED&X-Amz-Credential=CWNZUVKLDHXVHEZN%2F20250709%2FUS-EAST-04A%2Fs3%2Faws4_request&X-Amz-Date=20250709T140727Z&X-Amz-Expires=600&X-Amz-SignedHeaders=host&x-id=GetObject&X-Amz-Signature=21efdc6ea73fd3d09cf17ee29924d50a93fee1d3c2d65894c80d6cf4a28a371b url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/NKFLv81RmfXFTSYnBeAfTvbP4SIEIOWxJCPCGG80L0QEuEeTB/flux-lora.tar 2025-07-09T14:07:28Z | INFO | [ Complete ] dest=/tmp/tmpo0uq3sae/weights size="172 MB" total_elapsed=0.249s url=https://replicate.delivery/xezq/NKFLv81RmfXFTSYnBeAfTvbP4SIEIOWxJCPCGG80L0QEuEeTB/flux-lora.tar Downloaded weights in 0.32s Loaded LoRAs in 0.85s Using seed: 16171 Prompt: SSERAF. A woman is seated in a softly lit, minimalist space with neutral tones. She is leaning slightly forward on a cream-colored sofa, in a thoughtful yet relaxed pose. She appears to be in her early 40s, with a mature and composed presence that exudes confidence and self-awareness. She has slightly wavy chin-length hair in a light brown shade. The subtle grayish hues add depth and elegance, enhancing the refined, modern aesthetic of the portrait. Her gaze is warm and steady, directed at the camera with natural poise. She is wearing a long-sleeved, off-white ribbed top that slightly reveals one shoulder, adding a touch of understated sensuality. Her nails are painted a glossy black, offering a striking visual contrast against the softness of her surroundings. The atmosphere of the room is serene and contemporary, bathed in gentle natural light that enhances the intimate, composed character of the image. Input image size: 1440x1800 [!] Resizing input image from 1440x1800 to 1152x1440 [!] img2img mode 0%| | 0/23 [00:00<?, ?it/s] 4%|▍ | 1/23 [00:00<00:07, 3.07it/s] 9%|▊ | 2/23 [00:00<00:07, 2.67it/s] 13%|█▎ | 3/23 [00:01<00:07, 2.53it/s] 17%|█▋ | 4/23 [00:01<00:07, 2.49it/s] 22%|██▏ | 5/23 [00:01<00:07, 2.46it/s] 26%|██▌ | 6/23 [00:02<00:06, 2.45it/s] 30%|███ | 7/23 [00:02<00:06, 2.44it/s] 35%|███▍ | 8/23 [00:03<00:06, 2.43it/s] 39%|███▉ | 9/23 [00:03<00:05, 2.43it/s] 43%|████▎ | 10/23 [00:04<00:05, 2.42it/s] 48%|████▊ | 11/23 [00:04<00:04, 2.42it/s] 52%|█████▏ | 12/23 [00:04<00:04, 2.42it/s] 57%|█████▋ | 13/23 [00:05<00:04, 2.42it/s] 61%|██████ | 14/23 [00:05<00:03, 2.42it/s] 65%|██████▌ | 15/23 [00:06<00:03, 2.42it/s] 70%|██████▉ | 16/23 [00:06<00:02, 2.42it/s] 74%|███████▍ | 17/23 [00:06<00:02, 2.42it/s] 78%|███████▊ | 18/23 [00:07<00:02, 2.42it/s] 83%|████████▎ | 19/23 [00:07<00:01, 2.42it/s] 87%|████████▋ | 20/23 [00:08<00:01, 2.42it/s] 91%|█████████▏| 21/23 [00:08<00:00, 2.42it/s] 96%|█████████▌| 22/23 [00:09<00:00, 2.42it/s] 100%|██████████| 23/23 [00:09<00:00, 2.42it/s] 100%|██████████| 23/23 [00:09<00:00, 2.44it/s] Total safe images: 1 out of 1
Version Details
- Version ID
15258f3e4f622ee4b9289d7183ad305d3aeda4ef1d9d4970666e71e1630b805b- Version Created
- July 9, 2025