lukesai77/ai_profilepics 🖼️🔢❓📝✓ → 🖼️
About
Example Output
Prompt:
"foto of ai-profilepics, stylish, confident man in his late 20s, standing in a dimly lit, high-end rooftop lounge or modern bar. Neon lights and moody ambient lighting create a cinematic atmosphere. He wears a sleek, well-fitted outfit—maybe a leather jacket or a smart-casual blazer. He holds a drink casually, looking effortlessly cool with a relaxed but charismatic posture. The background is blurred with bokeh lights, hinting at a vibrant nightlife setting. Shot in ultra-realistic, high-definition photography style with soft depth of field and dramatic lighting"
Output
Performance Metrics
40.97s
Prediction Time
41.00s
Total Time
All Input Parameters
{
"model": "dev",
"prompt": "foto of ai-profilepics, stylish, confident man in his late 20s, standing in a dimly lit, high-end rooftop lounge or modern bar. Neon lights and moody ambient lighting create a cinematic atmosphere. He wears a sleek, well-fitted outfit—maybe a leather jacket or a smart-casual blazer. He holds a drink casually, looking effortlessly cool with a relaxed but charismatic posture. The background is blurred with bokeh lights, hinting at a vibrant nightlife setting. Shot in ultra-realistic, high-definition photography style with soft depth of field and dramatic lighting",
"go_fast": false,
"lora_scale": 1,
"megapixels": "1",
"num_outputs": 4,
"aspect_ratio": "1:1",
"output_format": "webp",
"guidance_scale": 2,
"output_quality": 80,
"prompt_strength": 0.8,
"extra_lora_scale": 1,
"num_inference_steps": 43
}
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
Loaded LoRAs in 0.60s Using seed: 41227 Prompt: foto of ai-profilepics, stylish, confident man in his late 20s, standing in a dimly lit, high-end rooftop lounge or modern bar. Neon lights and moody ambient lighting create a cinematic atmosphere. He wears a sleek, well-fitted outfit—maybe a leather jacket or a smart-casual blazer. He holds a drink casually, looking effortlessly cool with a relaxed but charismatic posture. The background is blurred with bokeh lights, hinting at a vibrant nightlife setting. Shot in ultra-realistic, high-definition photography style with soft depth of field and dramatic lighting [!] txt2img mode 0%| | 0/43 [00:00<?, ?it/s] 2%|▏ | 1/43 [00:00<00:38, 1.10it/s] 5%|▍ | 2/43 [00:01<00:33, 1.23it/s] 7%|▋ | 3/43 [00:02<00:34, 1.16it/s] 9%|▉ | 4/43 [00:03<00:34, 1.13it/s] 12%|█▏ | 5/43 [00:04<00:34, 1.12it/s] 14%|█▍ | 6/43 [00:05<00:33, 1.11it/s] 16%|█▋ | 7/43 [00:06<00:32, 1.10it/s] 19%|█▊ | 8/43 [00:07<00:31, 1.10it/s] 21%|██ | 9/43 [00:08<00:31, 1.09it/s] 23%|██▎ | 10/43 [00:09<00:30, 1.09it/s] 26%|██▌ | 11/43 [00:09<00:29, 1.09it/s] 28%|██▊ | 12/43 [00:10<00:28, 1.09it/s] 30%|███ | 13/43 [00:11<00:27, 1.09it/s] 33%|███▎ | 14/43 [00:12<00:26, 1.09it/s] 35%|███▍ | 15/43 [00:13<00:25, 1.09it/s] 37%|███▋ | 16/43 [00:14<00:24, 1.09it/s] 40%|███▉ | 17/43 [00:15<00:23, 1.09it/s] 42%|████▏ | 18/43 [00:16<00:22, 1.09it/s] 44%|████▍ | 19/43 [00:17<00:22, 1.09it/s] 47%|████▋ | 20/43 [00:18<00:21, 1.09it/s] 49%|████▉ | 21/43 [00:19<00:20, 1.09it/s] 51%|█████ | 22/43 [00:20<00:19, 1.09it/s] 53%|█████▎ | 23/43 [00:20<00:18, 1.09it/s] 56%|█████▌ | 24/43 [00:21<00:17, 1.09it/s] 58%|█████▊ | 25/43 [00:22<00:16, 1.09it/s] 60%|██████ | 26/43 [00:23<00:15, 1.09it/s] 63%|██████▎ | 27/43 [00:24<00:14, 1.09it/s] 65%|██████▌ | 28/43 [00:25<00:13, 1.09it/s] 67%|██████▋ | 29/43 [00:26<00:12, 1.09it/s] 70%|██████▉ | 30/43 [00:27<00:11, 1.09it/s] 72%|███████▏ | 31/43 [00:28<00:11, 1.09it/s] 74%|███████▍ | 32/43 [00:29<00:10, 1.08it/s] 77%|███████▋ | 33/43 [00:30<00:09, 1.08it/s] 79%|███████▉ | 34/43 [00:31<00:08, 1.08it/s] 81%|████████▏ | 35/43 [00:32<00:07, 1.08it/s] 84%|████████▎ | 36/43 [00:32<00:06, 1.08it/s] 86%|████████▌ | 37/43 [00:33<00:05, 1.08it/s] 88%|████████▊ | 38/43 [00:34<00:04, 1.08it/s] 91%|█████████ | 39/43 [00:35<00:03, 1.08it/s] 93%|█████████▎| 40/43 [00:36<00:02, 1.08it/s] 95%|█████████▌| 41/43 [00:37<00:01, 1.08it/s] 98%|█████████▊| 42/43 [00:38<00:00, 1.08it/s] 100%|██████████| 43/43 [00:39<00:00, 1.08it/s] 100%|██████████| 43/43 [00:39<00:00, 1.09it/s] Total safe images: 4 out of 4
Version Details
- Version ID
cd2dad7de37c2588d3021077dff04192ff9b3ff44aaf8e663a9a466adb942bd3- Version Created
- February 10, 2025