klassenmedia/drface 🖼️🔢❓📝✓ → 🖼️
About
Example Output
Prompt:
"DRFACE – a confident, attractive man with a trimmed beard, cap, and stylish glasses, dressed in a modern, sleek superhero suit (not bulky, more business-style), standing firmly in a high-tech server room with soft bokeh lights in the background. He looks directly at the camera with a focused, determined expression, arms slightly tense, signaling readiness for action. The lighting is cinematic and professional, emphasizing facial features and the texture of the suit. Business meets heroism – he’s not here to pose, he’s here to perform."
Output
Performance Metrics
12.27s
Prediction Time
12.38s
Total Time
All Input Parameters
{
"model": "dev",
"prompt": "DRFACE – a confident, attractive man with a trimmed beard, cap, and stylish glasses, dressed in a modern, sleek superhero suit (not bulky, more business-style), standing firmly in a high-tech server room with soft bokeh lights in the background. He looks directly at the camera with a focused, determined expression, arms slightly tense, signaling readiness for action. The lighting is cinematic and professional, emphasizing facial features and the texture of the suit. Business meets heroism – he’s not here to pose, he’s here to perform.",
"go_fast": false,
"lora_scale": 1,
"megapixels": "1",
"num_outputs": 1,
"aspect_ratio": "2:3",
"output_format": "png",
"guidance_scale": 3.13,
"output_quality": 100,
"prompt_strength": 0.8,
"extra_lora_scale": 1,
"num_inference_steps": 33
}
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=27958777823232 Downloading weights 2025-05-10T09:35:15Z | INFO | [ Initiating ] chunk_size=150M dest=/tmp/tmpv_36t2ub/weights url=https://replicate.delivery/xezq/eHCncV1aoG13Ma2ZDfRfahYetHYgJe3heHG0BZ4SPEeMeKaCUA/trained_model.tar 2025-05-10T09:35:15Z | INFO | [ Cache Service ] enabled=true scheme=http target=hermes.services.svc.cluster.local 2025-05-10T09:35:18Z | INFO | [ Complete ] dest=/tmp/tmpv_36t2ub/weights size="172 MB" total_elapsed=2.764s url=https://replicate.delivery/xezq/eHCncV1aoG13Ma2ZDfRfahYetHYgJe3heHG0BZ4SPEeMeKaCUA/trained_model.tar Downloaded weights in 2.78s Loaded LoRAs in 3.36s Using seed: 8240 Prompt: DRFACE – a confident, attractive man with a trimmed beard, cap, and stylish glasses, dressed in a modern, sleek superhero suit (not bulky, more business-style), standing firmly in a high-tech server room with soft bokeh lights in the background. He looks directly at the camera with a focused, determined expression, arms slightly tense, signaling readiness for action. The lighting is cinematic and professional, emphasizing facial features and the texture of the suit. Business meets heroism – he’s not here to pose, he’s here to perform. [!] txt2img mode 0%| | 0/33 [00:00<?, ?it/s] 3%|▎ | 1/33 [00:00<00:08, 3.92it/s] 6%|▌ | 2/33 [00:00<00:06, 4.44it/s] 9%|▉ | 3/33 [00:00<00:07, 4.19it/s] 12%|█▏ | 4/33 [00:00<00:07, 4.09it/s] 15%|█▌ | 5/33 [00:01<00:06, 4.03it/s] 18%|█▊ | 6/33 [00:01<00:06, 4.00it/s] 21%|██ | 7/33 [00:01<00:06, 3.97it/s] 24%|██▍ | 8/33 [00:01<00:06, 3.96it/s] 27%|██▋ | 9/33 [00:02<00:06, 3.95it/s] 30%|███ | 10/33 [00:02<00:05, 3.95it/s] 33%|███▎ | 11/33 [00:02<00:05, 3.94it/s] 36%|███▋ | 12/33 [00:03<00:05, 3.94it/s] 39%|███▉ | 13/33 [00:03<00:05, 3.94it/s] 42%|████▏ | 14/33 [00:03<00:04, 3.94it/s] 45%|████▌ | 15/33 [00:03<00:04, 3.93it/s] 48%|████▊ | 16/33 [00:04<00:04, 3.93it/s] 52%|█████▏ | 17/33 [00:04<00:04, 3.93it/s] 55%|█████▍ | 18/33 [00:04<00:03, 3.93it/s] 58%|█████▊ | 19/33 [00:04<00:03, 3.93it/s] 61%|██████ | 20/33 [00:05<00:03, 3.93it/s] 64%|██████▎ | 21/33 [00:05<00:03, 3.93it/s] 67%|██████▋ | 22/33 [00:05<00:02, 3.93it/s] 70%|██████▉ | 23/33 [00:05<00:02, 3.93it/s] 73%|███████▎ | 24/33 [00:06<00:02, 3.93it/s] 76%|███████▌ | 25/33 [00:06<00:02, 3.93it/s] 79%|███████▉ | 26/33 [00:06<00:01, 3.93it/s] 82%|████████▏ | 27/33 [00:06<00:01, 3.93it/s] 85%|████████▍ | 28/33 [00:07<00:01, 3.93it/s] 88%|████████▊ | 29/33 [00:07<00:01, 3.93it/s] 91%|█████████ | 30/33 [00:07<00:00, 3.93it/s] 94%|█████████▍| 31/33 [00:07<00:00, 3.93it/s] 97%|█████████▋| 32/33 [00:08<00:00, 3.93it/s] 100%|██████████| 33/33 [00:08<00:00, 3.93it/s] 100%|██████████| 33/33 [00:08<00:00, 3.95it/s] Total safe images: 1 out of 1
Version Details
- Version ID
73367fb88cf3284ba784e3646370fd3ab38233ac49e71cd1bdf4c889ffa7af09- Version Created
- January 6, 2025