herodetus335/ai-mikael-images 🖼️🔢❓📝✓ → 🖼️

▶️ 98 runs 📅 Nov 2025 ⚙️ Cog 0.15.3

About

Example Output

Prompt:

"TOK 's face replaces the existing one. He's more muscular too and is wearing a quarter zip jacket with a nice watch. Includes natural skin texture, subtle pores, tiny blemishes, micro-shadows, and realistic asymmetry. Avoid over-smoothing. Preserve natural imperfections. We want Subtle environmental light bounce and realistic shadow gradients on the face. Make sure the eyes are looking at the computer. "

Output

Performance Metrics

8.51s Prediction Time

8.56s Total Time

All Input Parameters

{
  "image": "https://replicate.delivery/pbxt/O6whaNUbMPi5sa1YumJhoa5lZAz7rXOG04GcpH7RHD7AGWhd/ai-generated-businessman-working-on-laptop-at-night-in-office-business-concept-concentration-entrepreneur-using-pc-technology-in-the-office-ai-generated-free-photo.jpg",
  "model": "dev",
  "width": 1440,
  "height": 1440,
  "prompt": "TOK 's face replaces the existing one. He's more muscular too and is wearing a quarter zip jacket with a nice watch. Includes natural skin texture, subtle pores, tiny blemishes, micro-shadows, and realistic asymmetry. Avoid over-smoothing. Preserve natural imperfections. We want Subtle environmental light bounce and realistic shadow gradients on the face. Make sure the eyes are looking at the computer. ",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "png",
  "guidance_scale": 2.5,
  "output_quality": 100,
  "prompt_strength": 0.6,
  "num_inference_steps": 30
}

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

Loaded LoRAs in 1.03s
Using seed: 31557
Prompt: TOK 's face replaces the existing one. He's more muscular too and is wearing a quarter zip jacket with a nice watch. Includes natural skin texture, subtle pores, tiny blemishes, micro-shadows, and realistic asymmetry. Avoid over-smoothing. Preserve natural imperfections. We want Subtle environmental light bounce and realistic shadow gradients on the face. Make sure the eyes are looking at the computer.
Input image size: 2940x1960
[!] Resizing input image from 2940x1960 to 1440x960
[!] img2img mode
  0%|          | 0/18 [00:00<?, ?it/s]
  6%|▌         | 1/18 [00:00<00:04,  3.65it/s]
 11%|█         | 2/18 [00:00<00:05,  3.17it/s]
 17%|█▋        | 3/18 [00:00<00:04,  3.05it/s]
 22%|██▏       | 4/18 [00:01<00:04,  2.99it/s]
 28%|██▊       | 5/18 [00:01<00:04,  2.96it/s]
 33%|███▎      | 6/18 [00:01<00:04,  2.94it/s]
 39%|███▉      | 7/18 [00:02<00:03,  2.92it/s]
 44%|████▍     | 8/18 [00:02<00:03,  2.91it/s]
 50%|█████     | 9/18 [00:03<00:03,  2.90it/s]
 56%|█████▌    | 10/18 [00:03<00:02,  2.90it/s]
 61%|██████    | 11/18 [00:03<00:02,  2.90it/s]
 67%|██████▋   | 12/18 [00:04<00:02,  2.90it/s]
 72%|███████▏  | 13/18 [00:04<00:01,  2.90it/s]
 78%|███████▊  | 14/18 [00:04<00:01,  2.90it/s]
 83%|████████▎ | 15/18 [00:05<00:01,  2.90it/s]
 89%|████████▉ | 16/18 [00:05<00:00,  2.90it/s]
 94%|█████████▍| 17/18 [00:05<00:00,  2.90it/s]
100%|██████████| 18/18 [00:06<00:00,  2.90it/s]
100%|██████████| 18/18 [00:06<00:00,  2.93it/s]
Total safe images: 1 out of 1

Version Details

Version ID: d003598e79135e4b9d08900a229bf74d9a83b26cd3b67be0274e8ddbd1d77c47
Version Created: November 23, 2025

Run on Replicate →