iguatemijr89/iguatemijradv 🖼️🔢❓📝✓ → 🖼️

▶️ 27 runs 📅 May 2025 ⚙️ Cog 0.14.3
image-to-image lora lora-person text-to-image

About

Example Output

Prompt:

"

Use the following reference images to create a dramatic only black and white colors portrait of a young Brazilian lawyer known as iguatemijradv, preserving exact facial features, skin texture, and micro-expressions. Maintain realistic human proportions, especially a natural and proportional ratio between head and body (head proportion to neck and hands on fibonacci scale). Preserve fine facial details such as pores, light under-eye lines, subtle texture, and natural expressions — enhancing realism and authenticity.

Apply subtle facial alignment correction only where necessary: gently balance minor asymmetries (such as slight swelling or disproportion between sides of the face), while fully retaining the original facial identity, contours, and natural details. Do not smooth or overly idealize — just refine symmetry for a balanced, professional appearance.

He is seated confidently on a wooden stool inside a minimalist, dark-toned studio with clean, matte textures. The lighting is soft but directional, casting gentle shadows that define his structured jawline, thick eyebrows, almond-shaped medium brown eyes, and full, well-groomed beard. His facial expression is calm, composed, and slightly intense — lips closed, gaze directly into the camera.

He wears a tailored, all-black modern suit with a fitted black shirt underneath — no tie, top button open. A discreet silver watch peeks slightly from his sleeve. His posture exudes calm confidence: one forearm resting on his thigh, the other hand in his trouser pocket.

Background is a smooth, moody black-to-dark-grey gradient, clean and free of visual distractions, enhancing the cinematic and editorial atmosphere. The image must capture a sense of professional identity, introspection, and silent power. Shot in a 4:5 vertical portrait ratio, simulating a Canon EOS R5 + 85mm f/1.2 lens, set at f/2, ISO 100, 1/125s shutter speed, 4K UHD. No surreal effects or softening filters. Just clean, bold, and unmistakably real.

"

Output

Example outputExample outputExample outputExample output

Performance Metrics

34.86s Prediction Time
35.14s Total Time
All Input Parameters 
{
  "image": "https://replicate.delivery/pbxt/NNG1OEo2bm6uTCoiWJri7ftw7GhuOlegnU58Lm5jwSvdW6VD/enhanced_ChatGPT%20Image%2017%20de%20jul-%20de%202025%2011_23_17%20%281%29.png",
  "model": "dev",
  "prompt": "Use the following reference images to create a dramatic only black and white colors portrait of a young Brazilian lawyer known as iguatemijradv, preserving exact facial features, skin texture, and micro-expressions. Maintain realistic human proportions, especially a natural and proportional ratio between head and body (head proportion to neck and hands on fibonacci scale). Preserve fine facial details such as pores, light under-eye lines, subtle texture, and natural expressions — enhancing realism and authenticity.\n\nApply subtle facial alignment correction only where necessary: gently balance minor asymmetries (such as slight swelling or disproportion between sides of the face), while fully retaining the original facial identity, contours, and natural details. Do not smooth or overly idealize — just refine symmetry for a balanced, professional appearance.\n\nHe is seated confidently on a wooden stool inside a minimalist, dark-toned studio with clean, matte textures. The lighting is soft but directional, casting gentle shadows that define his structured jawline, thick eyebrows, almond-shaped medium brown eyes, and full, well-groomed beard. His facial expression is calm, composed, and slightly intense — lips closed, gaze directly into the camera.\n\nHe wears a tailored, all-black modern suit with a fitted black shirt underneath — no tie, top button open. A discreet silver watch peeks slightly from his sleeve. His posture exudes calm confidence: one forearm resting on his thigh, the other hand in his trouser pocket.\n\nBackground is a smooth, moody black-to-dark-grey gradient, clean and free of visual distractions, enhancing the cinematic and editorial atmosphere. The image must capture a sense of professional identity, introspection, and silent power. Shot in a 4:5 vertical portrait ratio, simulating a Canon EOS R5 + 85mm f/1.2 lens, set at f/2, ISO 100, 1/125s shutter speed, 4K UHD. No surreal effects or softening filters. Just clean, bold, and unmistakably real.\n\n",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 4,
  "aspect_ratio": "4:5",
  "output_format": "png",
  "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 
Loaded LoRAs in 0.57s
Using seed: 45270
Prompt: Use the following reference images to create a dramatic only black and white colors portrait of a young Brazilian lawyer known as iguatemijradv, preserving exact facial features, skin texture, and micro-expressions. Maintain realistic human proportions, especially a natural and proportional ratio between head and body (head proportion to neck and hands on fibonacci scale). Preserve fine facial details such as pores, light under-eye lines, subtle texture, and natural expressions — enhancing realism and authenticity.
Apply subtle facial alignment correction only where necessary: gently balance minor asymmetries (such as slight swelling or disproportion between sides of the face), while fully retaining the original facial identity, contours, and natural details. Do not smooth or overly idealize — just refine symmetry for a balanced, professional appearance.
He is seated confidently on a wooden stool inside a minimalist, dark-toned studio with clean, matte textures. The lighting is soft but directional, casting gentle shadows that define his structured jawline, thick eyebrows, almond-shaped medium brown eyes, and full, well-groomed beard. His facial expression is calm, composed, and slightly intense — lips closed, gaze directly into the camera.
He wears a tailored, all-black modern suit with a fitted black shirt underneath — no tie, top button open. A discreet silver watch peeks slightly from his sleeve. His posture exudes calm confidence: one forearm resting on his thigh, the other hand in his trouser pocket.
Background is a smooth, moody black-to-dark-grey gradient, clean and free of visual distractions, enhancing the cinematic and editorial atmosphere. The image must capture a sense of professional identity, introspection, and silent power. Shot in a 4:5 vertical portrait ratio, simulating a Canon EOS R5 + 85mm f/1.2 lens, set at f/2, ISO 100, 1/125s shutter speed, 4K UHD. No surreal effects or softening filters. Just clean, bold, and unmistakably real.
Input image size: 5456x8192
[!] Resizing input image from 5456x8192 to 960x1440
[!] img2img mode
  0%|          | 0/23 [00:00<?, ?it/s]
  4%|▍         | 1/23 [00:01<00:23,  1.06s/it]
  9%|▊         | 2/23 [00:02<00:25,  1.21s/it]
 13%|█▎        | 3/23 [00:03<00:25,  1.26s/it]
 17%|█▋        | 4/23 [00:05<00:24,  1.28s/it]
 22%|██▏       | 5/23 [00:06<00:23,  1.30s/it]
 26%|██▌       | 6/23 [00:07<00:22,  1.31s/it]
 30%|███       | 7/23 [00:08<00:21,  1.31s/it]
 35%|███▍      | 8/23 [00:10<00:19,  1.32s/it]
 39%|███▉      | 9/23 [00:11<00:18,  1.32s/it]
 43%|████▎     | 10/23 [00:12<00:17,  1.32s/it]
 48%|████▊     | 11/23 [00:14<00:15,  1.32s/it]
 52%|█████▏    | 12/23 [00:15<00:14,  1.32s/it]
 57%|█████▋    | 13/23 [00:16<00:13,  1.32s/it]
 61%|██████    | 14/23 [00:18<00:11,  1.32s/it]
 65%|██████▌   | 15/23 [00:19<00:10,  1.32s/it]
 70%|██████▉   | 16/23 [00:20<00:09,  1.32s/it]
 74%|███████▍  | 17/23 [00:22<00:07,  1.32s/it]
 78%|███████▊  | 18/23 [00:23<00:06,  1.32s/it]
 83%|████████▎ | 19/23 [00:24<00:05,  1.32s/it]
 87%|████████▋ | 20/23 [00:26<00:03,  1.32s/it]
 91%|█████████▏| 21/23 [00:27<00:02,  1.32s/it]
 96%|█████████▌| 22/23 [00:28<00:01,  1.32s/it]
100%|██████████| 23/23 [00:30<00:00,  1.32s/it]
100%|██████████| 23/23 [00:30<00:00,  1.31s/it]
Total safe images: 4 out of 4
Version Details
Version ID
a5e79d671a5e1516a5814a8eac17939bd23d3e6c73d5790c7a5fd7e0aef6435e
Version Created
May 19, 2025
Run on Replicate →