fulbertsmart/fulbertai 🖼️🔢❓📝✓ → 🖼️

▶️ 48 runs 📅 Jun 2025 ⚙️ Cog 0.15.3

About

Example Output

Prompt:

"Portrait photograph of fulbertai a charismatic young Black man with medium build, well-groomed short fade haircut, neatly trimmed goatee and mustache, rich dark skin tone with natural highlights, confident smile and engaging eyes looking slightly off-camera, standing in relaxed professional pose with one hand adjusting jacket --ar 3:4 --style raw --subject wearing tailored navy blue business suit with modern slim fit, crisp white dress shirt with standard collar, vibrant red silk tie with subtle texture --accessories black leather wristwatch with square face on left wrist, small silver lapel pin on left jacket lapel, black leather belt, matching navy blue dress pants --environment professional studio setting with dramatic gradient background transitioning from dark charcoal on left to warm golden amber on right, creating sophisticated bokeh effect --lighting dramatic directional lighting with warm key light from right side creating natural skin glow, soft fill light preventing harsh shadows, golden hour color temperature 3200K, rim lighting separating subject from background --camera angle eye-level straight shot with slight turn of body creating three-quarter pose, upper body composition --composition subject positioned according to rule of thirds slightly left of center, creating visual balance with warm background gradient, professional executive portrait style --post-processing high-definition retouching with enhanced warm tones, increased contrast between suit and background, natural skin enhancement maintaining authentic appearance --details sharp focus on facial features and suit fabric texture, watch face reflecting ambient light, tie fabric showing subtle weave pattern, natural skin texture preserved --quality premium executive portrait photography, 85mm lens f/2.8, ISO 200, shutter speed 1/125s, contrast +20, highlights -10, shadows +15, vibrance +10, shot with Canon EOS R6, shallow depth of field with beautifully blurred gradient background, professional studio lighting with beauty dish main light and gradient background lighting setup."

Output

Performance Metrics

5.95s Prediction Time

6.03s Total Time

All Input Parameters

{
  "image": "https://replicate.delivery/pbxt/ND70QmJpxFrFijud8n2zEOVZR81YNqkyYveptJ2O7Iz2KmRl/birthday%20portrait.jpg",
  "model": "dev",
  "prompt": "Portrait photograph of fulbertai a charismatic young Black man with medium build, well-groomed short fade haircut, neatly trimmed goatee and mustache, rich dark skin tone with natural highlights, confident smile and engaging eyes looking slightly off-camera, standing in relaxed professional pose with one hand adjusting jacket --ar 3:4 --style raw --subject wearing tailored navy blue business suit with modern slim fit, crisp white dress shirt with standard collar, vibrant red silk tie with subtle texture --accessories black leather wristwatch with square face on left wrist, small silver lapel pin on left jacket lapel, black leather belt, matching navy blue dress pants --environment professional studio setting with dramatic gradient background transitioning from dark charcoal on left to warm golden amber on right, creating sophisticated bokeh effect --lighting dramatic directional lighting with warm key light from right side creating natural skin glow, soft fill light preventing harsh shadows, golden hour color temperature 3200K, rim lighting separating subject from background --camera angle eye-level straight shot with slight turn of body creating three-quarter pose, upper body composition --composition subject positioned according to rule of thirds slightly left of center, creating visual balance with warm background gradient, professional executive portrait style --post-processing high-definition retouching with enhanced warm tones, increased contrast between suit and background, natural skin enhancement maintaining authentic appearance --details sharp focus on facial features and suit fabric texture, watch face reflecting ambient light, tie fabric showing subtle weave pattern, natural skin texture preserved --quality premium executive portrait photography, 85mm lens f/2.8, ISO 200, shutter speed 1/125s, contrast +20, highlights -10, shadows +15, vibrance +10, shot with Canon EOS R6, shallow depth of field with beautifully blurred gradient background, professional studio lighting with beauty dish main light and gradient background lighting setup.",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "3:4",
  "output_format": "jpg",
  "guidance_scale": 3,
  "output_quality": 100,
  "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

free=27052336828416
Downloading weights
2025-06-19T01:00:32Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpd74jnlat/weights url=https://replicate.delivery/xezq/Hob8ODBToV7gL9BhYhJDnzeb8PogQPmdeL4BfPa865XjzgwpA/trained_model.tar
2025-06-19T01:00:32Z | INFO  | [ Cache Service ] enabled=true scheme=http target=hermes.services.svc.cluster.local
2025-06-19T01:00:32Z | INFO  | [ Cache URL Rewrite ] enabled=true target_url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/Hob8ODBToV7gL9BhYhJDnzeb8PogQPmdeL4BfPa865XjzgwpA/trained_model.tar url=https://replicate.delivery/xezq/Hob8ODBToV7gL9BhYhJDnzeb8PogQPmdeL4BfPa865XjzgwpA/trained_model.tar
2025-06-19T01:00:32Z | INFO  | [ Redirect ] redirect_url=http://r8-east4-loras-ric1.cwlota.com/0da368e5b849965ca70ad9c3f04b45f7552e679ca70e455b339e169ec396c9b6?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Checksum-Mode=ENABLED&X-Amz-Credential=CWNZUVKLDHXVHEZN%2F20250619%2FUS-EAST-04A%2Fs3%2Faws4_request&X-Amz-Date=20250619T010032Z&X-Amz-Expires=600&X-Amz-SignedHeaders=host&x-id=GetObject&X-Amz-Signature=dc9bd9885755f5e5fdaa52396385617e0c00ea9056fc852725af3dcb6d301118 url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/Hob8ODBToV7gL9BhYhJDnzeb8PogQPmdeL4BfPa865XjzgwpA/trained_model.tar
2025-06-19T01:00:32Z | INFO  | [ Complete ] dest=/tmp/tmpd74jnlat/weights size="172 MB" total_elapsed=0.235s url=https://replicate.delivery/xezq/Hob8ODBToV7gL9BhYhJDnzeb8PogQPmdeL4BfPa865XjzgwpA/trained_model.tar
Downloaded weights in 0.30s
Loaded LoRAs in 0.87s
Using seed: 26160
Prompt: Portrait photograph of fulbertai a charismatic young Black man with medium build, well-groomed short fade haircut, neatly trimmed goatee and mustache, rich dark skin tone with natural highlights, confident smile and engaging eyes looking slightly off-camera, standing in relaxed professional pose with one hand adjusting jacket --ar 3:4 --style raw --subject wearing tailored navy blue business suit with modern slim fit, crisp white dress shirt with standard collar, vibrant red silk tie with subtle texture --accessories black leather wristwatch with square face on left wrist, small silver lapel pin on left jacket lapel, black leather belt, matching navy blue dress pants --environment professional studio setting with dramatic gradient background transitioning from dark charcoal on left to warm golden amber on right, creating sophisticated bokeh effect --lighting dramatic directional lighting with warm key light from right side creating natural skin glow, soft fill light preventing harsh shadows, golden hour color temperature 3200K, rim lighting separating subject from background --camera angle eye-level straight shot with slight turn of body creating three-quarter pose, upper body composition --composition subject positioned according to rule of thirds slightly left of center, creating visual balance with warm background gradient, professional executive portrait style --post-processing high-definition retouching with enhanced warm tones, increased contrast between suit and background, natural skin enhancement maintaining authentic appearance --details sharp focus on facial features and suit fabric texture, watch face reflecting ambient light, tie fabric showing subtle weave pattern, natural skin texture preserved --quality premium executive portrait photography, 85mm lens f/2.8, ISO 200, shutter speed 1/125s, contrast +20, highlights -10, shadows +15, vibrance +10, shot with Canon EOS R6, shallow depth of field with beautifully blurred gradient background, professional studio lighting with beauty dish main light and gradient background lighting setup.
Input image size: 736x902
[!] Resizing input image from 736x902 to 736x912
[!] img2img mode
  0%|          | 0/23 [00:00<?, ?it/s]
  4%|▍         | 1/23 [00:00<00:03,  6.88it/s]
  9%|▊         | 2/23 [00:00<00:03,  6.07it/s]
 13%|█▎        | 3/23 [00:00<00:03,  5.84it/s]
 17%|█▋        | 4/23 [00:00<00:03,  5.75it/s]
 22%|██▏       | 5/23 [00:00<00:03,  5.69it/s]
 26%|██▌       | 6/23 [00:01<00:03,  5.66it/s]
 30%|███       | 7/23 [00:01<00:02,  5.64it/s]
 35%|███▍      | 8/23 [00:01<00:02,  5.63it/s]
 39%|███▉      | 9/23 [00:01<00:02,  5.62it/s]
 43%|████▎     | 10/23 [00:01<00:02,  5.61it/s]
 48%|████▊     | 11/23 [00:01<00:02,  5.61it/s]
 52%|█████▏    | 12/23 [00:02<00:01,  5.61it/s]
 57%|█████▋    | 13/23 [00:02<00:01,  5.60it/s]
 61%|██████    | 14/23 [00:02<00:01,  5.60it/s]
 65%|██████▌   | 15/23 [00:02<00:01,  5.60it/s]
 70%|██████▉   | 16/23 [00:02<00:01,  5.60it/s]
 74%|███████▍  | 17/23 [00:03<00:01,  5.60it/s]
 78%|███████▊  | 18/23 [00:03<00:00,  5.60it/s]
 83%|████████▎ | 19/23 [00:03<00:00,  5.60it/s]
 87%|████████▋ | 20/23 [00:03<00:00,  5.60it/s]
 91%|█████████▏| 21/23 [00:03<00:00,  5.60it/s]
 96%|█████████▌| 22/23 [00:03<00:00,  5.60it/s]
100%|██████████| 23/23 [00:04<00:00,  5.60it/s]
100%|██████████| 23/23 [00:04<00:00,  5.65it/s]
Total safe images: 1 out of 1

Version Details

Version ID: e826023244dd8f7b189fe19335120805064eba9216ff44fca942b5f85dfcaebe
Version Created: June 19, 2025

Run on Replicate →