adriencommery/adcom 🖼️🔢❓📝✓ → 🖼️

▶️ 16 runs 📅 Jul 2025 ⚙️ Cog 0.13.6

About

Example Output

Prompt:

The character named adcom is shown facing the camera, standing confidently outdoors on the lot of a modern motorhome dealership. He has short, well-groomed hair and a bright, friendly smile that conveys professionalism and approachability. His posture is natural yet assertive, with his arms relaxed at his sides and a subtle weight shift onto one leg, capturing the charisma of a brand ambassador.

He is dressed in a crisp white shirt with the top buttons casually open, fitted black jeans, and fresh white sneakers — a clean, urban style that blends casual elegance with commercial appeal. Behind him, several sleek, modern camper vans are lined up neatly, their glossy surfaces catching the light and reflecting the dealership’s premium image.

The scene takes place in daylight, with soft natural sunlight enhanced by cinematic lighting effects: subtle lens flares, vivid contrast, and a shallow depth of field that keeps the background slightly blurred while the character remains sharply focused. The mood is polished and aspirational, like a high-end automotive advertisement.

The entire visual must be ultra-realistic, with photo-accurate textures, natural lighting, lifelike proportions, and refined composition. The atmosphere should evoke the quality and prestige of a modern vehicle commercial — professional, impactful, and visually engaging.

Output

Performance Metrics

14.24s Prediction Time

22.83s Total Time

All Input Parameters

{
  "model": "dev",
  "prompt": "The character named adcom is shown facing the camera, standing confidently outdoors on the lot of a modern motorhome dealership. He has short, well-groomed hair and a bright, friendly smile that conveys professionalism and approachability. His posture is natural yet assertive, with his arms relaxed at his sides and a subtle weight shift onto one leg, capturing the charisma of a brand ambassador.\n\nHe is dressed in a crisp white shirt with the top buttons casually open, fitted black jeans, and fresh white sneakers — a clean, urban style that blends casual elegance with commercial appeal. Behind him, several sleek, modern camper vans are lined up neatly, their glossy surfaces catching the light and reflecting the dealership’s premium image.\n\nThe scene takes place in daylight, with soft natural sunlight enhanced by cinematic lighting effects: subtle lens flares, vivid contrast, and a shallow depth of field that keeps the background slightly blurred while the character remains sharply focused. The mood is polished and aspirational, like a high-end automotive advertisement.\n\nThe entire visual must be **ultra-realistic**, with photo-accurate textures, natural lighting, lifelike proportions, and refined composition. The atmosphere should evoke the quality and prestige of a modern vehicle commercial — professional, impactful, and visually engaging.\n",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "9:16",
  "output_format": "webp",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 50
}

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=24446309048320
Downloading weights
2025-07-21T17:55:27Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmp9qxete5o/weights url=https://replicate.delivery/xezq/P2QxeW5VKGRuDaOTNZR7QdyGrQnWQgDOrJfh1vrklT0e8FGqA/flux-lora.tar
2025-07-21T17:55:27Z | INFO  | [ Cache Service ] enabled=true scheme=http target=hermes.services.svc.cluster.local
2025-07-21T17:55:27Z | INFO  | [ Cache URL Rewrite ] enabled=true target_url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/P2QxeW5VKGRuDaOTNZR7QdyGrQnWQgDOrJfh1vrklT0e8FGqA/flux-lora.tar url=https://replicate.delivery/xezq/P2QxeW5VKGRuDaOTNZR7QdyGrQnWQgDOrJfh1vrklT0e8FGqA/flux-lora.tar
2025-07-21T17:55:27Z | INFO  | [ Redirect ] redirect_url=http://r8-east4-loras-ric1.cwlota.com/54924b36e73169210df2c08568faab433bb31fa26e70b46d00ab143a07d684c7?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Checksum-Mode=ENABLED&X-Amz-Credential=CWNZUVKLDHXVHEZN%2F20250721%2FUS-EAST-04A%2Fs3%2Faws4_request&X-Amz-Date=20250721T175527Z&X-Amz-Expires=600&X-Amz-SignedHeaders=host&x-id=GetObject&X-Amz-Signature=d909762364cbcfe082aa6aae6857b9debf4972d8114bc2333cfa3a5a05ce4fa5 url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/P2QxeW5VKGRuDaOTNZR7QdyGrQnWQgDOrJfh1vrklT0e8FGqA/flux-lora.tar
2025-07-21T17:55:27Z | INFO  | [ Complete ] dest=/tmp/tmp9qxete5o/weights size="172 MB" total_elapsed=0.444s url=https://replicate.delivery/xezq/P2QxeW5VKGRuDaOTNZR7QdyGrQnWQgDOrJfh1vrklT0e8FGqA/flux-lora.tar
Downloaded weights in 0.50s
Loaded LoRAs in 1.02s
Using seed: 32443
Prompt: The character named adcom is shown facing the camera, standing confidently outdoors on the lot of a modern motorhome dealership. He has short, well-groomed hair and a bright, friendly smile that conveys professionalism and approachability. His posture is natural yet assertive, with his arms relaxed at his sides and a subtle weight shift onto one leg, capturing the charisma of a brand ambassador.
He is dressed in a crisp white shirt with the top buttons casually open, fitted black jeans, and fresh white sneakers — a clean, urban style that blends casual elegance with commercial appeal. Behind him, several sleek, modern camper vans are lined up neatly, their glossy surfaces catching the light and reflecting the dealership’s premium image.
The scene takes place in daylight, with soft natural sunlight enhanced by cinematic lighting effects: subtle lens flares, vivid contrast, and a shallow depth of field that keeps the background slightly blurred while the character remains sharply focused. The mood is polished and aspirational, like a high-end automotive advertisement.
The entire visual must be **ultra-realistic**, with photo-accurate textures, natural lighting, lifelike proportions, and refined composition. The atmosphere should evoke the quality and prestige of a modern vehicle commercial — professional, impactful, and visually engaging.
[!] txt2img mode
  0%|          | 0/50 [00:00<?, ?it/s]
  2%|▏         | 1/50 [00:00<00:12,  3.84it/s]
  4%|▍         | 2/50 [00:00<00:11,  4.36it/s]
  6%|▌         | 3/50 [00:00<00:11,  4.11it/s]
  8%|▊         | 4/50 [00:00<00:11,  4.01it/s]
 10%|█         | 5/50 [00:01<00:11,  3.95it/s]
 12%|█▏        | 6/50 [00:01<00:11,  3.92it/s]
 14%|█▍        | 7/50 [00:01<00:11,  3.90it/s]
 16%|█▌        | 8/50 [00:02<00:10,  3.88it/s]
 18%|█▊        | 9/50 [00:02<00:10,  3.87it/s]
 20%|██        | 10/50 [00:02<00:10,  3.87it/s]
 22%|██▏       | 11/50 [00:02<00:10,  3.86it/s]
 24%|██▍       | 12/50 [00:03<00:09,  3.86it/s]
 26%|██▌       | 13/50 [00:03<00:09,  3.86it/s]
 28%|██▊       | 14/50 [00:03<00:09,  3.86it/s]
 30%|███       | 15/50 [00:03<00:09,  3.85it/s]
 32%|███▏      | 16/50 [00:04<00:08,  3.85it/s]
 34%|███▍      | 17/50 [00:04<00:08,  3.85it/s]
 36%|███▌      | 18/50 [00:04<00:08,  3.85it/s]
 38%|███▊      | 19/50 [00:04<00:08,  3.85it/s]
 40%|████      | 20/50 [00:05<00:07,  3.85it/s]
 42%|████▏     | 21/50 [00:05<00:07,  3.85it/s]
 44%|████▍     | 22/50 [00:05<00:07,  3.85it/s]
 46%|████▌     | 23/50 [00:05<00:07,  3.85it/s]
 48%|████▊     | 24/50 [00:06<00:06,  3.85it/s]
 50%|█████     | 25/50 [00:06<00:06,  3.85it/s]
 52%|█████▏    | 26/50 [00:06<00:06,  3.85it/s]
 54%|█████▍    | 27/50 [00:06<00:05,  3.85it/s]
 56%|█████▌    | 28/50 [00:07<00:05,  3.85it/s]
 58%|█████▊    | 29/50 [00:07<00:05,  3.85it/s]
 60%|██████    | 30/50 [00:07<00:05,  3.85it/s]
 62%|██████▏   | 31/50 [00:07<00:04,  3.85it/s]
 64%|██████▍   | 32/50 [00:08<00:04,  3.85it/s]
 66%|██████▌   | 33/50 [00:08<00:04,  3.85it/s]
 68%|██████▊   | 34/50 [00:08<00:04,  3.85it/s]
 70%|███████   | 35/50 [00:09<00:03,  3.85it/s]
 72%|███████▏  | 36/50 [00:09<00:03,  3.85it/s]
 74%|███████▍  | 37/50 [00:09<00:03,  3.85it/s]
 76%|███████▌  | 38/50 [00:09<00:03,  3.85it/s]
 78%|███████▊  | 39/50 [00:10<00:02,  3.85it/s]
 80%|████████  | 40/50 [00:10<00:02,  3.85it/s]
 82%|████████▏ | 41/50 [00:10<00:02,  3.85it/s]
 84%|████████▍ | 42/50 [00:10<00:02,  3.85it/s]
 86%|████████▌ | 43/50 [00:11<00:01,  3.85it/s]
 88%|████████▊ | 44/50 [00:11<00:01,  3.85it/s]
 90%|█████████ | 45/50 [00:11<00:01,  3.85it/s]
 92%|█████████▏| 46/50 [00:11<00:01,  3.85it/s]
 94%|█████████▍| 47/50 [00:12<00:00,  3.85it/s]
 96%|█████████▌| 48/50 [00:12<00:00,  3.85it/s]
 98%|█████████▊| 49/50 [00:12<00:00,  3.85it/s]
100%|██████████| 50/50 [00:12<00:00,  3.84it/s]
100%|██████████| 50/50 [00:12<00:00,  3.87it/s]
Total safe images: 1 out of 1

Version Details

Version ID: 11be480548c9a1f1c4658329cd840a68a9d1a5a4b28c13d54d764d07e11feaf5
Version Created: July 21, 2025

Run on Replicate →