andreeaboeriu-ai/alina 🖼️🔢❓📝✓ → 🖼️

▶️ 105 runs 📅 Sep 2025 ⚙️ Cog 0.13.6

About

Example Output

Prompt:

"Alina on a white horse, ultrarealistic portrait, sharp focus on alina's face, expressive eyes, red hair, natural cinematic light, dramatic mountains in background, hyperdetailed skin, photorealism, award-winning photography --negative blurry, distorted, cartoon, CGI, lowres, text, watermark, bad anatomy"

Output

Performance Metrics

31.36s Prediction Time

31.45s Total Time

All Input Parameters

{
  "model": "dev",
  "prompt": "Alina on a white horse, ultrarealistic portrait, sharp focus on alina's face, expressive eyes, red hair, natural cinematic light, dramatic mountains in background, hyperdetailed skin, photorealism, award-winning photography --negative blurry, distorted, cartoon, CGI, lowres, text, watermark, bad anatomy\n\n",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 4,
  "aspect_ratio": "16:9",
  "output_format": "webp",
  "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

free=26789511434240
Downloading weights
2025-10-01T21:20:51Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpsa0a3jg_/weights url=https://replicate.delivery/xezq/g5IGnos25eweUkw6nAAKFa5feiV9Tn8UGJSOffO7FlmYCbNWF/flux-lora.tar
2025-10-01T21:20:51Z | INFO  | [ Cache Service ] enabled=true scheme=http target=hermes.services.svc.cluster.local
2025-10-01T21:20:51Z | INFO  | [ Cache URL Rewrite ] enabled=true target_url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/g5IGnos25eweUkw6nAAKFa5feiV9Tn8UGJSOffO7FlmYCbNWF/flux-lora.tar url=https://replicate.delivery/xezq/g5IGnos25eweUkw6nAAKFa5feiV9Tn8UGJSOffO7FlmYCbNWF/flux-lora.tar
2025-10-01T21:20:51Z | INFO  | [ Redirect ] redirect_url=http://r8-east4-loras-ric1.cwlota.com/25c55d70f1305e71d949fbd63d8b6823ff0d725b3c552bd439c9a67388ce4b72?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Checksum-Mode=ENABLED&X-Amz-Credential=CWNZUVKLDHXVHEZN%2F20251001%2FUS-EAST-04A%2Fs3%2Faws4_request&X-Amz-Date=20251001T212051Z&X-Amz-Expires=600&X-Amz-SignedHeaders=host&x-id=GetObject&X-Amz-Signature=973ca042dd26b84914c169f34a1af6506230207976407bcb5a60761df5feec8c url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/g5IGnos25eweUkw6nAAKFa5feiV9Tn8UGJSOffO7FlmYCbNWF/flux-lora.tar
2025-10-01T21:20:51Z | INFO  | [ Complete ] dest=/tmp/tmpsa0a3jg_/weights size="172 MB" total_elapsed=0.238s url=https://replicate.delivery/xezq/g5IGnos25eweUkw6nAAKFa5feiV9Tn8UGJSOffO7FlmYCbNWF/flux-lora.tar
Downloaded weights in 0.30s
Loaded LoRAs in 1.53s
Using seed: 30131
Prompt: Alina on a white horse, ultrarealistic portrait, sharp focus on alina's face, expressive eyes, red hair, natural cinematic light, dramatic mountains in background, hyperdetailed skin, photorealism, award-winning photography --negative blurry, distorted, cartoon, CGI, lowres, text, watermark, bad anatomy
[!] txt2img mode
  0%|          | 0/28 [00:00<?, ?it/s]
  4%|▎         | 1/28 [00:00<00:25,  1.06it/s]
  7%|▋         | 2/28 [00:01<00:21,  1.19it/s]
 11%|█         | 3/28 [00:02<00:22,  1.12it/s]
 14%|█▍        | 4/28 [00:03<00:21,  1.09it/s]
 18%|█▊        | 5/28 [00:04<00:21,  1.08it/s]
 21%|██▏       | 6/28 [00:05<00:20,  1.07it/s]
 25%|██▌       | 7/28 [00:06<00:19,  1.06it/s]
 29%|██▊       | 8/28 [00:07<00:18,  1.06it/s]
 32%|███▏      | 9/28 [00:08<00:18,  1.06it/s]
 36%|███▌      | 10/28 [00:09<00:17,  1.05it/s]
 39%|███▉      | 11/28 [00:10<00:16,  1.05it/s]
 43%|████▎     | 12/28 [00:11<00:15,  1.05it/s]
 46%|████▋     | 13/28 [00:12<00:14,  1.05it/s]
 50%|█████     | 14/28 [00:13<00:13,  1.05it/s]
 54%|█████▎    | 15/28 [00:14<00:12,  1.05it/s]
 57%|█████▋    | 16/28 [00:15<00:11,  1.05it/s]
 61%|██████    | 17/28 [00:16<00:10,  1.05it/s]
 64%|██████▍   | 18/28 [00:16<00:09,  1.05it/s]
 68%|██████▊   | 19/28 [00:17<00:08,  1.05it/s]
 71%|███████▏  | 20/28 [00:18<00:07,  1.05it/s]
 75%|███████▌  | 21/28 [00:19<00:06,  1.05it/s]
 79%|███████▊  | 22/28 [00:20<00:05,  1.05it/s]
 82%|████████▏ | 23/28 [00:21<00:04,  1.05it/s]
 86%|████████▌ | 24/28 [00:22<00:03,  1.05it/s]
 89%|████████▉ | 25/28 [00:23<00:02,  1.05it/s]
 93%|█████████▎| 26/28 [00:24<00:01,  1.05it/s]
 96%|█████████▋| 27/28 [00:25<00:00,  1.05it/s]
100%|██████████| 28/28 [00:26<00:00,  1.05it/s]
100%|██████████| 28/28 [00:26<00:00,  1.06it/s]
Total safe images: 4 out of 4

Version Details

Version ID: baf5c9c337efb3652996fd8ff6753c93267d803f4214136a39cee53072d9c881
Version Created: September 25, 2025

Run on Replicate →