realblissfulcode/arina222 🖼️🔢❓📝✓ → 🖼️

▶️ 37 runs 📅 Aug 2025 ⚙️ Cog 0.15.3
lora lora-person text-to-image

About

Example Output

Prompt:

"

A breathtakingly beautiful young woman with long, silky brunette hair cascading in soft waves, glowing under cinematic lighting. Her eyes are luminous and expressive, with a glassy depth that draws attention, framed by perfectly shaped brows and fluttering lashes. Her skin is flawless and radiant, with a subtle dewy finish that highlights her natural elegance. She has full, soft lips with a gentle sheen, capturing a sense of timeless allure.

She is dressed in a sleek, modern outfit — a flowing satin gown with delicate straps, shimmering subtly under the light. The setting feels dreamy and atmospheric, with soft neon glows in the background, hints of bokeh, and a touch of ethereal mist. The palette mixes warm golden highlights with cool, moody tones, creating a balance of intimacy and glamour. The atmosphere evokes both high-fashion editorial and cinematic portrait photography, blending contemporary pop-star aesthetics with classic Hollywood allure.

The artwork style is hyper-realistic yet painterly, with ultra-detailed textures in the hair, fabric, and lighting. A gentle aura surrounds her, giving her presence an almost divine or iconic quality, as if captured in the perfect moment of stardom. The mood is elegant, romantic, and captivating — a portrait that radiates beauty, artistry, and modern sophistication.

"

Output

Example outputExample output

Performance Metrics

20.82s Prediction Time
20.83s Total Time
All Input Parameters 
{
  "model": "dev",
  "width": 1080,
  "height": 1080,
  "prompt": "A breathtakingly beautiful young woman with long, silky brunette hair cascading in soft waves, glowing under cinematic lighting. Her eyes are luminous and expressive, with a glassy depth that draws attention, framed by perfectly shaped brows and fluttering lashes. Her skin is flawless and radiant, with a subtle dewy finish that highlights her natural elegance. She has full, soft lips with a gentle sheen, capturing a sense of timeless allure.\n\nShe is dressed in a sleek, modern outfit — a flowing satin gown with delicate straps, shimmering subtly under the light. The setting feels dreamy and atmospheric, with soft neon glows in the background, hints of bokeh, and a touch of ethereal mist. The palette mixes warm golden highlights with cool, moody tones, creating a balance of intimacy and glamour. The atmosphere evokes both high-fashion editorial and cinematic portrait photography, blending contemporary pop-star aesthetics with classic Hollywood allure.\n\nThe artwork style is hyper-realistic yet painterly, with ultra-detailed textures in the hair, fabric, and lighting. A gentle aura surrounds her, giving her presence an almost divine or iconic quality, as if captured in the perfect moment of stardom. The mood is elegant, romantic, and captivating — a portrait that radiates beauty, artistry, and modern sophistication.",
  "go_fast": false,
  "extra_lora": "huggingface.co/XLabs-AI/flux-RealismLora",
  "lora_scale": 0.91,
  "megapixels": "1",
  "num_outputs": 2,
  "aspect_ratio": "1:1",
  "output_format": "png",
  "guidance_scale": 1.97,
  "output_quality": 100,
  "prompt_strength": 0.45,
  "extra_lora_scale": 0.69,
  "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 
free=23620421783552
Downloading weights
2025-08-17T03:30:12Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmp6s_oq7f7/weights url=https://replicate.delivery/xezq/e6aZlS1ufdrHg036yiuk5H4Le7kqNOkr0SMfXffXfVWBj4eKVA/trained_model.tar
2025-08-17T03:30:12Z | INFO  | [ Cache Service ] enabled=true scheme=http target=hermes.services.svc.cluster.local
2025-08-17T03:30:12Z | INFO  | [ Cache URL Rewrite ] enabled=true target_url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/e6aZlS1ufdrHg036yiuk5H4Le7kqNOkr0SMfXffXfVWBj4eKVA/trained_model.tar url=https://replicate.delivery/xezq/e6aZlS1ufdrHg036yiuk5H4Le7kqNOkr0SMfXffXfVWBj4eKVA/trained_model.tar
2025-08-17T03:30:12Z | INFO  | [ Redirect ] redirect_url=http://r8-east4-loras-ric1.cwlota.com/f032fe9d3ee1e457c3e86500f4ad42d3b6f3631b2cdc6d67a9be8f607a2449a4?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Checksum-Mode=ENABLED&X-Amz-Credential=CWNZUVKLDHXVHEZN%2F20250817%2FUS-EAST-04A%2Fs3%2Faws4_request&X-Amz-Date=20250817T033012Z&X-Amz-Expires=600&X-Amz-SignedHeaders=host&x-id=GetObject&X-Amz-Signature=606191da5b87fd03bf49c580af86720d62cadd0540dea4e3d445a6b8ee1ac7f4 url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/e6aZlS1ufdrHg036yiuk5H4Le7kqNOkr0SMfXffXfVWBj4eKVA/trained_model.tar
2025-08-17T03:30:12Z | INFO  | [ Complete ] dest=/tmp/tmp6s_oq7f7/weights size="194 MB" total_elapsed=0.273s url=https://replicate.delivery/xezq/e6aZlS1ufdrHg036yiuk5H4Le7kqNOkr0SMfXffXfVWBj4eKVA/trained_model.tar
Downloaded weights in 0.34s
free=23620227575808
Downloading weights
2025-08-17T03:30:14Z | INFO  | [ Initiating ] chunk_size=150M dest=/src/weights-cache/c51ca67ff74544d0 url=https://huggingface.co/XLabs-AI/flux-RealismLora/resolve/main/lora.safetensors
2025-08-17T03:30:14Z | INFO  | [ Cache Service ] enabled=true scheme=http target=hermes.services.svc.cluster.local
2025-08-17T03:30:14Z | INFO  | [ Cache URL Rewrite ] enabled=true target_url=http://hermes.services.svc.cluster.local/huggingface.co/XLabs-AI/flux-RealismLora/resolve/main/lora.safetensors url=https://huggingface.co/XLabs-AI/flux-RealismLora/resolve/main/lora.safetensors
2025-08-17T03:30:14Z | INFO  | [ Redirect ] redirect_url=http://r8-huggingface-ric1.cwlota.com/8fb1df9be96086999d646784c02de649fce766d64730fb3edd09743d88c6ad62?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Checksum-Mode=ENABLED&X-Amz-Credential=CWNZUVKLDHXVHEZN%2F20250817%2FUS-EAST-04A%2Fs3%2Faws4_request&X-Amz-Date=20250817T033014Z&X-Amz-Expires=600&X-Amz-SignedHeaders=host&x-id=GetObject&X-Amz-Signature=1da9a0837345687ccd4245136249637fcaa132221805a2855564af5f7ecbe550 url=http://hermes.services.svc.cluster.local/huggingface.co/XLabs-AI/flux-RealismLora/resolve/main/lora.safetensors
2025-08-17T03:30:14Z | INFO  | [ Complete ] dest=/src/weights-cache/c51ca67ff74544d0 size="22 MB" total_elapsed=0.068s url=https://huggingface.co/XLabs-AI/flux-RealismLora/resolve/main/lora.safetensors
Downloaded weights in 0.12s
Loaded LoRAs in 2.54s
Using seed: 257
Prompt: A breathtakingly beautiful young woman with long, silky brunette hair cascading in soft waves, glowing under cinematic lighting. Her eyes are luminous and expressive, with a glassy depth that draws attention, framed by perfectly shaped brows and fluttering lashes. Her skin is flawless and radiant, with a subtle dewy finish that highlights her natural elegance. She has full, soft lips with a gentle sheen, capturing a sense of timeless allure.
She is dressed in a sleek, modern outfit — a flowing satin gown with delicate straps, shimmering subtly under the light. The setting feels dreamy and atmospheric, with soft neon glows in the background, hints of bokeh, and a touch of ethereal mist. The palette mixes warm golden highlights with cool, moody tones, creating a balance of intimacy and glamour. The atmosphere evokes both high-fashion editorial and cinematic portrait photography, blending contemporary pop-star aesthetics with classic Hollywood allure.
The artwork style is hyper-realistic yet painterly, with ultra-detailed textures in the hair, fabric, and lighting. A gentle aura surrounds her, giving her presence an almost divine or iconic quality, as if captured in the perfect moment of stardom. The mood is elegant, romantic, and captivating — a portrait that radiates beauty, artistry, and modern sophistication.
[!] txt2img mode
  0%|          | 0/30 [00:00<?, ?it/s]
  3%|▎         | 1/30 [00:00<00:16,  1.80it/s]
  7%|▋         | 2/30 [00:00<00:13,  2.11it/s]
 10%|█         | 3/30 [00:01<00:13,  2.02it/s]
 13%|█▎        | 4/30 [00:02<00:13,  1.98it/s]
 17%|█▋        | 5/30 [00:02<00:12,  1.96it/s]
 20%|██        | 6/30 [00:03<00:12,  1.95it/s]
 23%|██▎       | 7/30 [00:03<00:11,  1.94it/s]
 27%|██▋       | 8/30 [00:04<00:11,  1.93it/s]
 30%|███       | 9/30 [00:04<00:10,  1.93it/s]
 33%|███▎      | 10/30 [00:05<00:10,  1.93it/s]
 37%|███▋      | 11/30 [00:05<00:09,  1.92it/s]
 40%|████      | 12/30 [00:06<00:09,  1.92it/s]
 43%|████▎     | 13/30 [00:06<00:08,  1.92it/s]
 47%|████▋     | 14/30 [00:07<00:08,  1.92it/s]
 50%|█████     | 15/30 [00:07<00:07,  1.92it/s]
 53%|█████▎    | 16/30 [00:08<00:07,  1.92it/s]
 57%|█████▋    | 17/30 [00:08<00:06,  1.92it/s]
 60%|██████    | 18/30 [00:09<00:06,  1.92it/s]
 63%|██████▎   | 19/30 [00:09<00:05,  1.92it/s]
 67%|██████▋   | 20/30 [00:10<00:05,  1.92it/s]
 70%|███████   | 21/30 [00:10<00:04,  1.92it/s]
 73%|███████▎  | 22/30 [00:11<00:04,  1.92it/s]
 77%|███████▋  | 23/30 [00:11<00:03,  1.92it/s]
 80%|████████  | 24/30 [00:12<00:03,  1.92it/s]
 83%|████████▎ | 25/30 [00:12<00:02,  1.92it/s]
 87%|████████▋ | 26/30 [00:13<00:02,  1.92it/s]
 90%|█████████ | 27/30 [00:13<00:01,  1.92it/s]
 93%|█████████▎| 28/30 [00:14<00:01,  1.92it/s]
 97%|█████████▋| 29/30 [00:15<00:00,  1.92it/s]
100%|██████████| 30/30 [00:15<00:00,  1.92it/s]
100%|██████████| 30/30 [00:15<00:00,  1.93it/s]
Total safe images: 2 out of 2
Version Details
Version ID
64c783feb4dc04d6e21be342c7c9610786518e81bf6d1d9b952c80d6fef8a614
Version Created
August 14, 2025
Run on Replicate →