krisdoan/au2115n 🖼️🔢❓📝✓ → 🖼️

▶️ 52 runs 📅 Jul 2025 ⚙️ Cog 0.13.6
eyeglasses glasses image-inpainting lora text-to-image

About

Example Output

Prompt:

"{
"meta": {
"styleName": "minimalist portrait photography",
"aspectRatio": "2:3",
"seed": null
},
"camera": {
"model": "50mm standard lens equivalent",
"lens": "f/4 aperture simulation",
"focalLength": "medium depth of field, background is present but gently out of focus, less blurry than a wider aperture. The focus is sharp on the eyes and face, softly falling off across the hair and shoulders."
},
"subject": {
"primary": "A Japanese woman in her 30s with natural, realistic skin and refined features. Her skin has subtle imperfections for enhanced realism, such as visible light freckles across her nose and cheeks and a tiny, distinct beauty mark (mole) near her lip or cheek.",
"emotion": "A gentle and approachable expression with a soft, direct gaze into the camera, conveying warmth and quiet confidence.",
"pose": "A classic portrait pose. Her body is slightly angled away from the camera, while her head is turned gently towards it with a slight tilt. One hand is delicately raised near her collarbone, with fingers relaxed, adding a soft, framing element to the composition."
},
"character": {
"identity": "30s Japanese female",
"appearance": "neatly styled medium-length dark brown hair, natural and refined makeup with soft pink lips, delicate facial structure",
"wardrobe": "A simple and elegant light-colored blouse or top with a soft texture."
},
"accessories": {
"eyewear": {
"model": "a pair of OWNDAYS AU2115N eyeglasses, rendered in a compact, standard size equivalent to a 49mm frame",
"style": "A contemporary but compact square frame from high-quality acetate in a deep, solid black (C1). The frame has a polished satin finish. The design should be interpreted as a standard, not oversized, fit.",
"fit": "A compact and tailored fit, avoiding any sense of being oversized. The intended visual size on the face should be equivalent to a classic 49mm to 50mm lens width frame. The goal is a sophisticated, understated, and perfectly normal size, not a bold, statement-making one.",
"positioning": "perfectly centered on nose bridge, symmetrical on both temples",
"nosePads": "Integrated acetate nose pads (saddle bridge style), sculpted directly into the frame for a seamless, modern look and a comfortable, fixed fit against the nose.",
"integration": "The polished black acetate catches soft, defined reflections. The frame casts a minimal shadow, consistent with its compact size."
}
},
"composition": {
"theory": "close-up crop focused on the face, with the hand creating a gentle leading line",
"visualHierarchy": "The glasses act as a refined accent, framing the eyes without overpowering the facial features."
},
"postEditing": {
"treatments": "high-end beauty retouching that preserves natural skin texture",
"filmStock": "emulation of a modern film stock like Fujifilm Pro 400H or Kodak Portra, characterized by a slightly lifted black point (faded look) and a fine, pleasant grain"
}
}"

Output

Example output

Performance Metrics

8.24s Prediction Time
8.35s Total Time
All Input Parameters
{
  "model": "dev",
  "width": 1440,
  "height": 1440,
  "prompt": "{\n  \"meta\": {\n    \"styleName\": \"minimalist portrait photography\",\n    \"aspectRatio\": \"2:3\",\n    \"seed\": null\n  },\n  \"camera\": {\n    \"model\": \"50mm standard lens equivalent\",\n    \"lens\": \"f/4 aperture simulation\",\n    \"focalLength\": \"medium depth of field, background is present but gently out of focus, less blurry than a wider aperture. The focus is sharp on the eyes and face, softly falling off across the hair and shoulders.\"\n  },\n  \"subject\": {\n    \"primary\": \"A Japanese woman in her 30s with natural, realistic skin and refined features. Her skin has subtle imperfections for enhanced realism, such as visible light freckles across her nose and cheeks and a tiny, distinct beauty mark (mole) near her lip or cheek.\",\n    \"emotion\": \"A gentle and approachable expression with a soft, direct gaze into the camera, conveying warmth and quiet confidence.\",\n    \"pose\": \"A classic portrait pose. Her body is slightly angled away from the camera, while her head is turned gently towards it with a slight tilt. One hand is delicately raised near her collarbone, with fingers relaxed, adding a soft, framing element to the composition.\"\n  },\n  \"character\": {\n    \"identity\": \"30s Japanese female\",\n    \"appearance\": \"neatly styled medium-length dark brown hair, natural and refined makeup with soft pink lips, delicate facial structure\",\n    \"wardrobe\": \"A simple and elegant light-colored blouse or top with a soft texture.\"\n  },\n  \"accessories\": {\n    \"eyewear\": {\n      \"model\": \"a pair of OWNDAYS AU2115N eyeglasses, rendered in a compact, standard size equivalent to a 49mm frame\",\n      \"style\": \"A contemporary but compact square frame from high-quality acetate in a deep, solid black (C1). The frame has a polished satin finish. The design should be interpreted as a standard, not oversized, fit.\",\n      \"fit\": \"A compact and tailored fit, avoiding any sense of being oversized. The intended visual size on the face should be equivalent to a classic 49mm to 50mm lens width frame. The goal is a sophisticated, understated, and perfectly normal size, not a bold, statement-making one.\",\n      \"positioning\": \"perfectly centered on nose bridge, symmetrical on both temples\",\n      \"nosePads\": \"Integrated acetate nose pads (saddle bridge style), sculpted directly into the frame for a seamless, modern look and a comfortable, fixed fit against the nose.\",\n      \"integration\": \"The polished black acetate catches soft, defined reflections. The frame casts a minimal shadow, consistent with its compact size.\"\n    }\n  },\n  \"composition\": {\n    \"theory\": \"close-up crop focused on the face, with the hand creating a gentle leading line\",\n    \"visualHierarchy\": \"The glasses act as a refined accent, framing the eyes without overpowering the facial features.\"\n  },\n  \"postEditing\": {\n    \"treatments\": \"high-end beauty retouching that preserves natural skin texture\",\n    \"filmStock\": \"emulation of a modern film stock like Fujifilm Pro 400H or Kodak Portra, characterized by a slightly lifted black point (faded look) and a fine, pleasant grain\"\n  }\n}",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "9:16",
  "output_format": "png",
  "guidance_scale": 2,
  "output_quality": 100,
  "prompt_strength": 1,
  "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: arrayItems Type: stringItems Format: uri

Example Execution Logs
Loaded LoRAs in 0.51s
Using seed: 9561
Prompt: {
"meta": {
"styleName": "minimalist portrait photography",
"aspectRatio": "2:3",
"seed": null
},
"camera": {
"model": "50mm standard lens equivalent",
"lens": "f/4 aperture simulation",
"focalLength": "medium depth of field, background is present but gently out of focus, less blurry than a wider aperture. The focus is sharp on the eyes and face, softly falling off across the hair and shoulders."
},
"subject": {
"primary": "A Japanese woman in her 30s with natural, realistic skin and refined features. Her skin has subtle imperfections for enhanced realism, such as visible light freckles across her nose and cheeks and a tiny, distinct beauty mark (mole) near her lip or cheek.",
"emotion": "A gentle and approachable expression with a soft, direct gaze into the camera, conveying warmth and quiet confidence.",
"pose": "A classic portrait pose. Her body is slightly angled away from the camera, while her head is turned gently towards it with a slight tilt. One hand is delicately raised near her collarbone, with fingers relaxed, adding a soft, framing element to the composition."
},
"character": {
"identity": "30s Japanese female",
"appearance": "neatly styled medium-length dark brown hair, natural and refined makeup with soft pink lips, delicate facial structure",
"wardrobe": "A simple and elegant light-colored blouse or top with a soft texture."
},
"accessories": {
"eyewear": {
"model": "a pair of OWNDAYS AU2115N eyeglasses, rendered in a compact, standard size equivalent to a 49mm frame",
"style": "A contemporary but compact square frame from high-quality acetate in a deep, solid black (C1). The frame has a polished satin finish. The design should be interpreted as a standard, not oversized, fit.",
"fit": "A compact and tailored fit, avoiding any sense of being oversized. The intended visual size on the face should be equivalent to a classic 49mm to 50mm lens width frame. The goal is a sophisticated, understated, and perfectly normal size, not a bold, statement-making one.",
"positioning": "perfectly centered on nose bridge, symmetrical on both temples",
"nosePads": "Integrated acetate nose pads (saddle bridge style), sculpted directly into the frame for a seamless, modern look and a comfortable, fixed fit against the nose.",
"integration": "The polished black acetate catches soft, defined reflections. The frame casts a minimal shadow, consistent with its compact size."
}
},
"composition": {
"theory": "close-up crop focused on the face, with the hand creating a gentle leading line",
"visualHierarchy": "The glasses act as a refined accent, framing the eyes without overpowering the facial features."
},
"postEditing": {
"treatments": "high-end beauty retouching that preserves natural skin texture",
"filmStock": "emulation of a modern film stock like Fujifilm Pro 400H or Kodak Portra, characterized by a slightly lifted black point (faded look) and a fine, pleasant grain"
}
}
[!] txt2img mode
  0%|          | 0/28 [00:00<?, ?it/s]
  4%|▎         | 1/28 [00:00<00:06,  3.86it/s]
  7%|▋         | 2/28 [00:00<00:05,  4.38it/s]
 11%|█         | 3/28 [00:00<00:06,  4.13it/s]
 14%|█▍        | 4/28 [00:00<00:05,  4.03it/s]
 18%|█▊        | 5/28 [00:01<00:05,  3.97it/s]
 21%|██▏       | 6/28 [00:01<00:05,  3.94it/s]
 25%|██▌       | 7/28 [00:01<00:05,  3.91it/s]
 29%|██▊       | 8/28 [00:02<00:05,  3.90it/s]
 32%|███▏      | 9/28 [00:02<00:04,  3.89it/s]
 36%|███▌      | 10/28 [00:02<00:04,  3.89it/s]
 39%|███▉      | 11/28 [00:02<00:04,  3.88it/s]
 43%|████▎     | 12/28 [00:03<00:04,  3.88it/s]
 46%|████▋     | 13/28 [00:03<00:03,  3.88it/s]
 50%|█████     | 14/28 [00:03<00:03,  3.87it/s]
 54%|█████▎    | 15/28 [00:03<00:03,  3.87it/s]
 57%|█████▋    | 16/28 [00:04<00:03,  3.87it/s]
 61%|██████    | 17/28 [00:04<00:02,  3.87it/s]
 64%|██████▍   | 18/28 [00:04<00:02,  3.87it/s]
 68%|██████▊   | 19/28 [00:04<00:02,  3.87it/s]
 71%|███████▏  | 20/28 [00:05<00:02,  3.87it/s]
 75%|███████▌  | 21/28 [00:05<00:01,  3.87it/s]
 79%|███████▊  | 22/28 [00:05<00:01,  3.87it/s]
 82%|████████▏ | 23/28 [00:05<00:01,  3.87it/s]
 86%|████████▌ | 24/28 [00:06<00:01,  3.87it/s]
 89%|████████▉ | 25/28 [00:06<00:00,  3.87it/s]
 93%|█████████▎| 26/28 [00:06<00:00,  3.87it/s]
 96%|█████████▋| 27/28 [00:06<00:00,  3.87it/s]
100%|██████████| 28/28 [00:07<00:00,  3.87it/s]
100%|██████████| 28/28 [00:07<00:00,  3.90it/s]
Total safe images: 1 out of 1
Version Details
Version ID
89cee79872f037ff9c40e60ae45c9683707ed82f5551347d9152f5d38c62c866
Version Created
July 29, 2025
Run on Replicate →