mayoita/oyadi 🖼️🔢❓📝✓ → 🖼️

▶️ 82 runs 📅 May 2025 ⚙️ Cog 0.14.3

About

Example Output

Prompt:

"A stunning, high-fashion photograph of Oyadi, a striking model with dark, curly hair, posed front-on, gazing directly at the camera with a confident expression, her features softly lit by a warm, golden key light positioned 45 degrees to her left, with a subtle fill light to the right, creating a sense of depth and dimension, evoking the visual style of iconic fashion photographer Annie Leibovitz, with a shallow depth of field (f/1.4) blurring the background, emphasizing Oyadi's elegant features, shot on Kodak Portra film stock, with a warm, analog color palette and subtle film grain."

Output

Performance Metrics

16.60s Prediction Time

16.89s Total Time

All Input Parameters

{
  "model": "dev",
  "prompt": "A stunning, high-fashion photograph of Oyadi, a striking model with dark, curly hair, posed front-on, gazing directly at the camera with a confident expression, her features softly lit by a warm, golden key light positioned 45 degrees to her left, with a subtle fill light to the right, creating a sense of depth and dimension, evoking the visual style of iconic fashion photographer Annie Leibovitz, with a shallow depth of field (f/1.4) blurring the background, emphasizing Oyadi's elegant features, shot on Kodak Portra film stock, with a warm, analog color palette and subtle film grain.",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "png",
  "guidance_scale": 2.41,
  "output_quality": 80,
  "prompt_strength": 0.44,
  "extra_lora_scale": 1,
  "num_inference_steps": 47
}

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=27559668039680
Downloading weights
2025-05-27T06:22:35Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpfz1_k9m5/weights url=https://replicate.delivery/xezq/C038WVD3k66uPFRqBfkARu7vjMMjZmSIc81J4vBAjLpf0dwUA/trained_model.tar
2025-05-27T06:22:35Z | INFO  | [ Cache Service ] enabled=true scheme=http target=hermes.services.svc.cluster.local
2025-05-27T06:22:38Z | INFO  | [ Complete ] dest=/tmp/tmpfz1_k9m5/weights size="344 MB" total_elapsed=3.183s url=https://replicate.delivery/xezq/C038WVD3k66uPFRqBfkARu7vjMMjZmSIc81J4vBAjLpf0dwUA/trained_model.tar
Downloaded weights in 3.21s
Loaded LoRAs in 3.81s
Using seed: 4519
Prompt: A stunning, high-fashion photograph of Oyadi, a striking model with dark, curly hair, posed front-on, gazing directly at the camera with a confident expression, her features softly lit by a warm, golden key light positioned 45 degrees to her left, with a subtle fill light to the right, creating a sense of depth and dimension, evoking the visual style of iconic fashion photographer Annie Leibovitz, with a shallow depth of field (f/1.4) blurring the background, emphasizing Oyadi's elegant features, shot on Kodak Portra film stock, with a warm, analog color palette and subtle film grain.
[!] txt2img mode
  0%|          | 0/47 [00:00<?, ?it/s]
  2%|▏         | 1/47 [00:00<00:12,  3.83it/s]
  4%|▍         | 2/47 [00:00<00:10,  4.34it/s]
  6%|▋         | 3/47 [00:00<00:10,  4.09it/s]
  9%|▊         | 4/47 [00:00<00:10,  3.99it/s]
 11%|█         | 5/47 [00:01<00:10,  3.93it/s]
 13%|█▎        | 6/47 [00:01<00:10,  3.90it/s]
 15%|█▍        | 7/47 [00:01<00:10,  3.88it/s]
 17%|█▋        | 8/47 [00:02<00:10,  3.86it/s]
 19%|█▉        | 9/47 [00:02<00:09,  3.86it/s]
 21%|██▏       | 10/47 [00:02<00:09,  3.85it/s]
 23%|██▎       | 11/47 [00:02<00:09,  3.84it/s]
 26%|██▌       | 12/47 [00:03<00:09,  3.84it/s]
 28%|██▊       | 13/47 [00:03<00:08,  3.84it/s]
 30%|██▉       | 14/47 [00:03<00:08,  3.84it/s]
 32%|███▏      | 15/47 [00:03<00:08,  3.84it/s]
 34%|███▍      | 16/47 [00:04<00:08,  3.83it/s]
 36%|███▌      | 17/47 [00:04<00:07,  3.84it/s]
 38%|███▊      | 18/47 [00:04<00:07,  3.83it/s]
 40%|████      | 19/47 [00:04<00:07,  3.83it/s]
 43%|████▎     | 20/47 [00:05<00:07,  3.83it/s]
 45%|████▍     | 21/47 [00:05<00:06,  3.83it/s]
 47%|████▋     | 22/47 [00:05<00:06,  3.84it/s]
 49%|████▉     | 23/47 [00:05<00:06,  3.84it/s]
 51%|█████     | 24/47 [00:06<00:05,  3.84it/s]
 53%|█████▎    | 25/47 [00:06<00:05,  3.84it/s]
 55%|█████▌    | 26/47 [00:06<00:05,  3.84it/s]
 57%|█████▋    | 27/47 [00:06<00:05,  3.84it/s]
 60%|█████▉    | 28/47 [00:07<00:04,  3.84it/s]
 62%|██████▏   | 29/47 [00:07<00:04,  3.84it/s]
 64%|██████▍   | 30/47 [00:07<00:04,  3.84it/s]
 66%|██████▌   | 31/47 [00:08<00:04,  3.84it/s]
 68%|██████▊   | 32/47 [00:08<00:03,  3.84it/s]
 70%|███████   | 33/47 [00:08<00:03,  3.84it/s]
 72%|███████▏  | 34/47 [00:08<00:03,  3.83it/s]
 74%|███████▍  | 35/47 [00:09<00:03,  3.84it/s]
 77%|███████▋  | 36/47 [00:09<00:02,  3.83it/s]
 79%|███████▊  | 37/47 [00:09<00:02,  3.83it/s]
 81%|████████  | 38/47 [00:09<00:02,  3.83it/s]
 83%|████████▎ | 39/47 [00:10<00:02,  3.83it/s]
 85%|████████▌ | 40/47 [00:10<00:01,  3.84it/s]
 87%|████████▋ | 41/47 [00:10<00:01,  3.84it/s]
 89%|████████▉ | 42/47 [00:10<00:01,  3.84it/s]
 91%|█████████▏| 43/47 [00:11<00:01,  3.84it/s]
 94%|█████████▎| 44/47 [00:11<00:00,  3.84it/s]
 96%|█████████▌| 45/47 [00:11<00:00,  3.84it/s]
 98%|█████████▊| 46/47 [00:11<00:00,  3.83it/s]
100%|██████████| 47/47 [00:12<00:00,  3.84it/s]
100%|██████████| 47/47 [00:12<00:00,  3.85it/s]
Total safe images: 1 out of 1

Version Details

Version ID: 86f7c59375584c7db13b59375ca0472f571745036fb985e63722eea5643fcbc9
Version Created: May 26, 2025

Run on Replicate →