femkegr/dora 🖼️🔢❓📝✓ → 🖼️

▶️ 83 runs 📅 Sep 2024 ⚙️ Cog 0.9.23

About

Example Output

Prompt:

A photorealistic image of dora standing in front of a mirror, taking a mirror selfie. She is wearing a stylish and elegant two-piece outfit. The top is a strapless, fitted black bodice with a smooth, matte finish, hugging the torso snugly, with subtle vertical seam details to accentuate the fit. The fabric of the top is structured, creating a sleek and minimalist look, with no embellishments, buttons, or zippers visible.The skirt starts high-waisted and is made of a lightweight, flowy fabric in pure white, featuring soft, wide pleats that create a dynamic movement as it reaches down to her mid-calf. The pleats are uniform and create an elegant, flowing silhouette that contrasts perfectly with the fitted black top.

Her accessories include a small black patent leather handbag with a short strap, which she holds gracefully in her left hand. She is also wearing glossy black strappy high-heeled shoes with a closed pointed toe, adding to the refined, formal look.

The setting is a modern, minimalist room, featuring a light-colored dresser with books and a small decorative vase with a single flower. The lighting is natural and soft, enhancing the simplicity and elegance of the outfit and the overall aesthetic

Output

Performance Metrics

25.53s Prediction Time

179.11s Total Time

All Input Parameters

{
  "model": "dev",
  "prompt": "A photorealistic image of dora standing in front of a mirror, taking a mirror selfie. She is wearing a stylish and elegant two-piece outfit. The top is a strapless, fitted black bodice with a smooth, matte finish, hugging the torso snugly, with subtle vertical seam details to accentuate the fit. The fabric of the top is structured, creating a sleek and minimalist look, with no embellishments, buttons, or zippers visible.The skirt starts high-waisted and is made of a lightweight, flowy fabric in pure white, featuring soft, wide pleats that create a dynamic movement as it reaches down to her mid-calf. The pleats are uniform and create an elegant, flowing silhouette that contrasts perfectly with the fitted black top.\n\nHer accessories include a small black patent leather handbag with a short strap, which she holds gracefully in her left hand. She is also wearing glossy black strappy high-heeled shoes with a closed pointed toe, adding to the refined, formal look.\n\nThe setting is a modern, minimalist room, featuring a light-colored dresser with books and a small decorative vase with a single flower. The lighting is natural and soft, enhancing the simplicity and elegance of the outfit and the overall aesthetic",
  "lora_scale": 1,
  "num_outputs": 2,
  "aspect_ratio": "9:16",
  "output_format": "png",
  "guidance_scale": 3,
  "output_quality": 90,
  "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

Using seed: 43173
Prompt: A photorealistic image of dora standing in front of a mirror, taking a mirror selfie. She is wearing a stylish and elegant two-piece outfit. The top is a strapless, fitted black bodice with a smooth, matte finish, hugging the torso snugly, with subtle vertical seam details to accentuate the fit. The fabric of the top is structured, creating a sleek and minimalist look, with no embellishments, buttons, or zippers visible.The skirt starts high-waisted and is made of a lightweight, flowy fabric in pure white, featuring soft, wide pleats that create a dynamic movement as it reaches down to her mid-calf. The pleats are uniform and create an elegant, flowing silhouette that contrasts perfectly with the fitted black top.
Her accessories include a small black patent leather handbag with a short strap, which she holds gracefully in her left hand. She is also wearing glossy black strappy high-heeled shoes with a closed pointed toe, adding to the refined, formal look.
The setting is a modern, minimalist room, featuring a light-colored dresser with books and a small decorative vase with a single flower. The lighting is natural and soft, enhancing the simplicity and elegance of the outfit and the overall aesthetic
[!] txt2img mode
Using dev model
free=6530853081088
Downloading weights
2024-09-17T16:39:23Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpdciccxqx/weights url=https://replicate.delivery/yhqm/5QfG1ff0mdfOyTV1hehhkDLds5iZxqDoII5aizMcRSNqPZubC/trained_model.tar
2024-09-17T16:39:25Z | INFO  | [ Complete ] dest=/tmp/tmpdciccxqx/weights size="172 MB" total_elapsed=1.940s url=https://replicate.delivery/yhqm/5QfG1ff0mdfOyTV1hehhkDLds5iZxqDoII5aizMcRSNqPZubC/trained_model.tar
Downloaded weights in 1.97s
Loaded LoRAs in 9.33s
  0%|          | 0/28 [00:00<?, ?it/s]
  4%|▎         | 1/28 [00:00<00:14,  1.85it/s]
  7%|▋         | 2/28 [00:00<00:12,  2.10it/s]
 11%|█         | 3/28 [00:01<00:12,  1.98it/s]
 14%|█▍        | 4/28 [00:02<00:12,  1.93it/s]
 18%|█▊        | 5/28 [00:02<00:12,  1.90it/s]
 21%|██▏       | 6/28 [00:03<00:11,  1.88it/s]
 25%|██▌       | 7/28 [00:03<00:11,  1.87it/s]
 29%|██▊       | 8/28 [00:04<00:10,  1.86it/s]
 32%|███▏      | 9/28 [00:04<00:10,  1.86it/s]
 36%|███▌      | 10/28 [00:05<00:09,  1.86it/s]
 39%|███▉      | 11/28 [00:05<00:09,  1.85it/s]
 43%|████▎     | 12/28 [00:06<00:08,  1.85it/s]
 46%|████▋     | 13/28 [00:06<00:08,  1.85it/s]
 50%|█████     | 14/28 [00:07<00:07,  1.85it/s]
 54%|█████▎    | 15/28 [00:07<00:07,  1.85it/s]
 57%|█████▋    | 16/28 [00:08<00:06,  1.85it/s]
 61%|██████    | 17/28 [00:09<00:05,  1.85it/s]
 64%|██████▍   | 18/28 [00:09<00:05,  1.85it/s]
 68%|██████▊   | 19/28 [00:10<00:04,  1.85it/s]
 71%|███████▏  | 20/28 [00:10<00:04,  1.85it/s]
 75%|███████▌  | 21/28 [00:11<00:03,  1.85it/s]
 79%|███████▊  | 22/28 [00:11<00:03,  1.85it/s]
 82%|████████▏ | 23/28 [00:12<00:02,  1.85it/s]
 86%|████████▌ | 24/28 [00:12<00:02,  1.85it/s]
 89%|████████▉ | 25/28 [00:13<00:01,  1.85it/s]
 93%|█████████▎| 26/28 [00:13<00:01,  1.85it/s]
 96%|█████████▋| 27/28 [00:14<00:00,  1.85it/s]
100%|██████████| 28/28 [00:15<00:00,  1.85it/s]
100%|██████████| 28/28 [00:15<00:00,  1.86it/s]

Version Details

Version ID: a8d3923a1f7d8c227a3711246cbf4bd9a12817356b6f6d496e56bfe53d8ce4cc
Version Created: September 17, 2024

Run on Replicate →