drrhinoai/kris 🖼️🔢❓📝✓ → 🖼️

▶️ 57 runs 📅 Dec 2024 ⚙️ Cog 0.11.1

About

Example Output

Prompt:

"AIKRIS, an elite swimwear model, is standing at the rail of a yacht, admiring the panoramic view of the blue-green ocean. The neon accents of her swimsuit perfectly compliment her hair and eyes. The ocean breeze blows gently through her hair. Her fingers rest gently on the teak wood as she leans against the rail."

Output

Performance Metrics

7.78s Prediction Time

7.93s Total Time

All Input Parameters

{
  "model": "dev",
  "prompt": "AIKRIS, an elite swimwear model, is standing at the rail of a yacht, admiring the panoramic view of the blue-green ocean. The neon accents of her swimsuit perfectly compliment her hair and eyes. The ocean breeze blows gently through her hair. Her fingers rest gently on the teak wood as she leans against the rail.",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "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

2025-01-03 01:07:35.616 | DEBUG    | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys
2025-01-03 01:07:35.616 | DEBUG    | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted
Applying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]
Applying LoRA:  91%|█████████▏| 278/304 [00:00<00:00, 2758.05it/s]
Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2684.32it/s]
2025-01-03 01:07:35.730 | SUCCESS  | fp8.lora_loading:unload_loras:564 - LoRAs unloaded in 0.11s
free=29577782108160
Downloading weights
2025-01-03T01:07:35Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpgm5c1az0/weights url=https://replicate.delivery/xezq/gnrUF0q66sqHI5nsYyHjEjVizboFIqIWe37bgOLGqa8zEQAKA/trained_model.tar
2025-01-03T01:07:37Z | INFO  | [ Complete ] dest=/tmp/tmpgm5c1az0/weights size="172 MB" total_elapsed=1.344s url=https://replicate.delivery/xezq/gnrUF0q66sqHI5nsYyHjEjVizboFIqIWe37bgOLGqa8zEQAKA/trained_model.tar
Downloaded weights in 1.37s
2025-01-03 01:07:37.098 | INFO     | fp8.lora_loading:convert_lora_weights:498 - Loading LoRA weights for /src/weights-cache/d30bcc2ab7b66f61
2025-01-03 01:07:37.165 | INFO     | fp8.lora_loading:convert_lora_weights:519 - LoRA weights loaded
2025-01-03 01:07:37.165 | DEBUG    | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys
2025-01-03 01:07:37.165 | DEBUG    | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted
Applying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]
Applying LoRA:  91%|█████████▏| 278/304 [00:00<00:00, 2763.18it/s]
Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2689.09it/s]
2025-01-03 01:07:37.279 | SUCCESS  | fp8.lora_loading:load_lora:539 - LoRA applied in 0.18s
Using seed: 22356
0it [00:00, ?it/s]
1it [00:00,  8.35it/s]
2it [00:00,  5.84it/s]
3it [00:00,  5.32it/s]
4it [00:00,  5.12it/s]
5it [00:00,  4.98it/s]
6it [00:01,  4.89it/s]
7it [00:01,  4.86it/s]
8it [00:01,  4.84it/s]
9it [00:01,  4.84it/s]
10it [00:01,  4.82it/s]
11it [00:02,  4.81it/s]
12it [00:02,  4.81it/s]
13it [00:02,  4.80it/s]
14it [00:02,  4.80it/s]
15it [00:03,  4.80it/s]
16it [00:03,  4.79it/s]
17it [00:03,  4.79it/s]
18it [00:03,  4.79it/s]
19it [00:03,  4.79it/s]
20it [00:04,  4.79it/s]
21it [00:04,  4.79it/s]
22it [00:04,  4.79it/s]
23it [00:04,  4.80it/s]
24it [00:04,  4.80it/s]
25it [00:05,  4.79it/s]
26it [00:05,  4.79it/s]
27it [00:05,  4.79it/s]
28it [00:05,  4.78it/s]
28it [00:05,  4.87it/s]
Total safe images: 1 out of 1

Version Details

Version ID: 656cc6dad9a3c646d39848b2b56d2f7b1bc2fc65c4580304728f426d64699060
Version Created: December 31, 2024

Run on Replicate →