micoblanc/dad-23-images 🖼️🔢❓📝✓ → 🖼️

▶️ 77 runs 📅 Nov 2024 ⚙️ Cog 0.11.1

About

Example Output

Prompt:

"TOK man looking at the camera with natural light"

Output

Performance Metrics

3.72s Prediction Time

24.33s Total Time

All Input Parameters

{
  "model": "dev",
  "prompt": "TOK man looking at the camera with natural light",
  "go_fast": true,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "jpg",
  "guidance_scale": 2,
  "output_quality": 90,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1.5,
  "num_inference_steps": 32
}

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

2024-11-26 22:10:41.895 | DEBUG    | fp8.lora_loading:apply_lora_to_model:569 - Extracting keys
2024-11-26 22:10:41.896 | DEBUG    | fp8.lora_loading:apply_lora_to_model:576 - Keys extracted
Applying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]
Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 13442.57it/s]
2024-11-26 22:10:41.918 | SUCCESS  | fp8.lora_loading:unload_loras:559 - LoRAs unloaded in 0.023s
2024-11-26 22:10:41.920 | INFO     | fp8.lora_loading:convert_lora_weights:493 - Loading LoRA weights for /src/weights-cache/c16590c7dd475b87
2024-11-26 22:10:41.992 | INFO     | fp8.lora_loading:convert_lora_weights:514 - LoRA weights loaded
2024-11-26 22:10:41.992 | DEBUG    | fp8.lora_loading:apply_lora_to_model:569 - Extracting keys
2024-11-26 22:10:41.992 | DEBUG    | fp8.lora_loading:apply_lora_to_model:576 - Keys extracted
Applying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]
Applying LoRA:  41%|████▏     | 126/304 [00:00<00:00, 1248.26it/s]
Applying LoRA:  83%|████████▎ | 251/304 [00:00<00:00, 983.60it/s] 
Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 969.09it/s]
2024-11-26 22:10:42.306 | SUCCESS  | fp8.lora_loading:load_lora:534 - LoRA applied in 0.39s
running quantized prediction
Using seed: 2941205488
  0%|          | 0/32 [00:00<?, ?it/s]
  6%|▋         | 2/32 [00:00<00:01, 16.70it/s]
 12%|█▎        | 4/32 [00:00<00:02, 12.31it/s]
 19%|█▉        | 6/32 [00:00<00:02, 11.39it/s]
 25%|██▌       | 8/32 [00:00<00:02, 10.98it/s]
 31%|███▏      | 10/32 [00:00<00:02, 10.64it/s]
 38%|███▊      | 12/32 [00:01<00:01, 10.47it/s]
 44%|████▍     | 14/32 [00:01<00:01, 10.43it/s]
 50%|█████     | 16/32 [00:01<00:01, 10.41it/s]
 56%|█████▋    | 18/32 [00:01<00:01, 10.41it/s]
 62%|██████▎   | 20/32 [00:01<00:01, 10.33it/s]
 69%|██████▉   | 22/32 [00:02<00:00, 10.28it/s]
 75%|███████▌  | 24/32 [00:02<00:00, 10.31it/s]
 81%|████████▏ | 26/32 [00:02<00:00, 10.30it/s]
 88%|████████▊ | 28/32 [00:02<00:00, 10.30it/s]
 94%|█████████▍| 30/32 [00:02<00:00, 10.31it/s]
100%|██████████| 32/32 [00:03<00:00, 10.28it/s]
100%|██████████| 32/32 [00:03<00:00, 10.55it/s]
Total safe images: 1 out of 1

Version Details

Version ID: 6f0027448906632fe3c96dea6dee27b55d712121d797f4e8aa9074987514756f
Version Created: November 26, 2024

Run on Replicate →