stonerjay420/scene-hair 🖼️🔢❓📝✓ → 🖼️

▶️ 19 runs 📅 Sep 2024 ⚙️ Cog 0.9.23

About

Example Output

Prompt:

"SceneKid, petite, ashen-skinned, innocent, 18yo, 1girl, short crop top, daisy dukes, blue eyes, flawless skin, high definition"

Output

Performance Metrics

15.34s Prediction Time

15.45s Total Time

All Input Parameters

{
  "model": "dev",
  "width": 727,
  "height": 1374,
  "prompt": "SceneKid, petite, ashen-skinned, innocent, 18yo, 1girl, short crop top, daisy dukes, blue eyes, flawless skin, high definition",
  "go_fast": true,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 4,
  "aspect_ratio": "9:16",
  "output_format": "png",
  "guidance_scale": 2.21,
  "output_quality": 100,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 33
}

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

Lora https://replicate.delivery/yhqm/PezhfyyEv2nAXkCRPB0Tp9JDtCyHjyFRspQOes3vVVl1gufNB/trained_model.tar already loaded
running quantized prediction
Using seed: 895564276
  0%|          | 0/33 [00:00<?, ?it/s]
  9%|▉         | 3/33 [00:00<00:01, 15.70it/s]
 15%|█▌        | 5/33 [00:00<00:02, 12.79it/s]
 21%|██        | 7/33 [00:00<00:02, 11.77it/s]
 27%|██▋       | 9/33 [00:00<00:02, 11.33it/s]
 33%|███▎      | 11/33 [00:00<00:02, 10.76it/s]
 39%|███▉      | 13/33 [00:01<00:01, 10.61it/s]
 45%|████▌     | 15/33 [00:01<00:01, 10.57it/s]
 52%|█████▏    | 17/33 [00:01<00:01, 10.58it/s]
 58%|█████▊    | 19/33 [00:01<00:01, 10.55it/s]
 64%|██████▎   | 21/33 [00:01<00:01, 10.44it/s]
 70%|██████▉   | 23/33 [00:02<00:00, 10.37it/s]
 76%|███████▌  | 25/33 [00:02<00:00, 10.43it/s]
 82%|████████▏ | 27/33 [00:02<00:00, 10.47it/s]
 88%|████████▊ | 29/33 [00:02<00:00, 10.52it/s]
 94%|█████████▍| 31/33 [00:02<00:00, 10.47it/s]
100%|██████████| 33/33 [00:03<00:00, 10.41it/s]
100%|██████████| 33/33 [00:03<00:00, 10.75it/s]
  0%|          | 0/33 [00:00<?, ?it/s]
  6%|▌         | 2/33 [00:00<00:02, 10.46it/s]
 12%|█▏        | 4/33 [00:00<00:02, 10.46it/s]
 18%|█▊        | 6/33 [00:00<00:02, 10.47it/s]
 24%|██▍       | 8/33 [00:00<00:02, 10.40it/s]
 30%|███       | 10/33 [00:00<00:02, 10.37it/s]
 36%|███▋      | 12/33 [00:01<00:02, 10.37it/s]
 42%|████▏     | 14/33 [00:01<00:01, 10.39it/s]
 48%|████▊     | 16/33 [00:01<00:01, 10.43it/s]
 55%|█████▍    | 18/33 [00:01<00:01, 10.42it/s]
 61%|██████    | 20/33 [00:01<00:01, 10.41it/s]
 67%|██████▋   | 22/33 [00:02<00:01, 10.39it/s]
 73%|███████▎  | 24/33 [00:02<00:00, 10.43it/s]
 79%|███████▉  | 26/33 [00:02<00:00, 10.44it/s]
 85%|████████▍ | 28/33 [00:02<00:00, 10.41it/s]
 91%|█████████ | 30/33 [00:02<00:00, 10.40it/s]
 97%|█████████▋| 32/33 [00:03<00:00, 10.37it/s]
100%|██████████| 33/33 [00:03<00:00, 10.40it/s]
  0%|          | 0/33 [00:00<?, ?it/s]
  6%|▌         | 2/33 [00:00<00:02, 10.59it/s]
 12%|█▏        | 4/33 [00:00<00:02, 10.51it/s]
 18%|█▊        | 6/33 [00:00<00:02, 10.50it/s]
 24%|██▍       | 8/33 [00:00<00:02, 10.47it/s]
 30%|███       | 10/33 [00:00<00:02, 10.44it/s]
 36%|███▋      | 12/33 [00:01<00:02, 10.41it/s]
 42%|████▏     | 14/33 [00:01<00:01, 10.44it/s]
 48%|████▊     | 16/33 [00:01<00:01, 10.44it/s]
 55%|█████▍    | 18/33 [00:01<00:01, 10.42it/s]
 61%|██████    | 20/33 [00:01<00:01, 10.40it/s]
 67%|██████▋   | 22/33 [00:02<00:01, 10.40it/s]
 73%|███████▎  | 24/33 [00:02<00:00, 10.39it/s]
 79%|███████▉  | 26/33 [00:02<00:00, 10.40it/s]
 85%|████████▍ | 28/33 [00:02<00:00, 10.38it/s]
 91%|█████████ | 30/33 [00:02<00:00, 10.35it/s]
 97%|█████████▋| 32/33 [00:03<00:00, 10.37it/s]
100%|██████████| 33/33 [00:03<00:00, 10.41it/s]
  0%|          | 0/33 [00:00<?, ?it/s]
  6%|▌         | 2/33 [00:00<00:02, 10.44it/s]
 12%|█▏        | 4/33 [00:00<00:02, 10.41it/s]
 18%|█▊        | 6/33 [00:00<00:02, 10.35it/s]
 24%|██▍       | 8/33 [00:00<00:02, 10.34it/s]
 30%|███       | 10/33 [00:00<00:02, 10.32it/s]
 36%|███▋      | 12/33 [00:01<00:02, 10.37it/s]
 42%|████▏     | 14/33 [00:01<00:01, 10.40it/s]
 48%|████▊     | 16/33 [00:01<00:01, 10.39it/s]
 55%|█████▍    | 18/33 [00:01<00:01, 10.44it/s]
 61%|██████    | 20/33 [00:01<00:01, 10.42it/s]
 67%|██████▋   | 22/33 [00:02<00:01, 10.42it/s]
 73%|███████▎  | 24/33 [00:02<00:00, 10.40it/s]
 79%|███████▉  | 26/33 [00:02<00:00, 10.38it/s]
 85%|████████▍ | 28/33 [00:02<00:00, 10.36it/s]
 91%|█████████ | 30/33 [00:02<00:00, 10.42it/s]
 97%|█████████▋| 32/33 [00:03<00:00, 10.44it/s]
100%|██████████| 33/33 [00:03<00:00, 10.40it/s]
NSFW content detected in image 1
NSFW content detected in image 3
Total safe images: 2 out of 4

Version Details

Version ID: 8de8d7803b4a520bc590fa37dc19fc7a47b80806746d053b909df3729faf19b6
Version Created: September 23, 2024

Run on Replicate →