ryokeken/bigboi 🖼️🔢❓📝✓ → 🖼️

▶️ 178 runs 📅 Oct 2024 ⚙️ Cog 0.9.23

About

bigboi the stray cat

Example Output

Prompt:

"a well lit studio photo portrait of bigboi the stray cat on a elegant minimalist wood stool ,standing like a ballerina,white background "

Output

Performance Metrics

22.83s Prediction Time

74.06s Total Time

All Input Parameters

{
  "seed": 1234567890,
  "model": "dev",
  "width": 1440,
  "height": 1440,
  "prompt": "a well lit studio photo portrait of bigboi the stray cat on a elegant minimalist wood stool ,standing like a ballerina,white background ",
  "lora_scale": 1,
  "num_outputs": 2,
  "aspect_ratio": "9:16",
  "output_format": "png",
  "guidance_scale": 3.5,
  "output_quality": 100,
  "prompt_strength": 1,
  "extra_lora_scale": 1,
  "num_inference_steps": 30
}

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: 1234567890
Prompt: a well lit studio photo portrait of bigboi the stray cat on a elegant minimalist wood stool ,standing like a ballerina,white background
[!] txt2img mode
Using dev model
free=6549844111360
Downloading weights
2024-10-11T16:11:38Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpqbegfr89/weights url=https://replicate.delivery/yhqm/CZhcm96UcqqrOZ1koF0vjxnpKBa6iOncPaOheZBEdIISvyyJA/trained_model.tar
2024-10-11T16:11:40Z | INFO  | [ Complete ] dest=/tmp/tmpqbegfr89/weights size="172 MB" total_elapsed=1.525s url=https://replicate.delivery/yhqm/CZhcm96UcqqrOZ1koF0vjxnpKBa6iOncPaOheZBEdIISvyyJA/trained_model.tar
Downloaded weights in 1.62s
Loaded LoRAs in 2.34s
  0%|          | 0/30 [00:00<?, ?it/s]
  3%|▎         | 1/30 [00:00<00:19,  1.53it/s]
  7%|▋         | 2/30 [00:01<00:16,  1.70it/s]
 10%|█         | 3/30 [00:01<00:16,  1.62it/s]
 13%|█▎        | 4/30 [00:02<00:16,  1.58it/s]
 17%|█▋        | 5/30 [00:03<00:16,  1.56it/s]
 20%|██        | 6/30 [00:03<00:15,  1.55it/s]
 23%|██▎       | 7/30 [00:04<00:14,  1.54it/s]
 27%|██▋       | 8/30 [00:05<00:14,  1.54it/s]
 30%|███       | 9/30 [00:05<00:13,  1.53it/s]
 33%|███▎      | 10/30 [00:06<00:13,  1.53it/s]
 37%|███▋      | 11/30 [00:07<00:12,  1.53it/s]
 40%|████      | 12/30 [00:07<00:11,  1.53it/s]
 43%|████▎     | 13/30 [00:08<00:11,  1.53it/s]
 47%|████▋     | 14/30 [00:09<00:10,  1.53it/s]
 50%|█████     | 15/30 [00:09<00:09,  1.53it/s]
 53%|█████▎    | 16/30 [00:10<00:09,  1.53it/s]
 57%|█████▋    | 17/30 [00:11<00:08,  1.53it/s]
 60%|██████    | 18/30 [00:11<00:07,  1.53it/s]
 63%|██████▎   | 19/30 [00:12<00:07,  1.53it/s]
 67%|██████▋   | 20/30 [00:12<00:06,  1.53it/s]
 70%|███████   | 21/30 [00:13<00:05,  1.53it/s]
 73%|███████▎  | 22/30 [00:14<00:05,  1.53it/s]
 77%|███████▋  | 23/30 [00:14<00:04,  1.53it/s]
 80%|████████  | 24/30 [00:15<00:03,  1.53it/s]
 83%|████████▎ | 25/30 [00:16<00:03,  1.53it/s]
 87%|████████▋ | 26/30 [00:16<00:02,  1.53it/s]
 90%|█████████ | 27/30 [00:17<00:01,  1.53it/s]
 93%|█████████▎| 28/30 [00:18<00:01,  1.53it/s]
 97%|█████████▋| 29/30 [00:18<00:00,  1.53it/s]
100%|██████████| 30/30 [00:19<00:00,  1.53it/s]
100%|██████████| 30/30 [00:19<00:00,  1.53it/s]

Version Details

Version ID: 262c44d38a47d71dc0168728963b5549666a5be21d1a04b87675d3f682ed7267
Version Created: October 11, 2024

Run on Replicate →