kaseylee20247263/tokk 🖼️🔢❓📝✓ → 🖼️

▶️ 329 runs 📅 Oct 2024 ⚙️ Cog 0.9.23

About

Example Output

Prompt:

"a raw photo realistic ,high quality photo of tokk photo taken cannon ,black hair natural look,a plus size woman,mid 30's wearing a simi transparent tank top , adjusting her top, smiling, pulling top,tan lines,small saggy breasts,(best quality,4k,8k,highres,masterpiece:,ultra-detailed,(realistic,photorealistic,photo-realistic:HDR,UHD,studio lighting,,sharp focus,physically-based rendering,extreme detail description,professional,vivid colors,,photographic,bedroom on a bed ,on a couch ,,curvy figure,voluptuous,self-confident,empowering,body positive"

Output

Performance Metrics

28.59s Prediction Time

28.68s Total Time

All Input Parameters

{
  "model": "dev",
  "prompt": "a raw photo realistic ,high quality photo of tokk photo taken cannon ,black  hair natural look,a plus size woman,mid 30's wearing a simi transparent tank top , adjusting her  top, smiling, pulling top,tan lines,small saggy breasts,(best quality,4k,8k,highres,masterpiece:,ultra-detailed,(realistic,photorealistic,photo-realistic:HDR,UHD,studio lighting,,sharp focus,physically-based rendering,extreme detail description,professional,vivid colors,,photographic,bedroom on a bed ,on a couch ,,curvy figure,voluptuous,self-confident,empowering,body positive",
  "lora_scale": 1,
  "num_outputs": 3,
  "aspect_ratio": "1:1",
  "output_format": "png",
  "guidance_scale": 2.01,
  "output_quality": 100,
  "prompt_strength": 0.58,
  "extra_lora_scale": 1,
  "num_inference_steps": 27
}

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: 56542
Prompt: a raw photo realistic ,high quality photo of tokk photo taken cannon ,black  hair natural look,a plus size woman,mid 30's wearing a simi transparent tank top , adjusting her  top, smiling, pulling top,tan lines,small saggy breasts,(best quality,4k,8k,highres,masterpiece:,ultra-detailed,(realistic,photorealistic,photo-realistic:HDR,UHD,studio lighting,,sharp focus,physically-based rendering,extreme detail description,professional,vivid colors,,photographic,bedroom on a bed ,on a couch ,,curvy figure,voluptuous,self-confident,empowering,body positive
[!] txt2img mode
Using dev model
free=28983750369280
Downloading weights
2024-11-25T08:17:01Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpm90dr_28/weights url=https://replicate.delivery/yhqm/vNsuanGfTZ1oMqiK7qKYzXIATGIdUZlmgfQzLmWZDihMqniTA/trained_model.tar
2024-11-25T08:17:02Z | INFO  | [ Complete ] dest=/tmp/tmpm90dr_28/weights size="172 MB" total_elapsed=1.889s url=https://replicate.delivery/yhqm/vNsuanGfTZ1oMqiK7qKYzXIATGIdUZlmgfQzLmWZDihMqniTA/trained_model.tar
Downloaded weights in 1.91s
Loaded LoRAs in 2.52s
  0%|          | 0/27 [00:00<?, ?it/s]
  4%|▎         | 1/27 [00:00<00:23,  1.10it/s]
  7%|▋         | 2/27 [00:01<00:20,  1.23it/s]
 11%|█         | 3/27 [00:02<00:20,  1.17it/s]
 15%|█▍        | 4/27 [00:03<00:20,  1.14it/s]
 19%|█▊        | 5/27 [00:04<00:19,  1.13it/s]
 22%|██▏       | 6/27 [00:05<00:18,  1.12it/s]
 26%|██▌       | 7/27 [00:06<00:17,  1.11it/s]
 30%|██▉       | 8/27 [00:07<00:17,  1.11it/s]
 33%|███▎      | 9/27 [00:08<00:16,  1.11it/s]
 37%|███▋      | 10/27 [00:08<00:15,  1.10it/s]
 41%|████      | 11/27 [00:09<00:14,  1.10it/s]
 44%|████▍     | 12/27 [00:10<00:13,  1.10it/s]
 48%|████▊     | 13/27 [00:11<00:12,  1.10it/s]
 52%|█████▏    | 14/27 [00:12<00:11,  1.10it/s]
 56%|█████▌    | 15/27 [00:13<00:10,  1.10it/s]
 59%|█████▉    | 16/27 [00:14<00:09,  1.10it/s]
 63%|██████▎   | 17/27 [00:15<00:09,  1.10it/s]
 67%|██████▋   | 18/27 [00:16<00:08,  1.10it/s]
 70%|███████   | 19/27 [00:17<00:07,  1.10it/s]
 74%|███████▍  | 20/27 [00:18<00:06,  1.10it/s]
 78%|███████▊  | 21/27 [00:18<00:05,  1.10it/s]
 81%|████████▏ | 22/27 [00:19<00:04,  1.10it/s]
 85%|████████▌ | 23/27 [00:20<00:03,  1.10it/s]
 89%|████████▉ | 24/27 [00:21<00:02,  1.10it/s]
 93%|█████████▎| 25/27 [00:22<00:01,  1.10it/s]
 96%|█████████▋| 26/27 [00:23<00:00,  1.10it/s]
100%|██████████| 27/27 [00:24<00:00,  1.10it/s]
100%|██████████| 27/27 [00:24<00:00,  1.11it/s]

Version Details

Version ID: 6b89ff89ef18145219aab3d1a99970644c5ed4225cfbb48d7d5c6b797e652960
Version Created: October 2, 2024

Run on Replicate →