biguloff/zaur-ttkv 🖼️🔢❓📝✓ → 🖼️

▶️ 253 runs 📅 Nov 2024 ⚙️ Cog 0.11.1

About

Example Output

Prompt:

"A hyper-realistic portrait of tall skinny fit and masculine man , ZTKV, handsome man ZTKV A candid photo of ZTKV , dressed in an immaculate tailored suit, standing on the balcony of a luxury penthouse in Monaco. The Mediterranean Sea glistens in the background. Film grain effect with warm Kodak tones, capturing the elegance of a billionaire lifestyle."

Output

Performance Metrics

40.10s Prediction Time

40.11s Total Time

All Input Parameters

{
  "model": "dev",
  "prompt": "A hyper-realistic portrait of tall skinny fit and masculine man , ZTKV, handsome man ZTKV A candid photo of ZTKV , dressed in an immaculate tailored suit, standing on the balcony of a luxury penthouse in Monaco. The Mediterranean Sea glistens in the background. Film grain effect with warm Kodak tones, capturing the elegance of a billionaire lifestyle.",
  "lora_scale": -0.91,
  "num_outputs": 4,
  "aspect_ratio": "9:16",
  "output_format": "png",
  "guidance_scale": 3.84,
  "output_quality": 90,
  "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

Using seed: 19062
Prompt: A hyper-realistic portrait of tall skinny fit and masculine man , ZTKV, handsome man ZTKV A candid photo of ZTKV , dressed in an immaculate tailored suit, standing on the balcony of a luxury penthouse in Monaco. The Mediterranean Sea glistens in the background. Film grain effect with warm Kodak tones, capturing the elegance of a billionaire lifestyle.
[!] txt2img mode
Using dev model
free=6596379840512
Downloading weights
2024-11-06T12:27:21Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmp25c9lxod/weights url=https://replicate.delivery/yhqm/KfpBXqLFpDVxZaB18mYMNljtnseXMa7LNedXYf9rgTf1IrwdC/trained_model.tar
2024-11-06T12:27:22Z | INFO  | [ Complete ] dest=/tmp/tmp25c9lxod/weights size="344 MB" total_elapsed=1.435s url=https://replicate.delivery/yhqm/KfpBXqLFpDVxZaB18mYMNljtnseXMa7LNedXYf9rgTf1IrwdC/trained_model.tar
Downloaded weights in 1.47s
Loaded LoRAs in 2.23s
  0%|          | 0/28 [00:00<?, ?it/s]
  4%|▎         | 1/28 [00:01<00:34,  1.28s/it]
  7%|▋         | 2/28 [00:02<00:30,  1.16s/it]
 11%|█         | 3/28 [00:03<00:30,  1.21s/it]
 14%|█▍        | 4/28 [00:04<00:29,  1.24s/it]
 18%|█▊        | 5/28 [00:06<00:28,  1.25s/it]
 21%|██▏       | 6/28 [00:07<00:27,  1.26s/it]
 25%|██▌       | 7/28 [00:08<00:26,  1.26s/it]
 29%|██▊       | 8/28 [00:09<00:25,  1.27s/it]
 32%|███▏      | 9/28 [00:11<00:24,  1.27s/it]
 36%|███▌      | 10/28 [00:12<00:22,  1.27s/it]
 39%|███▉      | 11/28 [00:13<00:21,  1.27s/it]
 43%|████▎     | 12/28 [00:15<00:20,  1.27s/it]
 46%|████▋     | 13/28 [00:16<00:19,  1.27s/it]
 50%|█████     | 14/28 [00:17<00:17,  1.27s/it]
 54%|█████▎    | 15/28 [00:18<00:16,  1.27s/it]
 57%|█████▋    | 16/28 [00:20<00:15,  1.27s/it]
 61%|██████    | 17/28 [00:21<00:13,  1.27s/it]
 64%|██████▍   | 18/28 [00:22<00:12,  1.27s/it]
 68%|██████▊   | 19/28 [00:24<00:11,  1.27s/it]
 71%|███████▏  | 20/28 [00:25<00:10,  1.27s/it]
 75%|███████▌  | 21/28 [00:26<00:08,  1.27s/it]
 79%|███████▊  | 22/28 [00:27<00:07,  1.27s/it]
 82%|████████▏ | 23/28 [00:29<00:06,  1.27s/it]
 86%|████████▌ | 24/28 [00:30<00:05,  1.27s/it]
 89%|████████▉ | 25/28 [00:31<00:03,  1.27s/it]
 93%|█████████▎| 26/28 [00:32<00:02,  1.27s/it]
 96%|█████████▋| 27/28 [00:34<00:01,  1.27s/it]
100%|██████████| 28/28 [00:35<00:00,  1.27s/it]
100%|██████████| 28/28 [00:35<00:00,  1.27s/it]

Version Details

Version ID: a97fe436ea033af7600b18bb28398a0b83bca58211fa97e649d01a574b9744f9
Version Created: November 5, 2024

Run on Replicate →