panosphotos/saduk 🖼️🔢❓📝✓ → 🖼️

▶️ 37 runs 📅 Feb 2025 ⚙️ Cog 0.13.7

About

a photo of SADUK

Example Output

Prompt:

"a photo of SADUK a female dog running in new york streets during snowfall"

Output

Performance Metrics

28.79s Prediction Time

28.90s Total Time

All Input Parameters

{
  "model": "dev",
  "width": 1440,
  "height": 1440,
  "prompt": "a photo of SADUK a female dog running in new york streets during snowfall",
  "go_fast": false,
  "extra_lora": "https://huggingface.co/plimper/saduk",
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "16:9",
  "output_format": "jpg",
  "guidance_scale": 3,
  "output_quality": 100,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 35
}

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

free=27773230481408
Downloading weights
2025-02-11T22:02:15Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmp39g_5glt/weights url=https://replicate.delivery/xezq/9hDHNZFinYKjCpOQPWNmGMFx7fis7Nq2D3jpxfDWmkZPFWOUA/trained_model.tar
2025-02-11T22:02:17Z | INFO  | [ Complete ] dest=/tmp/tmp39g_5glt/weights size="172 MB" total_elapsed=2.507s url=https://replicate.delivery/xezq/9hDHNZFinYKjCpOQPWNmGMFx7fis7Nq2D3jpxfDWmkZPFWOUA/trained_model.tar
Downloaded weights in 2.53s
free=27773057826816
Downloading weights
2025-02-11T22:02:18Z | INFO  | [ Initiating ] chunk_size=150M dest=/src/weights-cache/4cf989ca2b88d06f url=https://huggingface.co/plimper/saduk/resolve/main/lora.safetensors
2025-02-11T22:02:18Z | INFO  | [ Redirect ] redirect_url=https://cdn-lfs-us-1.hf.co/repos/a5/26/a5265055eeb94edf7f726b9dfb1f0b661173c050340a74a0317340de322aa3c9/b03e5b1e02d4a4b7c92d4261d4c4dc52f5bbe7d23864c8d389527ba5075e31f5?response-content-disposition=inline%3B+filename*%3DUTF-8%27%27lora.safetensors%3B+filename%3D%22lora.safetensors%22%3B&Expires=1739314938&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTczOTMxNDkzOH19LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy11cy0xLmhmLmNvL3JlcG9zL2E1LzI2L2E1MjY1MDU1ZWViOTRlZGY3ZjcyNmI5ZGZiMWYwYjY2MTE3M2MwNTAzNDBhNzRhMDMxNzM0MGRlMzIyYWEzYzkvYjAzZTViMWUwMmQ0YTRiN2M5MmQ0MjYxZDRjNGRjNTJmNWJiZTdkMjM4NjRjOGQzODk1MjdiYTUwNzVlMzFmNT9yZXNwb25zZS1jb250ZW50LWRpc3Bvc2l0aW9uPSoifV19&Signature=EM9YXkIaWJHY3ecNWrgx57a88gPPHRr4plyMTYvHd1Q1MLVhBoani%7EuRjPswu2lPBGloVoTo4sKIj52ESxzAX3UIk%7EpX4hte52Nrbo94Zg-rLyImEG1MQUmaY60RR7yMvJeHjjDhjmimJQmN6YyLE-YuRPYWgUQTiraNkUlS7-okkwYpyOgMaQelWooOHyvnbDH8D1EtUlx5skBP7%7EvzSYNL17yxEoHioEB5VdNjNLOclMGkvZdDWp8JHmh5ToqtRIED-bt4sUF1T1dOUUUgt%7EOLgB%7EdTh1QpUT3ThqIWkCxiYFpm1EY2jQXPGGqdmYyfw6okeQHdesram5f1Z8wbg__&Key-Pair-Id=K24J24Z295AEI9 url=https://huggingface.co/plimper/saduk/resolve/main/lora.safetensors
2025-02-11T22:02:33Z | INFO  | [ Complete ] dest=/src/weights-cache/4cf989ca2b88d06f size="172 MB" total_elapsed=14.730s url=https://huggingface.co/plimper/saduk/resolve/main/lora.safetensors
Downloaded weights in 14.78s
Loaded LoRAs in 18.74s
Using seed: 41781
Prompt: a photo of SADUK a female dog running in new york streets during snowfall
[!] txt2img mode
  0%|          | 0/35 [00:00<?, ?it/s]
  3%|▎         | 1/35 [00:00<00:09,  3.52it/s]
  6%|▌         | 2/35 [00:00<00:08,  3.86it/s]
  9%|▊         | 3/35 [00:00<00:08,  3.71it/s]
 11%|█▏        | 4/35 [00:01<00:08,  3.64it/s]
 14%|█▍        | 5/35 [00:01<00:08,  3.61it/s]
 17%|█▋        | 6/35 [00:01<00:08,  3.59it/s]
 20%|██        | 7/35 [00:01<00:07,  3.57it/s]
 23%|██▎       | 8/35 [00:02<00:07,  3.56it/s]
 26%|██▌       | 9/35 [00:02<00:07,  3.56it/s]
 29%|██▊       | 10/35 [00:02<00:07,  3.55it/s]
 31%|███▏      | 11/35 [00:03<00:06,  3.55it/s]
 34%|███▍      | 12/35 [00:03<00:06,  3.55it/s]
 37%|███▋      | 13/35 [00:03<00:06,  3.55it/s]
 40%|████      | 14/35 [00:03<00:05,  3.54it/s]
 43%|████▎     | 15/35 [00:04<00:05,  3.54it/s]
 46%|████▌     | 16/35 [00:04<00:05,  3.54it/s]
 49%|████▊     | 17/35 [00:04<00:05,  3.54it/s]
 51%|█████▏    | 18/35 [00:05<00:04,  3.54it/s]
 54%|█████▍    | 19/35 [00:05<00:04,  3.54it/s]
 57%|█████▋    | 20/35 [00:05<00:04,  3.54it/s]
 60%|██████    | 21/35 [00:05<00:03,  3.54it/s]
 63%|██████▎   | 22/35 [00:06<00:03,  3.54it/s]
 66%|██████▌   | 23/35 [00:06<00:03,  3.54it/s]
 69%|██████▊   | 24/35 [00:06<00:03,  3.54it/s]
 71%|███████▏  | 25/35 [00:07<00:02,  3.54it/s]
 74%|███████▍  | 26/35 [00:07<00:02,  3.54it/s]
 77%|███████▋  | 27/35 [00:07<00:02,  3.54it/s]
 80%|████████  | 28/35 [00:07<00:01,  3.54it/s]
 83%|████████▎ | 29/35 [00:08<00:01,  3.54it/s]
 86%|████████▌ | 30/35 [00:08<00:01,  3.54it/s]
 89%|████████▊ | 31/35 [00:08<00:01,  3.54it/s]
 91%|█████████▏| 32/35 [00:08<00:00,  3.54it/s]
 94%|█████████▍| 33/35 [00:09<00:00,  3.54it/s]
 97%|█████████▋| 34/35 [00:09<00:00,  3.54it/s]
100%|██████████| 35/35 [00:09<00:00,  3.54it/s]
100%|██████████| 35/35 [00:09<00:00,  3.56it/s]
Total safe images: 1 out of 1

Version Details

Version ID: 1e148f923dba26e0ecd48afaa3d756df0d8dce75db137baf25bbdffd7275406a
Version Created: February 11, 2025

Run on Replicate →