charlesmccarthy/pony-sdxl ❓🔢📝✓ → 🖼️

▶️ 116.5K runs 📅 May 2024 ⚙️ Cog 0.9.4

About

The best Pony-SDXL models! Current one is based on Pony Realism.

Example Output

Prompt:

"1girl, cat girl, cat ears, cat tail, yellow eyes, white hair, bob cut, from side, scenery, sunset"

Output

Performance Metrics

9.70s Prediction Time

365.75s Total Time

All Input Parameters

{
  "vae": "sdxl-vae-fp16-fix",
  "seed": -1,
  "model": "ponyRealism_v20VAE.safetensors",
  "steps": 35,
  "width": 1184,
  "height": 864,
  "prompt": "1girl, cat girl, cat ears, cat tail, yellow eyes, white hair, bob cut, from side, scenery, sunset",
  "cfg_scale": 7,
  "scheduler": "DPM++ 2M SDE Karras",
  "batch_size": 1,
  "negative_prompt": "unaestheticXL_Sky3.1, animal, cat, dog, big breasts",
  "guidance_rescale": 0.7,
  "prepend_preprompt": true
}

Input Parameters

vae Default: sdxl-vae-fp16-fix: The VAE to use
seed Type: integerDefault: -1: The seed used when generating, set to -1 for random seed
model Default: mklannsfwrealxl2.safetensors: The model to use
steps Type: integerDefault: 35Range: 1 - 100: The steps when generating
width Type: integerDefault: 1184Range: 1 - 2048: The width of the image
height Type: integerDefault: 864Range: 1 - 2048: The height of the image
prompt Type: stringDefault: 1girl, cat girl, cat ears, cat tail, yellow eyes, white hair, bob cut, from side, scenery, sunset: The prompt
cfg_scale Type: numberDefault: 7Range: 1 - 30: CFG Scale defines how much attention the model pays to the prompt when generating
scheduler Default: DPM++ 2M SDE Karras: The scheduler to use
batch_size Type: integerDefault: 1Range: 1 - 4: Number of images to generate (1-4)
negative_prompt Type: stringDefault: unaestheticXL_Sky3.1, animal, cat, dog, big breasts: The negative prompt (For things you don't want)
guidance_rescale Type: numberDefault: 0.7Range: 0 - 1: The amount to rescale CFG generated noise to avoid generating overexposed images
prepend_preprompt Type: booleanDefault: true: Prepend preprompt (Prompt: "score_9, score_8_up, score_7_up, " Negative prompt: "score_4, score_3, score_2, score_1, worst quality, bad hands, bad feet, ").

Output Schema

Output

Type: array • Items Type: string • Items Format: uri

Example Execution Logs

0%|          | 0/35 [00:00<?, ?it/s]/root/.pyenv/versions/3.10.14/lib/python3.10/site-packages/torch/nn/modules/conv.py:456: UserWarning: Plan failed with a cudnnException: CUDNN_BACKEND_EXECUTION_PLAN_DESCRIPTOR: cudnnFinalize Descriptor Failed cudnn_status: CUDNN_STATUS_NOT_SUPPORTED (Triggered internally at ../aten/src/ATen/native/cudnn/Conv_v8.cpp:919.)
return F.conv2d(input, weight, bias, self.stride,
  3%|▎         | 1/35 [00:00<00:12,  2.78it/s]
  6%|▌         | 2/35 [00:00<00:06,  4.74it/s]
  9%|▊         | 3/35 [00:00<00:06,  4.98it/s]
 11%|█▏        | 4/35 [00:00<00:06,  5.10it/s]
 14%|█▍        | 5/35 [00:01<00:05,  5.16it/s]
 17%|█▋        | 6/35 [00:01<00:05,  5.20it/s]
 20%|██        | 7/35 [00:01<00:05,  5.20it/s]
 23%|██▎       | 8/35 [00:01<00:05,  5.22it/s]
 26%|██▌       | 9/35 [00:01<00:04,  5.23it/s]
 29%|██▊       | 10/35 [00:01<00:04,  5.25it/s]
 31%|███▏      | 11/35 [00:02<00:04,  5.25it/s]
 34%|███▍      | 12/35 [00:02<00:04,  5.24it/s]
 37%|███▋      | 13/35 [00:02<00:04,  5.24it/s]
 40%|████      | 14/35 [00:02<00:04,  5.24it/s]
 43%|████▎     | 15/35 [00:02<00:03,  5.25it/s]
 46%|████▌     | 16/35 [00:03<00:03,  5.27it/s]
 49%|████▊     | 17/35 [00:03<00:03,  5.27it/s]
 51%|█████▏    | 18/35 [00:03<00:03,  5.27it/s]
 54%|█████▍    | 19/35 [00:03<00:03,  5.28it/s]
 57%|█████▋    | 20/35 [00:03<00:02,  5.28it/s]
 60%|██████    | 21/35 [00:04<00:02,  5.29it/s]
 63%|██████▎   | 22/35 [00:04<00:02,  5.28it/s]
 66%|██████▌   | 23/35 [00:04<00:02,  5.28it/s]
 69%|██████▊   | 24/35 [00:04<00:02,  5.28it/s]
 71%|███████▏  | 25/35 [00:04<00:01,  5.22it/s]
 74%|███████▍  | 26/35 [00:05<00:01,  5.24it/s]
 77%|███████▋  | 27/35 [00:05<00:01,  5.26it/s]
 80%|████████  | 28/35 [00:05<00:01,  5.26it/s]
 83%|████████▎ | 29/35 [00:05<00:01,  5.26it/s]
 86%|████████▌ | 30/35 [00:05<00:00,  5.27it/s]
 89%|████████▊ | 31/35 [00:05<00:00,  5.27it/s]
 91%|█████████▏| 32/35 [00:06<00:00,  5.28it/s]
 94%|█████████▍| 33/35 [00:06<00:00,  5.28it/s]
 97%|█████████▋| 34/35 [00:06<00:00,  5.27it/s]
100%|██████████| 35/35 [00:06<00:00,  5.27it/s]
100%|██████████| 35/35 [00:06<00:00,  5.20it/s]

Version Details

Version ID: b070dedae81324788c3c933a5d9e1270093dc74636214b9815dae044b4b3a58a
Version Created: June 10, 2024

Run on Replicate →