aisha-ai-official/nova-anime-ilxl-v5.5 ❓🔢📝✓ → 🖼️

▶️ 2.2K runs 📅 Mar 2025 ⚙️ Cog 0.13.7 ⚖️ License

anime text-to-image

About

Example Output

Prompt:

"street, 1girl, dark-purple short hair, purple eyes, medium breasts, cleavage, casual clothes, smile, V"

Output

Performance Metrics

9.80s Prediction Time

82.42s Total Time

All Input Parameters

{
  "vae": "default",
  "seed": -1,
  "model": "Nova-Anime-ILXL-v5.5",
  "steps": 30,
  "width": 1024,
  "height": 1024,
  "prompt": "street, 1girl, dark-purple short hair, purple eyes, medium breasts, cleavage, casual clothes, smile, V",
  "cfg_scale": 5,
  "clip_skip": 2,
  "pag_scale": 0,
  "scheduler": "Euler a",
  "batch_size": 1,
  "face_yolov9c": true,
  "hand_yolov9c": false,
  "negative_prompt": "nsfw, naked",
  "guidance_rescale": 1,
  "prepend_preprompt": true,
  "person_yolov8m_seg": false
}

Input Parameters

vae Default: default: The VAE to use
seed Type: integerDefault: -1: The seed used when generating, set to -1 for random seed
model Default: Nova-Anime-ILXL-v5.5: The model to use
steps Type: integerDefault: 30Range: 1 - 100: The steps when generating
width Type: integerDefault: 1024Range: 1 - 4096: The width of the image
height Type: integerDefault: 1024Range: 1 - 4096: The height of the image
prompt Type: stringDefault: street, 1girl, dark-purple short hair, purple eyes, medium breasts, cleavage, casual clothes, smile, V: The prompt, uses Compel weighting syntax
cfg_scale Type: numberDefault: 5Range: 1 - 50: CFG scale defines how much attention the model pays to the prompt when generating, set to 1 to disable
clip_skip Type: integerDefault: 2Range: 1 - ∞: How many CLIP layers to skip, 1 is actually no skip, this is the behavior in A1111 so it's aligned to it
pag_scale Type: numberDefault: 0Range: 0 - 50: PAG scale is similar to CFG but it literally makes the result better, it's compatible with CFG too, set to 0 to disable
scheduler Default: Euler a: The scheduler to use
batch_size Type: integerDefault: 1Range: 1 - 4: Number of images to generate (1-4), note if you set this to 4, some high resolution gens might fail because of not enough VRAM
face_yolov9c Type: booleanDefault: true: Use ADetailer face_yolov9c.pt
hand_yolov9c Type: booleanDefault: false: Use ADetailer hand_yolov9c.pt
negative_prompt Type: stringDefault: nsfw, naked: The negative prompt (For things you don't want), uses Compel weighting syntax
guidance_rescale Type: numberDefault: 1Range: 0 - 5: The amount to rescale CFG generated noise to avoid generating overexposed images, set to 0 or 1 to disable
prepend_preprompt Type: booleanDefault: true: Prepend preprompt (Prompt: "masterpiece, best quality, amazing quality, very aesthetic, high resolution, ultra-detailed, absurdres, newest, scenery, " Negative prompt: "modern, recent, old, oldest, cartoon, graphic, text, painting, crayon, graphite, abstract, glitch, deformed, mutated, ugly, disfigured, long body, lowres, bad anatomy, bad hands, missing fingers, extra digits, fewer digits, cropped, very displeasing, (worst quality, bad quality:1.2), bad anatomy, sketch, jpeg artifacts, signature, watermark, username, signature, simple background, conjoined,bad ai-generated, ")
person_yolov8m_seg Type: booleanDefault: false: Use ADetailer person_yolov8m-seg.pt

Output Schema

Output

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

Example Execution Logs

Using text to image mode.
Using seed: 456556676
  0%|          | 0/30 [00:00<?, ?it/s]
  3%|▎         | 1/30 [00:00<00:09,  3.01it/s]
 10%|█         | 3/30 [00:00<00:04,  6.66it/s]
 13%|█▎        | 4/30 [00:00<00:03,  7.20it/s]
 17%|█▋        | 5/30 [00:00<00:03,  7.57it/s]
 20%|██        | 6/30 [00:00<00:03,  7.83it/s]
 23%|██▎       | 7/30 [00:00<00:02,  8.02it/s]
 27%|██▋       | 8/30 [00:01<00:02,  8.15it/s]
 30%|███       | 9/30 [00:01<00:02,  8.24it/s]
 33%|███▎      | 10/30 [00:01<00:02,  8.31it/s]
 37%|███▋      | 11/30 [00:01<00:02,  8.35it/s]
 40%|████      | 12/30 [00:01<00:02,  8.38it/s]
 43%|████▎     | 13/30 [00:01<00:02,  8.39it/s]
 47%|████▋     | 14/30 [00:01<00:01,  8.40it/s]
 50%|█████     | 15/30 [00:01<00:01,  8.41it/s]
 53%|█████▎    | 16/30 [00:02<00:01,  8.42it/s]
 57%|█████▋    | 17/30 [00:02<00:01,  8.41it/s]
 60%|██████    | 18/30 [00:02<00:01,  8.42it/s]
 63%|██████▎   | 19/30 [00:02<00:01,  8.42it/s]
 67%|██████▋   | 20/30 [00:02<00:01,  8.42it/s]
 70%|███████   | 21/30 [00:02<00:01,  8.43it/s]
 73%|███████▎  | 22/30 [00:02<00:00,  8.43it/s]
 77%|███████▋  | 23/30 [00:02<00:00,  8.43it/s]
 80%|████████  | 24/30 [00:02<00:00,  8.42it/s]
 83%|████████▎ | 25/30 [00:03<00:00,  8.41it/s]
 87%|████████▋ | 26/30 [00:03<00:00,  8.41it/s]
 90%|█████████ | 27/30 [00:03<00:00,  8.41it/s]
 93%|█████████▎| 28/30 [00:03<00:00,  8.41it/s]
 97%|█████████▋| 29/30 [00:03<00:00,  8.41it/s]
100%|██████████| 30/30 [00:03<00:00,  8.41it/s]
100%|██████████| 30/30 [00:03<00:00,  8.09it/s]
/root/.pyenv/versions/3.12.8/lib/python3.12/site-packages/huggingface_hub/file_download.py:834: UserWarning: `local_dir_use_symlinks` parameter is deprecated and will be ignored. The process to download files to a local folder has been updated and do not rely on symlinks anymore. You only need to pass a destination folder as`local_dir`.
For more details, check out https://huggingface.co/docs/huggingface_hub/main/en/guides/download#download-files-to-local-folder.
warnings.warn(
Inpainting...
0: 640x640 1 face, 5.6ms
Speed: 7.5ms preprocess, 5.6ms inference, 28.9ms postprocess per image at shape (1, 3, 640, 640)
padded dim: (np.int64(269), np.int64(148), np.int64(742), np.int64(605))
Loading StableDiffusionXLInpaintPipeline
  0%|          | 0/4 [00:00<?, ?it/s]
 25%|██▌       | 1/4 [00:00<00:00,  8.78it/s]
 50%|█████     | 2/4 [00:00<00:00,  8.59it/s]
 75%|███████▌  | 3/4 [00:00<00:00,  8.53it/s]
100%|██████████| 4/4 [00:00<00:00,  9.20it/s]
generated inpaint dim: (1024, 1024)

Version Details

Version ID: ac582da6619c6deb7ff561eefb5824324c9ff0f485ccb7867964bce7040b0568
Version Created: March 7, 2025

Run on Replicate →