kirirururu/nova-anime-xl-17 🔢📝❓✓ → 🖼️

▶️ 3.2K runs 📅 Mar 2026 ⚙️ Cog 0.16.12 🔗 GitHub ⚖️ License
anime danbooru text-to-image

About

Nova Anime XL (Illustrious) v17.0

Example Output

Prompt:

"1girl, solo, cute, pink hair, long hair, choppy bangs, long sidelocks, nebulae cosmic purple eyes, rimlit eyes, facing to the side, looking at viewer, downturned eyes, light smile, red annular solar eclipse halo, red choker, detailed purple blazer, collared white shirt, big red neckerchief, glowing stars in hand, dispersion \(optics\), from side, from below, dutch angle, portrait, upper body, head tilt, colorful, rim light, backlit, (colorful light particles:1.2), cosmic sky, aurora, chaos, perfect night, fantasy background, dreamlike atmosphere, BREAK, detailed background, blurry foreground, bokeh"

Output

Example output

Performance Metrics

13.14s Prediction Time
13.15s Total Time
All Input Parameters
{
  "seed": 4249806,
  "width": 768,
  "height": 1344,
  "prompt": "1girl, solo, cute, pink hair, long hair, choppy bangs, long sidelocks, nebulae cosmic purple eyes, rimlit eyes, facing to the side, looking at viewer, downturned eyes, light smile, red annular solar eclipse halo, red choker, detailed purple blazer, collared white shirt, big red neckerchief, glowing stars in hand, dispersion \\(optics\\), from side, from below, dutch angle, portrait, upper body, head tilt, colorful, rim light, backlit, (colorful light particles:1.2), cosmic sky, aurora, chaos, perfect night, fantasy background, dreamlike atmosphere, BREAK, detailed background, blurry foreground, bokeh",
  "scheduler": "Euler a",
  "num_outputs": 1,
  "hires_enable": true,
  "hires_factor": 1.5,
  "guidance_scale": 4.5,
  "hires_strength": 0.4,
  "negative_prompt": "photorealistic, realistic, 3d, extra digits, (particles, adversarial_noise:1.2), multiple views, multiple angle, split view, grid view, two shot, outside border, picture frame, framed, border, letterboxed, pillarboxed, 2koma",
  "num_inference_steps": 20,
  "add_recommended_tags": true,
  "hires_guidance_scale": 4,
  "hires_num_inference_steps": 40
}
Input Parameters
seed Type: integerDefault: -1
Random seed. Set to -1 to pick random seed.
width Type: integerDefault: 1024
Width of output image(s). It is recommended to pick resolutions where total pixels remain under 1-megapixel threshold.
height Type: integerDefault: 1024
Height of output image(s). It is recommended to pick resolutions where total pixels remain under 1-megapixel threshold.
prompt Type: stringDefault: 1girl, solo, cute
Positive prompt. Put here a comma-separated list of Danbooru tags to describe, what should be present on image(s). You can add weights to tags and use BREAK token. See https://civitai.com/articles/19107/crodys-illustrious-noobai-image-generation-tips#2.-prompting-guide-and-resources
scheduler Default: Euler a
Scheduler to use ('Euler a' is recommended)
num_outputs Type: integerDefault: 1Range: 1 - 10
Number of images to generate
hires_enable Type: booleanDefault: false
Upscale the image(s) (apply Hires.fix).
hires_factor Type: numberDefault: 1.5Range: 1 - 4
Upscaling factor
guidance_scale Type: numberDefault: 4.5Range: 1 - 20
Scale for classifier-free guidance (CFG). It controls how much the image generation follows the prompt. Higher values make the output more closely aligned with the prompt, but may reduce image quality. Lower values allow more creative freedom, but may stray from the prompt.
hires_strength Type: numberDefault: 0.4Range: 0 - 1
Denoising strength for the upscaling stage. It controls how much the upscaler can change the image(s).
adjust_contrast Type: array
Contrast adjustments to apply to the image(s) [expert setting] Rules are the same as for brightness adjustments.
negative_prompt Type: stringDefault:
Negative prompt. Put here a comma-separated list of Danbooru tags to describe, what should NOT be present on image(s). Syntax is the same as for positive prompt.
adjust_brightness Type: array
Brightness adjustments to apply to the image(s) [expert setting] The adjustments will be applied after low-resolution generation. The value must be a list of THREE float numbers - adjustment factors for shadows, midtones and highlights. Numbers must be between 0 and 10, 1.0 means no adjustment.
num_inference_steps Type: integerDefault: 20Range: 1 - 100
Number of denoising steps
add_recommended_tags Type: booleanDefault: true
If true, the recommended tags will be added to both prompts. In that case you only need to describe a scene.
hires_guidance_scale Type: numberDefault: 4Range: 1 - 20
Scale for classifier-free guidance (CFG) for the upscaling stage
disable_safety_checker Type: booleanDefault: false
Disable safety checker for generated images. This feature is only available through the API.
hires_num_inference_steps Type: integerDefault: 40Range: 1 - 100
Number of denoising steps for the upscaling stage
Output Schema

Output

Type: arrayItems Type: stringItems Format: uri

Example Execution Logs
Prompt extended to: 'masterpiece, best quality, amazing quality, 4k, very aesthetic, high resolution, ultra-detailed, absurdres, newest, scenery, 1girl, solo, cute, pink hair, long hair, choppy bangs, long sidelocks, nebulae cosmic purple eyes, rimlit eyes, facing to the side, looking at viewer, downturned eyes, light smile, red annular solar eclipse halo, red choker, detailed purple blazer, collared white shirt, big red neckerchief, glowing stars in hand, dispersion \(optics\), from side, from below, dutch angle, portrait, upper body, head tilt, colorful, rim light, backlit, (colorful light particles:1.2), cosmic sky, aurora, chaos, perfect night, fantasy background, dreamlike atmosphere, BREAK, detailed background, blurry foreground, bokeh, depth of field, volumetric lighting'
Negative prompt extended to: 'photorealistic, realistic, 3d, extra digits, (particles, adversarial_noise:1.2), multiple views, multiple angle, split view, grid view, two shot, outside border, picture frame, framed, border, letterboxed, pillarboxed, 2koma, 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 fingers, extra digits, fewer digits, cropped, very displeasing, (worst quality, bad quality:1.2), sketch, jpeg artifacts, signature, watermark, username, (censored, bar_censor, mosaic_censor:1.2), simple background, conjoined, bad ai-generated'
Using seed: 4249806
> Generating images...
  0%|          | 0/20 [00:00<?, ?it/s]
  5%|▌         | 1/20 [00:00<00:16,  1.15it/s]
 10%|█         | 2/20 [00:00<00:07,  2.34it/s]
 15%|█▌        | 3/20 [00:01<00:04,  3.48it/s]
 20%|██        | 4/20 [00:01<00:03,  4.51it/s]
 25%|██▌       | 5/20 [00:01<00:02,  5.40it/s]
 30%|███       | 6/20 [00:01<00:02,  6.11it/s]
 35%|███▌      | 7/20 [00:01<00:01,  6.68it/s]
 40%|████      | 8/20 [00:01<00:01,  7.10it/s]
 45%|████▌     | 9/20 [00:01<00:01,  7.42it/s]
 50%|█████     | 10/20 [00:01<00:01,  7.65it/s]
 55%|█████▌    | 11/20 [00:02<00:01,  7.82it/s]
 60%|██████    | 12/20 [00:02<00:01,  7.94it/s]
 65%|██████▌   | 13/20 [00:02<00:00,  8.04it/s]
 70%|███████   | 14/20 [00:02<00:00,  8.09it/s]
 75%|███████▌  | 15/20 [00:02<00:00,  8.13it/s]
 80%|████████  | 16/20 [00:02<00:00,  8.17it/s]
 85%|████████▌ | 17/20 [00:02<00:00,  8.19it/s]
 90%|█████████ | 18/20 [00:02<00:00,  8.20it/s]
 95%|█████████▌| 19/20 [00:03<00:00,  8.21it/s]
100%|██████████| 20/20 [00:03<00:00,  8.22it/s]
100%|██████████| 20/20 [00:03<00:00,  6.31it/s]
> Adjusting brightness and contrast...
> Running safety checker...
> Upscaling images...
  0%|          | 0/16 [00:00<?, ?it/s]
  6%|▋         | 1/16 [00:00<00:11,  1.34it/s]
 12%|█▎        | 2/16 [00:01<00:06,  2.13it/s]
 19%|█▉        | 3/16 [00:01<00:04,  2.63it/s]
 25%|██▌       | 4/16 [00:01<00:04,  2.95it/s]
 31%|███▏      | 5/16 [00:01<00:03,  3.16it/s]
 38%|███▊      | 6/16 [00:02<00:03,  3.31it/s]
 44%|████▍     | 7/16 [00:02<00:02,  3.40it/s]
 50%|█████     | 8/16 [00:02<00:02,  3.47it/s]
 56%|█████▋    | 9/16 [00:02<00:01,  3.51it/s]
 62%|██████▎   | 10/16 [00:03<00:01,  3.54it/s]
 69%|██████▉   | 11/16 [00:03<00:01,  3.56it/s]
 75%|███████▌  | 12/16 [00:03<00:01,  3.57it/s]
 81%|████████▏ | 13/16 [00:04<00:00,  3.58it/s]
 88%|████████▊ | 14/16 [00:04<00:00,  3.59it/s]
 94%|█████████▍| 15/16 [00:04<00:00,  3.60it/s]
100%|██████████| 16/16 [00:04<00:00,  3.60it/s]
100%|██████████| 16/16 [00:04<00:00,  3.27it/s]
> Saving images...
Version Details
Version ID
8f702486aa2852a08564ede8c83a7f58e52c83f6698e7be0e061d79c113dc88b
Version Created
March 7, 2026
Run on Replicate →