aisha-ai-official/illust3relustion ❓🔢📝✓ → 🖼️

▶️ 321.4K runs 📅 Mar 2025 ⚙️ Cog 0.13.7 ⚖️ License
anime text-to-image

About

Example Output

Prompt:

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

Output

Example output

Performance Metrics

22.97s Prediction Time
22.98s Total Time
All Input Parameters 
{
  "vae": "default",
  "seed": -1,
  "model": "Illust3Relustion",
  "steps": 20,
  "width": 1024,
  "height": 1024,
  "prompt": "street, 1girl, people\ndark-purple short hair, purple eyes, medium breasts, cleavage, casual clothes, smile",
  "refiner": true,
  "upscale": "x2",
  "cfg_scale": 5.5,
  "clip_skip": 2,
  "pag_scale": 0,
  "scheduler": "Euler a beta",
  "adetailer_face": false,
  "adetailer_hand": false,
  "refiner_prompt": "",
  "negative_prompt": "nsfw, naked",
  "adetailer_person": false,
  "guidance_rescale": 1,
  "refiner_strength": 0.6,
  "prepend_preprompt": true,
  "prompt_conjunction": true,
  "adetailer_face_prompt": "",
  "adetailer_hand_prompt": "",
  "adetailer_person_prompt": "",
  "negative_prompt_conjunction": false,
  "adetailer_face_negative_prompt": "",
  "adetailer_hand_negative_prompt": "",
  "adetailer_person_negative_prompt": ""
}
Input Parameters
vae Default: default
The VAE to use
seed Type: integerDefault: -1
The seed for generation; set to -1 for random seed
model Default: Illust3Relustion
The model to use
steps Type: integerDefault: 16Range: 1 - 100
Number of 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
The prompt, uses Compel weighting syntax
refiner Type: booleanDefault: false
Enable image refiner using model
upscale Default: Original
Upscale factor
cfg_scale Type: numberDefault: 5.5Range: 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: 0 - ∞
How many CLIP layers to skip; 1 means no skip
pag_scale Type: numberDefault: 0Range: 0 - 50
PAG scale is similar to CFG but improves the result; set to 0 to disable
scheduler Default: LCMScheduler Karras
The scheduler to use
adetailer_face Type: booleanDefault: false
Use ADetailer face_yolov9c.pt
adetailer_hand Type: booleanDefault: false
Use ADetailer hand_yolov9c.pt
refiner_prompt Type: stringDefault:
The prompt of refiner (leave empty for default correct hands and details)
negative_prompt Type: stringDefault: nsfw, naked
The negative prompt (for things you don't want), uses Compel weighting syntax
adetailer_person Type: booleanDefault: false
Use ADetailer person_yolov8m-seg.pt
guidance_rescale Type: numberDefault: 1Range: 0 - 5
Amount to rescale CFG generated noise to avoid overexposed images, set to 0 or 1 to disable
refiner_strength Type: numberDefault: 0.4Range: 0 - 1
Refiner strength (0.0 to 1.0)
prepend_preprompt Type: booleanDefault: true
Prepend preprompt (Prompt: "masterpiece, best quality, amazing quality, realistic,soft lighting," | Negative prompt: "lowres, worst quality, low quality, bad anatomy, worst aesthetic, jpeg artifacts, scan artifacts, compression artifacts,")
prompt_conjunction Type: booleanDefault: false
Force Compel conjunction syntax on prompt, separating linebreaks into different items on the Compel conjunction function
adetailer_face_prompt Type: stringDefault:
ADetailer face prompt (if blank, will use the image prompt)
adetailer_hand_prompt Type: stringDefault:
ADetailer hand prompt (if blank, will use: detailed hands, realistic anatomy, well-defined fingers, natural pose, soft shadows, high resolution, intricate details)
adetailer_person_prompt Type: stringDefault:
ADetailer person prompt (if blank, will use: best quality, detailed, realistic shadows)
negative_prompt_conjunction Type: booleanDefault: false
Force Compel conjunction syntax on prompt, separating linebreaks into different items on the Compel conjunction function
adetailer_face_negative_prompt Type: stringDefault:
ADetailer face negative prompt (if blank, will use: blurry, deformed face, extra features, unrealistic skin texture, oversmoothed, low resolution, artifacts)
adetailer_hand_negative_prompt Type: stringDefault:
ADetailer hand negative prompt (if blank, will use: extra fingers, fused or missing fingers, blurry, distorted, low detail, poorly drawn, unnatural proportions)
adetailer_person_negative_prompt Type: stringDefault:
ADetailer person negative prompt (if blank, will use: deformed, unrealistic proportions, extra limbs, blurred, low quality, distorted pose, exaggerated features)
Output Schema

Output

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

Example Execution Logs 
Balancing prompt's shape
Using text to image mode
Using seed: 194060730
  0%|          | 0/20 [00:00<?, ?it/s]
  5%|▌         | 1/20 [00:00<00:05,  3.63it/s]
 15%|█▌        | 3/20 [00:00<00:02,  7.28it/s]
 20%|██        | 4/20 [00:00<00:02,  7.64it/s]
 25%|██▌       | 5/20 [00:00<00:01,  7.87it/s]
 30%|███       | 6/20 [00:00<00:01,  8.02it/s]
 35%|███▌      | 7/20 [00:00<00:01,  8.12it/s]
 40%|████      | 8/20 [00:01<00:01,  8.18it/s]
 45%|████▌     | 9/20 [00:01<00:01,  8.22it/s]
 50%|█████     | 10/20 [00:01<00:01,  8.27it/s]
 55%|█████▌    | 11/20 [00:01<00:01,  8.31it/s]
 60%|██████    | 12/20 [00:01<00:00,  8.32it/s]
 65%|██████▌   | 13/20 [00:01<00:00,  8.34it/s]
 70%|███████   | 14/20 [00:01<00:00,  8.34it/s]
 75%|███████▌  | 15/20 [00:01<00:00,  8.33it/s]
 80%|████████  | 16/20 [00:02<00:00,  8.35it/s]
 85%|████████▌ | 17/20 [00:02<00:00,  8.34it/s]
 90%|█████████ | 18/20 [00:02<00:00,  8.33it/s]
 95%|█████████▌| 19/20 [00:02<00:00,  8.32it/s]
100%|██████████| 20/20 [00:02<00:00,  8.32it/s]
100%|██████████| 20/20 [00:02<00:00,  8.03it/s]
Upscaling image to x2
Refining image
  0%|          | 0/12 [00:00<?, ?it/s]
  8%|▊         | 1/12 [00:00<00:02,  4.09it/s]
 17%|█▋        | 2/12 [00:00<00:04,  2.44it/s]
 25%|██▌       | 3/12 [00:01<00:04,  2.16it/s]
 33%|███▎      | 4/12 [00:01<00:03,  2.05it/s]
 42%|████▏     | 5/12 [00:02<00:03,  1.99it/s]
 50%|█████     | 6/12 [00:02<00:03,  1.96it/s]
 58%|█████▊    | 7/12 [00:03<00:02,  1.94it/s]
 67%|██████▋   | 8/12 [00:03<00:02,  1.92it/s]
 75%|███████▌  | 9/12 [00:04<00:01,  1.92it/s]
 83%|████████▎ | 10/12 [00:04<00:01,  1.91it/s]
 92%|█████████▏| 11/12 [00:05<00:00,  1.90it/s]
100%|██████████| 12/12 [00:06<00:00,  1.90it/s]
100%|██████████| 12/12 [00:06<00:00,  1.98it/s]
Version Details
Version ID
7ff25c52350d3ef76aba554a6ae0b327331411572aeb758670a1034da3f1fec8
Version Created
March 20, 2025
Run on Replicate →