aisha-ai-official/project-il-v2 ❓🔢📝✓ → 🖼️

▶️ 150 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

6.05s Prediction Time

37.66s Total Time

All Input Parameters

{
  "vae": "default",
  "seed": -1,
  "model": "Project-IL-v2",
  "steps": 34,
  "width": 1024,
  "height": 1024,
  "prompt": "street, 1girl, dark-purple short hair, purple eyes, medium breasts, cleavage, casual clothes, smile, V",
  "cfg_scale": 7,
  "clip_skip": 2,
  "pag_scale": 0,
  "scheduler": "Euler a",
  "batch_size": 1,
  "negative_prompt": "nsfw, naked",
  "guidance_rescale": 1,
  "prepend_preprompt": true
}

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: Project-IL-v2: The model to use
steps Type: integerDefault: 34Range: 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: 7Range: 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
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,absurdres,newest, " Negative prompt: "low quality, bad quality, watermark, text, username, artist name, watermark, bad_hands, worst, low quality, mutated_hands, mutated_fingers, extra_fingers, 6fingers, six_fingers, ")

Output Schema

Output

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

Example Execution Logs

Using text to image mode.
Using seed: 1903314324
  0%|          | 0/34 [00:00<?, ?it/s]
  3%|▎         | 1/34 [00:00<00:07,  4.49it/s]
  9%|▉         | 3/34 [00:00<00:03,  8.38it/s]
 12%|█▏        | 4/34 [00:00<00:03,  8.53it/s]
 15%|█▍        | 5/34 [00:00<00:03,  8.63it/s]
 18%|█▊        | 6/34 [00:00<00:03,  8.70it/s]
 21%|██        | 7/34 [00:00<00:03,  8.74it/s]
 24%|██▎       | 8/34 [00:00<00:02,  8.76it/s]
 26%|██▋       | 9/34 [00:01<00:02,  8.78it/s]
 29%|██▉       | 10/34 [00:01<00:02,  8.80it/s]
 32%|███▏      | 11/34 [00:01<00:02,  8.80it/s]
 35%|███▌      | 12/34 [00:01<00:02,  8.81it/s]
 38%|███▊      | 13/34 [00:01<00:02,  8.80it/s]
 41%|████      | 14/34 [00:01<00:02,  8.79it/s]
 44%|████▍     | 15/34 [00:01<00:02,  8.80it/s]
 47%|████▋     | 16/34 [00:01<00:02,  8.78it/s]
 50%|█████     | 17/34 [00:01<00:01,  8.78it/s]
 53%|█████▎    | 18/34 [00:02<00:01,  8.78it/s]
 56%|█████▌    | 19/34 [00:02<00:01,  8.79it/s]
 59%|█████▉    | 20/34 [00:02<00:01,  8.79it/s]
 62%|██████▏   | 21/34 [00:02<00:01,  8.78it/s]
 65%|██████▍   | 22/34 [00:02<00:01,  8.78it/s]
 68%|██████▊   | 23/34 [00:02<00:01,  8.78it/s]
 71%|███████   | 24/34 [00:02<00:01,  8.78it/s]
 74%|███████▎  | 25/34 [00:02<00:01,  8.78it/s]
 76%|███████▋  | 26/34 [00:03<00:00,  8.78it/s]
 79%|███████▉  | 27/34 [00:03<00:00,  8.78it/s]
 82%|████████▏ | 28/34 [00:03<00:00,  8.77it/s]
 85%|████████▌ | 29/34 [00:03<00:00,  8.77it/s]
 88%|████████▊ | 30/34 [00:03<00:00,  8.77it/s]
 91%|█████████ | 31/34 [00:03<00:00,  8.77it/s]
 94%|█████████▍| 32/34 [00:03<00:00,  8.76it/s]
 97%|█████████▋| 33/34 [00:03<00:00,  8.76it/s]
100%|██████████| 34/34 [00:03<00:00,  8.75it/s]
100%|██████████| 34/34 [00:03<00:00,  8.68it/s]

Version Details

Version ID: 93c6b4467c152de3e5b70c09ae03d28528176c83d303768bfc039f8ee3262022
Version Created: March 5, 2025

Run on Replicate →