aisha-ai-official/perfect-rsb-mix-v15 ❓🔢📝✓ → 🖼️

▶️ 87 runs 📅 Feb 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, closeup"

Output

Example output

Performance Metrics

7.62s Prediction Time
7.62s Total Time
All Input Parameters 
{
  "vae": "default",
  "seed": -1,
  "model": "PerfectRSBmix",
  "steps": 40,
  "width": 1024,
  "height": 1024,
  "prompt": "street, 1girl, dark-purple short hair, purple eyes, medium breasts, cleavage, casual clothes, smile, V, closeup",
  "cfg_scale": 5,
  "clip_skip": 2,
  "pag_scale": 3,
  "scheduler": "Euler a",
  "batch_size": 1,
  "negative_prompt": "nsfw, naked",
  "guidance_rescale": 0.5,
  "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: PerfectRSBmix
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: 3Range: 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: DPM++ 2M SDE
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: 0.5Range: 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, (scenery, volumetric lighting))1.2, " Negative prompt: "(simplified, abstract, unrealistic, impressionistic, low resolution, lowres, bad anatomy, bad hands, missing fingers, worst quality, low quality, normal quality)1.2, ")
Output Schema

Output

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

Example Execution Logs 
Using text to image mode.
Using seed: 401743199
  0%|          | 0/40 [00:00<?, ?it/s]
  5%|▌         | 2/40 [00:00<00:04,  9.10it/s]
  8%|▊         | 3/40 [00:00<00:04,  7.87it/s]
 10%|█         | 4/40 [00:00<00:04,  7.35it/s]
 12%|█▎        | 5/40 [00:00<00:04,  7.06it/s]
 15%|█▌        | 6/40 [00:00<00:04,  6.91it/s]
 18%|█▊        | 7/40 [00:00<00:04,  6.80it/s]
 20%|██        | 8/40 [00:01<00:04,  6.74it/s]
 22%|██▎       | 9/40 [00:01<00:04,  6.69it/s]
 25%|██▌       | 10/40 [00:01<00:04,  6.67it/s]
 28%|██▊       | 11/40 [00:01<00:04,  6.64it/s]
 30%|███       | 12/40 [00:01<00:04,  6.61it/s]
 32%|███▎      | 13/40 [00:01<00:04,  6.61it/s]
 35%|███▌      | 14/40 [00:02<00:03,  6.59it/s]
 38%|███▊      | 15/40 [00:02<00:03,  6.59it/s]
 40%|████      | 16/40 [00:02<00:03,  6.59it/s]
 42%|████▎     | 17/40 [00:02<00:03,  6.58it/s]
 45%|████▌     | 18/40 [00:02<00:03,  6.58it/s]
 48%|████▊     | 19/40 [00:02<00:03,  6.57it/s]
 50%|█████     | 20/40 [00:02<00:03,  6.57it/s]
 52%|█████▎    | 21/40 [00:03<00:02,  6.57it/s]
 55%|█████▌    | 22/40 [00:03<00:02,  6.56it/s]
 57%|█████▊    | 23/40 [00:03<00:02,  6.56it/s]
 60%|██████    | 24/40 [00:03<00:02,  6.56it/s]
 62%|██████▎   | 25/40 [00:03<00:02,  6.55it/s]
 65%|██████▌   | 26/40 [00:03<00:02,  6.55it/s]
 68%|██████▊   | 27/40 [00:04<00:01,  6.55it/s]
 70%|███████   | 28/40 [00:04<00:01,  6.54it/s]
 72%|███████▎  | 29/40 [00:04<00:01,  6.54it/s]
 75%|███████▌  | 30/40 [00:04<00:01,  6.54it/s]
 78%|███████▊  | 31/40 [00:04<00:01,  6.54it/s]
 80%|████████  | 32/40 [00:04<00:01,  6.53it/s]
 82%|████████▎ | 33/40 [00:04<00:01,  6.53it/s]
 85%|████████▌ | 34/40 [00:05<00:00,  6.53it/s]
 88%|████████▊ | 35/40 [00:05<00:00,  6.53it/s]
 90%|█████████ | 36/40 [00:05<00:00,  6.53it/s]
 92%|█████████▎| 37/40 [00:05<00:00,  6.52it/s]
 95%|█████████▌| 38/40 [00:05<00:00,  6.52it/s]
 98%|█████████▊| 39/40 [00:05<00:00,  6.52it/s]
100%|██████████| 40/40 [00:06<00:00,  6.52it/s]
100%|██████████| 40/40 [00:06<00:00,  6.65it/s]
Version Details
Version ID
ae2191905b35c7167d695066bfebcd8ae438e09b809b37c453aee030d92ad673
Version Created
February 20, 2025
Run on Replicate →