babysea/avatar 🖼️🔢📝❓✓ → 🖼️

▶️ 1.1K runs 📅 Apr 2025 ⚙️ Cog 0.9.5 🔗 GitHub ⚖️ License
anime digital-art image-generation lora text-to-image

About

Your Daily AI Partner

Example Output

Prompt:

"a Modern Anime woman, professional digital illustration with vibrant saturated colors, pristine high-quality anime art style, crisp clean linework, rich color depth and shading, beautiful expressive eyes with highlights, detailed intricate hair with proper highlights and shadows, contemporary anime aesthetics as seen in high-budget anime productions, subtle color gradient background complementing character colors, perfect composition with character centered, expert lighting with proper highlights and shadows, detailed facial features matching user photo, high production value animation studio quality, 1024x1024 resolution"

Output

Example output

Performance Metrics

9.06s Prediction Time
15.43s Total Time
All Input Parameters
{
  "width": 1024,
  "height": 1024,
  "prompt": "a Modern Anime woman, professional digital illustration with vibrant saturated colors, pristine high-quality anime art style, crisp clean linework, rich color depth and shading, beautiful expressive eyes with highlights, detailed intricate hair with proper highlights and shadows, contemporary anime aesthetics as seen in high-budget anime productions, subtle color gradient background complementing character colors, perfect composition with character centered, expert lighting with proper highlights and shadows, detailed facial features matching user photo, high production value animation studio quality, 1024x1024 resolution",
  "refine": "no_refiner",
  "scheduler": "K_EULER",
  "lora_scale": 0.6,
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "apply_watermark": true,
  "high_noise_frac": 0.8,
  "negative_prompt": "worst quality, low quality, normal quality, low-res, skin spots, acne, skin blemishes, age spots, ugly, duplicate, morbid, mutilated, blur, motion-blur, blurry, bokeh, crossed eyes, deformed hands, deformed face, extra fingers, fused fingers, too many fingers, long neck, deformed, disfigured, missing limbs, floating limbs, disconnected limbs, malformed hands, poorly drawn face, poorly drawn hands, multiple images, image grid, collage, side by side images, cartoon, 3d render, long body, bad anatomy, bad hands, digital art style, harsh outlines, high contrast, multiple characters",
  "prompt_strength": 0.8,
  "num_inference_steps": 50
}
Input Parameters
mask Type: string
Input mask for inpaint mode. Black areas will be preserved, white areas will be inpainted.
seed Type: integer
Random seed. Leave blank to randomize the seed
image Type: string
Input image for img2img or inpaint mode
width Type: integerDefault: 1024
Width of output image
height Type: integerDefault: 1024
Height of output image
prompt Type: stringDefault: An astronaut riding a rainbow unicorn
Input prompt
refine Default: no_refiner
Which refine style to use
scheduler Default: K_EULER
scheduler
lora_scale Type: numberDefault: 0.6Range: 0 - 1
LoRA additive scale. Only applicable on trained models.
num_outputs Type: integerDefault: 1Range: 1 - 4
Number of images to output.
refine_steps Type: integer
For base_image_refiner, the number of steps to refine, defaults to num_inference_steps
guidance_scale Type: numberDefault: 7.5Range: 1 - 50
Scale for classifier-free guidance
apply_watermark Type: booleanDefault: true
Applies a watermark to enable determining if an image is generated in downstream applications. If you have other provisions for generating or deploying images safely, you can use this to disable watermarking.
high_noise_frac Type: numberDefault: 0.8Range: 0 - 1
For expert_ensemble_refiner, the fraction of noise to use
negative_prompt Type: stringDefault:
Input Negative Prompt
prompt_strength Type: numberDefault: 0.8Range: 0 - 1
Prompt strength when using img2img / inpaint. 1.0 corresponds to full destruction of information in image
replicate_weights Type: string
Replicate LoRA weights to use. Leave blank to use the default weights.
num_inference_steps Type: integerDefault: 50Range: 1 - 500
Number of denoising steps
disable_safety_checker Type: booleanDefault: false
Disable safety checker for generated images. This feature is only available through the API. See [https://replicate.com/docs/how-does-replicate-work#safety](https://replicate.com/docs/how-does-replicate-work#safety)
Output Schema

Output

Type: arrayItems Type: stringItems Format: uri

Example Execution Logs
Using seed: 21190
Loading fine-tuned model
Does not have Unet. assume we are using LoRA
Loading Unet LoRA
Prompt: a Modern Anime woman, professional digital illustration with vibrant saturated colors, pristine high-quality anime art style, crisp clean linework, rich color depth and shading, beautiful expressive eyes with highlights, detailed intricate hair with proper highlights and shadows, contemporary anime aesthetics as seen in high-budget anime productions, subtle color gradient background complementing character colors, perfect composition with character centered, expert lighting with proper highlights and shadows, detailed facial features matching user photo, high production value animation studio quality, 1024x1024 resolution
txt2img mode
The following part of your input was truncated because CLIP can only handle sequences up to 77 tokens: ['lighting with proper highlights and shadows, detailed facial features matching user photo, high production value animation studio quality, 1 0 2 4 x 1 0 2 4 resolution']
The following part of your input was truncated because CLIP can only handle sequences up to 77 tokens: ['lighting with proper highlights and shadows, detailed facial features matching user photo, high production value animation studio quality, 1 0 2 4 x 1 0 2 4 resolution']
  0%|          | 0/50 [00:00<?, ?it/s]
  2%|▏         | 1/50 [00:00<00:05,  8.23it/s]
  4%|▍         | 2/50 [00:00<00:05,  8.07it/s]
  6%|▌         | 3/50 [00:00<00:05,  8.00it/s]
  8%|▊         | 4/50 [00:00<00:05,  7.97it/s]
 10%|█         | 5/50 [00:00<00:05,  7.96it/s]
 12%|█▏        | 6/50 [00:00<00:05,  7.95it/s]
 14%|█▍        | 7/50 [00:00<00:05,  7.95it/s]
 16%|█▌        | 8/50 [00:01<00:05,  7.95it/s]
 18%|█▊        | 9/50 [00:01<00:05,  7.93it/s]
 20%|██        | 10/50 [00:01<00:05,  7.92it/s]
 22%|██▏       | 11/50 [00:01<00:04,  7.91it/s]
 24%|██▍       | 12/50 [00:01<00:04,  7.91it/s]
 26%|██▌       | 13/50 [00:01<00:04,  7.90it/s]
 28%|██▊       | 14/50 [00:01<00:04,  7.89it/s]
 30%|███       | 15/50 [00:01<00:04,  7.89it/s]
 32%|███▏      | 16/50 [00:02<00:04,  7.88it/s]
 34%|███▍      | 17/50 [00:02<00:04,  7.89it/s]
 36%|███▌      | 18/50 [00:02<00:04,  7.89it/s]
 38%|███▊      | 19/50 [00:02<00:03,  7.89it/s]
 40%|████      | 20/50 [00:02<00:03,  7.90it/s]
 42%|████▏     | 21/50 [00:02<00:03,  7.89it/s]
 44%|████▍     | 22/50 [00:02<00:03,  7.90it/s]
 46%|████▌     | 23/50 [00:02<00:03,  7.90it/s]
 48%|████▊     | 24/50 [00:03<00:03,  7.90it/s]
 50%|█████     | 25/50 [00:03<00:03,  7.89it/s]
 52%|█████▏    | 26/50 [00:03<00:03,  7.88it/s]
 54%|█████▍    | 27/50 [00:03<00:02,  7.89it/s]
 56%|█████▌    | 28/50 [00:03<00:02,  7.89it/s]
 58%|█████▊    | 29/50 [00:03<00:02,  7.89it/s]
 60%|██████    | 30/50 [00:03<00:02,  7.88it/s]
 62%|██████▏   | 31/50 [00:03<00:02,  7.88it/s]
 64%|██████▍   | 32/50 [00:04<00:02,  7.89it/s]
 66%|██████▌   | 33/50 [00:04<00:02,  7.88it/s]
 68%|██████▊   | 34/50 [00:04<00:02,  7.88it/s]
 70%|███████   | 35/50 [00:04<00:01,  7.88it/s]
 72%|███████▏  | 36/50 [00:04<00:01,  7.89it/s]
 74%|███████▍  | 37/50 [00:04<00:01,  7.89it/s]
 76%|███████▌  | 38/50 [00:04<00:01,  7.89it/s]
 78%|███████▊  | 39/50 [00:04<00:01,  7.89it/s]
 80%|████████  | 40/50 [00:05<00:01,  7.89it/s]
 82%|████████▏ | 41/50 [00:05<00:01,  7.89it/s]
 84%|████████▍ | 42/50 [00:05<00:01,  7.88it/s]
 86%|████████▌ | 43/50 [00:05<00:00,  7.89it/s]
 88%|████████▊ | 44/50 [00:05<00:00,  7.88it/s]
 90%|█████████ | 45/50 [00:05<00:00,  7.87it/s]
 92%|█████████▏| 46/50 [00:05<00:00,  7.88it/s]
 94%|█████████▍| 47/50 [00:05<00:00,  7.87it/s]
 96%|█████████▌| 48/50 [00:06<00:00,  7.87it/s]
 98%|█████████▊| 49/50 [00:06<00:00,  7.87it/s]
100%|██████████| 50/50 [00:06<00:00,  7.87it/s]
100%|██████████| 50/50 [00:06<00:00,  7.90it/s]
Version Details
Version ID
8f3b1fe1e3854d30acb151322c158310def4bdfa3149de7e27620b4f1a214e68
Version Created
August 20, 2025
Run on Replicate →