buddhiraz/photomaker_ape_stylized 🔢📝❓🖼️✓ → 🖼️

▶️ 515 runs 📅 May 2024 ⚙️ Cog 0.9.7

About

Example Output

Prompt:

"A man img shooting laser from a handheld gun"

Output

Performance Metrics

6.98s Prediction Time

134.53s Total Time

All Input Parameters

{
  "prompt": "A man img shooting laser from a handheld gun",
  "num_steps": 20,
  "style_name": "Rick and Morty Character",
  "input_image": "https://replicate.delivery/pbxt/L0xlDLTYT2KLD8sierC2gGAvxVXrLP0kB0M4ylg5segVY7MW/image.png",
  "num_outputs": 1,
  "guidance_scale": 5,
  "negative_prompt": "realistic, photo-realistic, bad quality, bad anatomy, worst quality, low quality, lowres, extra fingers, blur, blurry, ugly, wrong proportions, watermark, image artifacts, bad eyes, bad hands, bad arms",
  "aspect_ratio_name": "Instagram (1:1)",
  "style_strength_ratio": 20
}

Input Parameters

seed Type: integerRange: 0 - 2147483647: Seed. Leave blank to use a random number
prompt Type: stringDefault: A girl img riding dragon over a whimsical castle, 3d CGI, art by Pixar, half-body, screenshot from animation: Prompt. Example: 'a photo of a man/woman img speaking on stage'. The phrase 'img' is the trigger word.
num_steps Type: integerDefault: 20Range: 1 - 100: Number of sample steps
style_name Default: Disney Charactor: Style template. The style template will add a style-specific prompt and negative prompt to the user's prompt.
input_image (required) Type: string: The input image, for example a photo of your face.
lora_choice Default: xl_more_art-full_v1: Choose the LoRA model to use
num_outputs Type: integerDefault: 1Range: 1 - 4: Number of output images
input_image2 Type: string: Additional input image (optional)
input_image3 Type: string: Additional input image (optional)
input_image4 Type: string: Additional input image (optional)
guidance_scale Type: numberDefault: 5Range: 1 - 10: Guidance scale. A guidance scale of 1 corresponds to doing no classifier free guidance.
negative_prompt Type: stringDefault: realistic, photo-realistic, bad quality, bad anatomy, worst quality, low quality, lowres, extra fingers, blur, blurry, ugly, wrong proportions, watermark, image artifacts, bad eyes, bad hands, bad arms: Negative Prompt. The negative prompt should NOT contain the trigger word.
start_merge_step Type: numberDefault: 0Range: 0 - 100: Determines when the model starts blending the prompt's style into the image generation process.if not given its calculated by --> (style_strength_ratio / 100) * num_steps
aspect_ratio_name Default: Instagram (1:1): Aspect-Ratio template. It will add an aspect-ratio-specific prompt and negative prompt to the user's prompt.
style_strength_ratio Type: numberDefault: 20Range: 1 - 100: Style strength (%)
disable_safety_checker Type: booleanDefault: false: Disable safety checker for generated images.

Output Schema

Output

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

Example Execution Logs

Using seed 1701235812...
[Debug] Generate image using aspect ratio [Instagram (1:1)] => 1024 x 1024
Loading image /tmp/tmp6vlbefyximage.png...
Setting seed...
Start inference...
[Debug] Prompt: A Rick and Morty cartoon character of A man img shooting laser from a handheld gun. rick-and-morty-style, cartoon, sci-fi, high-quality
[Debug] Neg Prompt: lowres, bad anatomy, bad hands, text, bad eyes, bad arms, bad legs, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, blurry, grayscale, noisy, sloppy, messy, grainy, highly detailed, ultra textured, photo realistic, photo-realistic, bad quality, bad anatomy, worst quality, low quality, lowres, extra fingers, blur, blurry, ugly, wrong proportions, watermark, image artifacts, bad eyes, bad hands, bad arms
Start merge step: 4
  0%|          | 0/20 [00:00<?, ?it/s]
  5%|▌         | 1/20 [00:00<00:06,  2.98it/s]
 10%|█         | 2/20 [00:00<00:04,  3.85it/s]
 15%|█▌        | 3/20 [00:00<00:03,  4.25it/s]
 20%|██        | 4/20 [00:00<00:03,  4.47it/s]
 25%|██▌       | 5/20 [00:01<00:03,  4.58it/s]
 30%|███       | 6/20 [00:01<00:03,  4.65it/s]
 35%|███▌      | 7/20 [00:01<00:02,  4.72it/s]
 40%|████      | 8/20 [00:01<00:02,  4.76it/s]
 45%|████▌     | 9/20 [00:01<00:02,  4.79it/s]
 50%|█████     | 10/20 [00:02<00:02,  4.81it/s]
 55%|█████▌    | 11/20 [00:02<00:01,  4.83it/s]
 60%|██████    | 12/20 [00:02<00:01,  4.82it/s]
 65%|██████▌   | 13/20 [00:02<00:01,  4.83it/s]
 70%|███████   | 14/20 [00:03<00:01,  4.84it/s]
 75%|███████▌  | 15/20 [00:03<00:01,  4.84it/s]
 80%|████████  | 16/20 [00:03<00:00,  4.82it/s]
 85%|████████▌ | 17/20 [00:03<00:00,  4.82it/s]
 90%|█████████ | 18/20 [00:03<00:00,  4.82it/s]
 95%|█████████▌| 19/20 [00:04<00:00,  4.81it/s]
100%|██████████| 20/20 [00:04<00:00,  4.80it/s]
100%|██████████| 20/20 [00:04<00:00,  4.68it/s]
Running safety checker...
Saving images to file...

Version Details

Version ID: da423f8c1c8b9fa392b776f3789b79f6fee4128c0fac35344049ae268225a281
Version Created: June 21, 2024

Run on Replicate →