Parameter anzeigen
- Ursprünglicher Prompt
- 1male, night, black body armor, holding shotgun, face mask shaped like a skull
- Größe
- 768 x 1280
- Sampling-Schritte
- 28
- Sampling-Methode
- Euler a
- CFG scale
- 5
- Negativ
- nsfw, worst quality, bad quality, low quality, lowres, anatomical nonsense, artistic error, bad anatomy, interlocked fingers, extra fingers, text, artist name, signature, bad feet, extra toes, ugly, poorly drawn, censor, blurry, watermark, simple background, transparent background, old, oldest, glitch, deformed, mutated, disfigured, long body, bad hands, missing fingers, extra digit, fewer digits, cropped, very displeasing, sketch, jpeg artifacts, username, censored, bar_censor, mosaic_censor, conjoined, bad ai-generated, nsfw, long neck, skin blemishes, skin spots, acne, the wrong limb, error, black line, excess hands
Gesichtskorrektur
Verwendetes Modell und LoRA
Ähnliche Bilder
Mehr anzeigen
ks
from PIL import Image
import numpy as np
import imageio.v2 as imageio
import os
src = "/mnt/data/1000010071.jpg"
out = "/mnt/data/anime_image_motion.mp
img = Image.open(src).convert("RGB")
W, H = 720, 1280
img_ratio = img.width / img.height
target_ratio = W / H
if img_ratio > target_ratio:
crop_h = img.height
crop_w = int(crop_h * target_ratio)
else:
crop_w = img.width
crop_h = int(crop_w / target_ratio)
left = (img.width - crop_w) // 2
top = (img.height - crop_h) // 2
img = img.crop((left, top, left + crop_w, top + crop_h))
fps = 30
seconds = 6
writer = imageio.get_writer(
out, fps=fps, codec="libx264",
quality=8, pixelformat="yuv420p"
)
for i in range(fps * seconds):
t = i / (fps * seconds - 1)
# Gentle zoom-in with a tiny side-to-side camera drift.
scale = 1.0 + 0.055 * t
sw = int(crop_w / scale)
sh = int(crop_h / scale)
cx = crop_w / 2 + 18 * np.sin(t * 2 * np.pi)
cy = crop_h / 2 - 10 * t
x0 = int(max(0, min(crop_w - sw, cx - sw / 2)))
y0 = int(max(0, min(crop_h - sh, cy - sh / 2)))
frame = img.crop((x0, y0, x0 + sw, y0 + sh)).resize((W, H), Image.Resampling.LANCZOS)
writer.append_data(np.asarray(frame))
writer.close()
print(f"Created: {out}")
Kim Sokchet
An eye-level medium shot featuring a lone male soldier standing centrally in a desolate environment. The character is clad in heavy, matte-black tactical armor with reinforced plating on the shoulders and chest, integrated with a rugged gas mask and a combat helmet. His eyes glow with an intense, piercing red light from behind the mask's lenses. He firmly grips a massive heavy machine gun, resembling an MG42, with a thick ammunition belt draped across his chest and feeding into the weapon. In his other hand, he holds an M16 rifle pointed toward the ground. The background is a dimly lit, smoky wasteland with debris and atmospheric haze. The visual style is a high-quality anime illustration characterized by sharp line art, deep shadows, and a dark, moody color palette, with the only vibrant highlights being the eerie red glow of his eyes.
Belmel
p
best quality, highly detailed, masterpiece, 1boy,mature, solo, black tactical vest, white clothes, {{white mask}}, {{white full face mask}}, fully covered face, covered eyes, hood, white tactical clothes, holding rifle, indoors, black walls, night
Pharoah
An eye-level medium shot featuring a lone male soldier standing centrally in a desolate environment. The character is clad in heavy, matte-black tactical armor with reinforced plating on the shoulders and chest, integrated with a rugged gas mask and a combat helmet. His eyes glow with an intense, piercing red light from behind the mask's lenses. He firmly grips a massive heavy machine gun, resembling an MG42, with a thick ammunition belt draped across his chest and feeding into the weapon. In his other hand, he holds an M16 rifle pointed toward the ground. The background is a dimly lit, smoky wasteland with debris and atmospheric haze. The visual style is a high-quality anime illustration characterized by sharp line art, deep shadows, and a dark, moody color palette, with the only vibrant highlights being the eerie red glow of his eyes.
Belmel
Kommentare