PC 98 Style Lora
NSFW
NSFW-modell. Dess bilder är dolda medan NSFW är av; slå på NSFW för att se dem.
Kör lokalt
pc_98_style_h3_minimax_h3_lora.safetensors
296 MB · SafeTensor · fp16
Nedladdningar sköts av Civitai. Vissa skapare kräver att du först loggar in på Civitai.
Om denna modell
Jämför
MINIMAX H3 · LoRA
by paralaif_xox - PC-98 Style Lora - Training done with some screenshots of pc-98 old japanese games, this is intended to bring old anime aesthetic and pixelart.
Skaparens anteckningar
I'm bringing this new training done with some screenshots of pc-98 old japanese games, this is intended to bring old anime aesthetic and pixelart.
SHA256
3CC0D8C7C8C3A4E7D35DE2856E5C98786D2EE63283319F986B21F091C6971B76
ModelTrends.ai modell-ID
#27042
Rapportera innehåll
Exempelrenderingar
Prompter och inställningar delade av personerna som gjorde dessa renderingar på Civitai. Välj en rendering för att se hur den gjordes.
Inställningar
Steg
8
Seed
1234567890
Storlek
768x512
Prompt
subject_definitions:
<Subject 1> is the character as depicted in <Image 1>. Her facial features, eyes, eye color, hairstyle, and body are anchored strictly to <Image 1>. She has long hair tied into a low ponytail.
style_and_rendering:
640x400 native resolution pixel art, PC-9801 retro Japanese visual novel pixel art, 16-bit NEC PC-98 graphics, 1990s retro anime game aesthetic.
Hand-drawn pixel art, strict 16-color palette, cross-hatch pixel dithering for shading, visible scanlines, sharp 1:1 pixel grid, zero anti-aliasing.
Hand-drawn retro sprite animation on threes and fours (4fps-6fps effective motion rate), stepped 3-frame sprite swaps, zero procedural bone-rigging, zero vector tweening, zero motion interpolation.
Zero modern 3D render, zero smooth digital interpolation, zero high-resolution gradients, zero anti-aliased lines.
camera_specifications:
[Shot 1] Tight low-angle medium shot from table-surface level, tilted slightly upward looking up at <Subject 1>. Tight crop from table level to top of her head. In the immediate lower-left foreground, the base and spout of a normal ceramic teapot sit directly on the table surface, partially cropped by the frame edge. <Subject 1> sits sharp in focus on the right side of the frame in a 7/8 profile view.
[Shot 2] Hard cut to static close-up shot of <Subject 1>'s face, fixed framing.
integrated_multimodal_description:
[Shot 1] PC-98 visual novel scene in an outdoor Victorian garden. Tight table-level perspective looking slightly upward. <Subject 1> sits tightly framed on the right half of the screen. Resting directly on the wooden table surface in the lower-left foreground is a normal ceramic teapot, partially cut off by the left screen boundary.
From 00:00 to 00:01.000, <Subject 1> sits in an idle animation loop with a graceful demeanor. Pixelated steam rises from her teacup in a 3-frame looping cycle. Her low ponytail, skirt, and garden foliage move in a hand-drawn 3-frame asymmetric sprite loop, snapping strictly between 3 distinct pixel-shift keyframes with zero smooth vector warping.
From 00:01.000 to 00:03.000, while her hair and skirt continue snapping through the same stepped 3-frame wind loop, she looks down at the teacup then brings the teacup up to her lips and takes a sip closing her eyes.
From 00:03.000 to 00:06.000, as the hair and clothing maintain the rigid 3-frame stepped pixel wind loop without smoothing, she remains frozen holding the teacup up against her lips with her eyes closed in a static sprite hold pose.
[Shot 2] Hard cut directly to a static close-up frame of <Subject 1>'s face from a three-quarters view, her eyes closed, starting with the ceramic teacup held directly in front of her lower face and lips. Pixelated steam rises from the teacup.
From 00:06.000 to 00:08.000, while individual locks of her hair snap through a stepped 3-frame pixel wind cycle, she lowers the teacup downward out of frame with measured, deliberate speed. Her eyes open with a composed look, looking down at the teacup, her throat moves in a subtle 2-frame swallow pose.
From 00:08.000 to 00:10.000, as wind continues snapping her hair, her eyes shift in a crisp 2-frame pixel swap to give a slow, composed, deadpan stare. Her eyebrows remain level, and her mouth settles into a tight line of stoic disappointment and disgust while emitting a soft grunt.
overall_soundscape:
low-bitrate compressed ceramic teacup clink and sip sound effect, 8-bit low-register disappointed tone, retro FM-synth ambient garden chirping loop.
non_diegetic_music:
N/A
Liknande modeller
Popularitetstrend
Hur den här modellens popularitet har rört sig jämfört med resten av katalogen: dess tillväxt i nedladdningar, gillningar och användning under varje period, mätt mot en typisk modells tillväxt under samma period, med dess heat-poäng vid den tiden. Över den typiska tillväxten ses som en uppgång, under som en nedgång. Det förflutna rekonstrueras från dagens totalsummor, modellens första dag och dess uppmätta nedladdningshastighet där två mätningar finns; en modell som inte fanns i början av en period visar n/a.
Den här veckan
▲
25.0%
8,120° då, 8,164° nu
Den här månaden
n/a
Inte släppt än i början av den här perioden
Senaste året
n/a
Inte släppt än i början av den här perioden
Ingen andra mätning av källorna än, så kurvan fördelar dagens totalsummor jämnt över modellens livslängd. Den blir tydligare när dagliga synkroniseringar lägger till mätningar.
Först sedd 6 Sep 2026.
AI-modeller för bild-, video- och textgenerering
PC 98 Style Lora är en LoRA för familjen MiniMax H3, listad på ModelTrends.ai, en skrivskyddad katalog över AI-modeller med öppen källkod för bild, video och text. Jämför den med andra MiniMax H3-modeller, se dess hettapoäng och prova den på PirateDiffusion eller BitVector.
Bläddra efter modellfamilj
Text / LLM-modeller
415
Anima-modeller
519
Chroma-modeller
17
Flux-modeller
1,498
Flux 2 / Klein-modeller
1,239
MiniMax H3-modeller
330
Hunyuan-modeller
204
Ideogram-modeller
20
Krea2-modeller
676
Qwen-modeller
20
Qwen2-modeller
36
Ltx2-modeller
152
Stable Diffusion 1.5-modeller
7,042
Stable Diffusion XL 1.0-modeller
17,420
Zimage-modeller
815
Wan-modeller
1,067

Model
Trends
.ai
© ModelTrends.ai
|
© 2026
|
Alla rättigheter förbehållna

