Reproducción automática
Ejecutar en local
LTX-2 Galaxy.safetensors
384 MB · SafeTensor
Las descargas las sirve Civitai. Algunos creadores piden iniciar sesión en Civitai primero.
Sobre este modelo
LTX2 · LoRAs
by aiguild - GalaxyAce LoRA
Notas del creador
📱 GalaxyAce LoRA
🎬 MiniMax H3 added
Model: MiniMax H3
Recommended LoRA Strength: 1.00
Trigger Word: Not required
📷 Krea 2 added
Model: Krea 2 (trained on Krea-2-Raw, works on Raw & Turbo)
Recommended LoRA Strength: 1.0 for in-dataset scenes — up to 2.0 (see Strength Behavior)
🎬 LTX-2.3 added
Model: LTX-2.3
Recommended LoRA Strength: 1.00
Trigger Word: Not required
In LTX 2.3 T2V&I2V ComfyUI Workflow, LoRA is connected immediately after the checkpoint node inside the subgraph
🎬 LTX-2 added
Model: LTX-2
Recommended LoRA Strength: 1.00
Trigger Word: early 2010s low-end android phone footage
This LoRA replicates the early 2010s video style of a Samsung Galaxy Ace smartphone.
The training videos include streets, parks, everyday scenes, casual portraits, and real-life moments typical for low-end Android devices.
The LoRA transfers:
-
color reproduction of the Galaxy Ace camera
-
sensor noise & compression artifacts
-
dynamic range and exposure behavior typical for small sensors
-
lens softness and subtle edge blur
-
subtle motion jitter and handheld feel
-
overall “early 2010s low-end Android phone video” aesthetics
⭐ How to Use
-
LoRA Strength: 1.00
-
Base Model: LTX-2
-
Best with natural scenes: street videos, parks, cafes, casual portraits, travel clips, everyday life
-
Adds subtle imperfections and low-fi realism for video
-
Recommended workflow: official ComfyUI LTX-2 Text-to-Video pipeline
🧪 Notes
-
Ideal for: street videos, diary-style clips, lifestyle captures, travel footage, nature
-
Preserves realism, avoids stylization, reproduces small-sensor behavior
-
Enhances authenticity while keeping motion, lighting, and colors faithful to early 2010s low-end Android look
📷 Z-Image-Turbo (Photos)
Model: Z-Image-Turbo
Recommended LoRA Strength: 1.20
⭐ How to Use
-
LoRA Strength: 1.20
-
Base Model: Z-Image-Turbo
-
Works perfectly with natural, simple prompts
-
Adds subtle imperfections and real-photo feel of a low-megapixel phone camera
🧪 Notes
-
Best results: street photos, portraits, pets, travel shots, nature, everyday objects
-
Maintains realism, avoids stylization
-
Recreates small-sensor characteristics of the original device
SHA256
704FF9746666742DA7E75B6181BF7F0617C66141E27EBFCC39DB45ED5F985229
ID de modelo de ModelTrends.ai
#24641
Denunciar contenido
Renders de ejemplo
Prompts y ajustes compartidos por quienes hicieron estos renders en Civitai. Elige un render para ver cómo se hizo.
Ajustes
Sampler
Euler a
Pasos
8
Guidance
1
Semilla
1114124778528247
Tamaño
672x1248
Prompt
[real time motion], [realism], [in real life footage], [real animal texture], early 2010s low-end android footage.
Photorealistic shot 1: [Wide cinematic tracking camera]. A stylish anthropomorphic sheep with curled ram horns and thick cream wool stands inside a bright industrial loft with large arched brick windows, soft daylight flooding the room. She wears a tight blue long-sleeve dress hugging her fluffy body. She bends slightly forward with hands on her knees, looking toward the camera as if asking for approval, tail twitching slightly.
female sheep Voice: "Hey baby… be honest… does this dress make me look fluffy or fabulous?",
Male off-screen voice: "It, uhh, it looks fabulous hon".
Photorealistic shot 2: [Medium handheld push-in camera]. The sheep slowly straightens and turns sideways, shifting her hips to show the profile of the dress. The fabric stretches smoothly over her wool while she checks her reflection in the window glass, giving a playful glance back to the camera.
Female sheep Voice: "Wait… maybe it’s just the angle. Cameras add like… ten pounds of wool, right?",
Male off-screen voice: "N-no, you're fine".
Photorealistic shot 3: [Low angle cinematic dolly move]. She rotates her body and places one hoof-hand on her hip, striking a confident pose while tilting her head. The camera circles slightly around her as sunlight highlights the texture of her fleece and the bright blue dress.
female sheep Voice: "Okay okay, new pose. This is my ‘runway sexy chic’ look.",
Male off-screen voice: "l-lets go baby, we don't want to late for the party".
Photorealistic shot 4: [Close-up slow tracking camera]. She leans closer to the lens, adjusting the dress at the waist and twisting her torso to show another angle, ears flicking while she studies the camera’s reaction.
Voice: "If this dress survives my sexy fluff physics… it deserves a fashion award.",
Male off-screen voice: "ofcourse, lets go, we gonna be late".
Photorealistic shot 5: [Wide cinematic orbit camera]. She spins lightly and finishes with a playful pose, hands on hips and one leg slightly forward, the dress stretching as she proudly shows every angle in the sunlit loft.
Voice: "Alright, final verdict… do I look stunning, or should I blame the dress again?",
Male off-screen voice: "Y-You look Fantastic, can we go now?".
Prompt negativo
cartoon, anime, bad quality, blur, text, words, unreal, fake skin, unrealistic, unnatural, bad motion,
Ajustes
Tamaño
704x1280
Prompt
early 2010s low-end android phone footage
Shot 1: [Close-up]
Flat daylight at a small city bus stop. A beautiful Instagram-style young blonde woman sits on a metal bench. The frame captures her from shoulders up. Clean skin, light makeup, glossy lips, well-groomed eyebrows. Her blonde hair falls neatly over one shoulder. Background is softly blurred: hints of a bus stop sign and pavement. The framing is casual, slightly tilted, with mild digital noise.
(Sound FX: distant traffic hum, footsteps, faint wind)
Shot 2: [Extreme Close-up, Abrupt Digital Zoom]
The camera snaps closer, slightly oversharpened. A male voice speaks from off-screen, calm but tentative. She looks toward the sound, pauses for half a second, then gives a small, confident smile — practiced but natural, the kind meant for a camera.
(Dialogue:
— "Hi, can I talk to you?"
— "Yes.")
Shot 3: [Close-up, Static Hold]
The camera holds on her face. The smile remains, soft and composed. She adjusts her posture slightly, chin lifting a fraction. She does not speak again. The moment lingers, clean and quiet.
(Sound FX: distant bus braking, soft city ambience)
Ajustes
Pasos
40
Tamaño
704x1280
Prompt
Shot 1: [Wide Shot, Slow Dolly In] early 2010s low-end android phone footage, a lot of diverse cars driving in a busy street in new york manhatten reflecting off wet asphalt and car windows, a row of parked cars glinting under street lamps in the golden hour. a lot of pedestrians walking on the sidewalk. The street hums with distant engines and faint music from nearby clubs. (Sound FX: engine idling, distant chatter). from the distance you her singing an female opera voice in Italian:
"La donna è mobile, qual piuma al vento, muta d’accento e di pensiero. Sempre un amabile, leggiadro viso, in pianto o in riso, è menzognero."
Rich, resonant notes echo through the space.
Shot 2: [Medium Close-up, Handheld] a woman in a red opera dress and on high heels strolling on the sidewalk comes into the frame. As her voice climbs in pitch, her brows lift, and her expression becomes more passionate, almost vulnerable.
Shot 3: [Tracking Shot, Over-the-Shoulder] Camera follows her as she walks past the row of cars, traffic lights reflecting in her eyes. pedestrians claps their hand behind her, yellow cabs and cars pass by, and the street feels alive. (Sound FX: tires on asphalt, distant people applaud.)
Ajustes
Pasos
40
Guidance
4
Tamaño
832x1216
Prompt
Style: cinematic-realistic video, handheld selfie video captured with a front-facing camera on a low-end early-2010s Android smartphone, golden hour, New York City, Manhattan.
A woman records herself in selfie mode, holding the phone at arm’s length. Her face is clearly visible, front-facing, centered, and remains fully inside the frame at all times, from forehead to chin. The framing is unmistakably a selfie: the camera is slightly angled downward and inward toward her face, with mild wide-angle distortion typical of a cheap front camera.
Her right forearm and hand are continuously visible along the far-left edge of the frame, fixed in position and never swinging or drifting, confirming she is physically holding the phone. The arm remains a stable compositional anchor throughout the entire clip.
She walks forward at a steady pace while maintaining direct eye contact with the camera lens. The camera motion shows gentle vertical bobbing synchronized to her footsteps — subtle, imperfect, human — but the framing of her face stays locked and consistent despite movement.
Behind her, the city scrolls past: rain-wet Manhattan sidewalks reflect headlights and amber streetlights; cars move in both directions — sedans, SUVs, yellow taxis — their lights briefly streaking and smearing due to motion and sensor noise. Parked cars line the curb behind her shoulders, metallic surfaces glowing warmly. Pedestrians pass behind her, blurred figures crossing the background, entering subway entrances, pausing near storefronts.
Urban ambience surrounds her: distant diesel engines idle, muffled horn blasts echo intermittently, low bass pulses leak from nearby clubs. The scene feels alive and unfiltered.
Throughout the walk she sings directly to the camera, operatically and confidently, in fluent Italian. Her facial performance is readable and consistent: eyebrows lift slightly during crescendos, lips open wide on sustained notes, cheeks tense with breath support, eyes briefly closing during climactic phrases before reopening to reconnect with the lens. Her expression is sincere and intimate, not theatrical — a private performance unfolding in public space.
She sings in Italian:
"La donna è mobile, qual piuma al vento,
muta d’accento e di pensiero.
Sempre un amabile, leggiadro viso,
in pianto o in riso, è menzognero.
È sempre misero chi a lei s’affida."
The environment remains grounded and unstaged: rain-darkened asphalt absorbs scattered sunlight unevenly, glass facades behind her refract warm orange-gold tones fading into dusky violet. Neon reflections ripple across puddles. Street signs blur softly with motion. Nothing feels staged — this is a real selfie video, imperfect, personal, and continuous.
Ajustes
Tamaño
1088x1920
Prompt
Woman going out, Selfie
Prompt negativo
blurry
Ajustes
Tamaño
960x1280
Prompt
Woman going out, Selfie
Prompt negativo
blurry
Ajustes
Sampler
Euler a
Pasos
8
Guidance
1
Tamaño
1088x1920
Prompt
Shot 1: [Wide Shot, Slow Dolly In] early 2010s low-end android phone footage, a lot of yellow cab driving in a busy street in new york manhatten reflecting off wet asphalt and car windows, a row of parked cars glinting under street lamps. a lot of pedestrians walking on the sidewalk. Young people in casual 2010s fashion lean against vehicles, checking phones and chatting. The street hums with distant engines and faint music from nearby clubs. (Sound FX: engine idling, muffled bass, distant chatter)
Shot 2: [Medium Close-up, Handheld] a woman in bikini sitting in one of the cars on the passenger side and yells through the open window (she says: "yippi ya yeah, Are we finally going somewhere tonight?"). she holds her arms out through the windows up into the air. she says "Party! PArtyy!".
Shot 3: [Tracking Shot, Over-the-Shoulder] Camera follows her as she drives past the row of cars, traffic lights reflecting in her eyes. pedestrians laugh behind her, yellow cabs and cars pass by, and the street feels alive. She exhales and smiles slightly, ready for the fun?. (Sound FX: tires on asphalt, distant laughter)
Modelos similares
Modelos de IA para generar imagen, vídeo y texto
galaxyace ltx2 es un LoRA para la familia Ltx2 listado en ModelTrends.ai, un catálogo de solo lectura de modelos de IA de imagen, vídeo y texto de código abierto. Compáralo con otros modelos Ltx2, consulta su puntuación de calor para ver su tendencia y ábrelo en PirateDiffusion o BitVector para probarlo.
Explorar por familia de modelos
Modelos Text / LLM
411
Modelos Anima
509
Modelos Chroma
14
Modelos Flux
1,071
Modelos Flux 2 / Klein
1,237
Modelos MiniMax H3
331
Modelos Hunyuan
197
Modelos Ideogram
20
Modelos Krea2
674
Modelos Qwen
17
Modelos Qwen2
36
Modelos Ltx2
150
Modelos Stable Diffusion 1.5
6,465
Modelos Stable Diffusion XL 1.0
15,432
Modelos Zimage
804
Modelos Wan
919

Model
Trends
.ai
© ModelTrends.ai
|
Hecho en Japón
|
© 2026
