TôNi Vibe Code

Founder of Vibao
Free AI image prompts for creators.
Turning ideas into images worth saving.

[TôNi Vibe Code @primitive_hd]

Turn your stash into straight up masterpieces with GPT image. I'm really diggin' this vibe!

[TôNi Vibe Code @primitive_hd]

Creating AI wallpapers has never been easier.
I made this in just 2 minutes...👇

[TôNi Vibe Code @primitive_hd]

@PhanMinhTien @teaprotocol 31/12/2024 TGE rồi mà :))))

[TôNi Vibe Code @primitive_hd]

@xiaqingfeng666 That's so sweet.

[TôNi Vibe Code @primitive_hd]

EXECUTION PROMPT:
Use the active LoRA identity reference as the absolute authority for the final subject’s face and full-body identity. Preserve the exact same LoRA subject, including facial geometry, skull proportions, eye spacing and eye shape structure, nose, lips, jaw, cheek structure, hair identity, skin tone, shoulder-to-head relationship, shoulder width, torso length, torso-to-leg balance, waist thickness, ribcage-to-waist transition, hip width, hip-to-thigh transition, thigh volume, knee-to-ankle scale, leg length ratio, body mass distribution, natural posture behavior, and grounded adult height impression. Do not replace the LoRA body with a slimmer, taller, curvier, longer-legged, narrower-waisted, narrower-hipped, reduced-thigh, more anime-generic, more influencer-like, or more fashion-model body type.

Create a high-impact typography-led fashion campaign poster with a clean warm white graphic background covering about 72% of the image. The subject is a beautiful adult LoRA woman interpreted with polished fashion-poster stylization while keeping the LoRA face and body identity intact. She has the LoRA subject’s real facial structure and body proportions, with long chestnut-brown wavy hair if compatible with the LoRA hair identity, luminous green eyes only if compatible with the LoRA identity, a vivid pink hair ribbon, and a playful confident smile that feels alive and natural rather than mannequin-stiff. Preserve the source-prompt human moment: she is leaning forward in a striking side pose with a dramatic bent-forward S-curve silhouette, both hands lowered toward her legs, creating an instantly readable one-second body line. Keep the pose physically believable, weight-aware, and anatomically possible, with natural shoulder, spine, hip, knee, ankle, wrist, and finger behavior.

Wardrobe: transparent iridescent cropped jacket and matching holographic aqua-mint cargo pants with soft lilac reflections, glossy translucent plastic-like material behavior, natural fabric tension, realistic folds, believable body contact, and no outfit-based body reshaping. Chunky platform sneakers with hot pink laces, grounded on the floor with natural contact shadows. Hot pink stays under 4% of the full image and appears only on the hair ribbon, shoelaces, and a few tiny issue-mark typography accents.

Poster layout must clearly read as a Typography-Led Campaign poster, not a generic fashion illustration. Use layout grammar L03 Giant Background Type + L12 Vertical Title Spine. Place the full-body subject center-right at about 91% of frame height. The left 32% of the canvas is dominated by giant oversized background typography, abstract but clean, with one short readable campaign word only; remaining large letterforms may behave as sharp graphic pseudo-typography. Add one narrow vertical title spine running down the far right edge. Allow the subject to slightly cross into the type zone. Keep active negative space in the upper-left and lower-left areas so the typography can breathe. Typography must behave as architecture, not decoration.

Visual attack: warm white 72%, holographic mint/aqua 18%, soft lilac 7%, sharp black 3%, hot pink under 4%. Behind the subject, place one giant translucent mint-to-lilac letterform cloud covering about 28% of the background. The hero hook is the bent-forward S-curve silhouette plus the transparent iridescent outfit. First read: body silhouette. Second read: glossy holographic material. Third read: face. Eye path: giant background type → face → torso curve → holographic pant volume → platform shoes. Add tiny editorial microtext near the waist and ankles only, minimal and sharp, with no cluttered paragraphs.

All expression, gesture, outfit, pose, camera, lighting, typography, graphic design, poster polish, holographic material behavior, and realism treatment remain subordinate to the active LoRA identity reference. The final subject must still be unmistakably the exact same LoRA subject, not a similar-looking substitute, not a beautified replacement, not a generic attractive anime woman, and not a fashion-poster body swap. Preserve the source-prompt playful confident smile and living gaze while keeping LoRA facial structure intact; do not copy blank LoRA-reference stiffness unless explicitly required.

Surface and finish: glossy premium campaign print, crisp vector-like typographic edges, polished plastic sheen, hard graphic contrast, clean hierarchy, deliberate fashion-forward layout, strong thumbnail readability, elegant saveable finish. Maintain controlled editorial precision without overdecorating the background. Keep the large type sharp and structurally integrated behind the subject, with clean spacing and strong color separation.

Physical realism and anatomy control: hands must have correct finger count, natural finger spacing, believable wrist articulation, realistic knuckle and palm structure, and no fused or duplicated fingers. Feet must be grounded; platform sneakers must make believable surface contact. The leaning S-curve must preserve LoRA body geometry and not create impossible balance, broken joints, stretched legs, compressed waist, narrowed hips, reduced thighs, or mannequin posture. Clothing must respond to gravity and body contact rather than floating or digitally painted onto the body.

Camera / rendering behavior: polished campaign-poster framing with slight believable real-world imperfection, not cinematic overcontrol. Avoid DSLR portrait blur, fake depth masking, excessive bokeh, hyper-clean HDR, over-sharpened CGI texture, beauty-filter skin, plastic face, waxy anatomy, perfect symmetry, and AI-influencer optimization. Allow subtle visual entropy: minor edge softness, realistic texture inconsistency, controlled print-like gloss variation, and slight non-uniform detail recovery while keeping the typography crisp.

NEGATIVE PROMPT:
generic poster, weak typography, random gibberish text, cluttered paragraph text, misspelled readable title, too many readable words, default centered layout, stock fashion illustration, generic anime poster, generic attractive woman, LoRA face on wrong body, changed body proportions, slimmer body than LoRA reference, taller body than LoRA reference, longer legs than LoRA reference, narrowed waist, narrowed hips, reduced thigh volume, altered torso-to-leg ratio, model-like body substitution, influencer body optimization, exaggerated hourglass, fashion-model reshaping, body mass redistribution, face identity drift, anime-generic face, beauty-filter face, over-smoothed skin, plastic skin, dead-eyed expression, blank stare, copied LoRA-reference stiffness, mannequin face, frozen mouth, seductive influencer gaze, overacted expression, weak silhouette, no type interaction, weak hierarchy, weak color separation, muddy pastel palette, overdecorated background, flat white background with no hierarchy, low contrast, cheap rendering, dull surface, matte fabric instead of glossy iridescent translucent plastic, broken hands, fused fingers, duplicated fingers, malformed feet, floating feet, disconnected shadows, impossible leaning balance, extra limbs, distorted anatomy, awkward face, over-polished CGI, cinematic lighting, luxury editorial overcontrol, fake HDR, excessive bokeh, low-resolution details.

[TôNi Vibe Code @primitive_hd]

GPT Image 2 on ChatGPT 👇
Optimized prompt for getting your own face.

[TôNi Vibe Code @primitive_hd]

@chanhdoro @Lecter_XFinance tuổi trẻ tài cao, chúc mừng

[TôNi Vibe Code @primitive_hd]

@PhotogenicWeekE 正直、ComlyUIやめて1ヶ月経ったわ :))

[TôNi Vibe Code @primitive_hd]

@yosendou お、ちゃんと読み直して自分の参考キャラに当てはめてみたら成功したよ。シェアありがとう！

[TôNi Vibe Code @primitive_hd]

@yosendou GPTに挑戦したけど負けたわ、でもシェアしてくれてありがとう。

[TôNi Vibe Code @primitive_hd]

@Live_life_style 彼女、めっちゃエモいじゃん。

[TôNi Vibe Code @primitive_hd]

GPT Image Prompt:
Photorealistic casual iPhone-style vertical street photo of the exact same real woman from the active LoRA identity reference, with strict preservation of her full face and body identity before anything else: same recognizable facial geometry, eye spacing, eye shape structure, nose–lip–jaw relationship, oval face shape, cheek and chin structure, light natural skin tone, long dark straight hair identity, shoulder-to-head relationship, shoulder width, torso length, torso-to-leg balance, waist thickness, hip width, thigh volume, leg length ratio, body mass distribution, grounded adult height impression, and relaxed physical presence. Do not beautify, slim, elongate, reshape, or replace her body with a generic attractive version. The final subject must remain the exact LoRA woman, not a similar-looking substitute.

She is standing close to the camera on a muted ordinary urban street, torso leaning diagonally to one side with natural body weight and believable balance, shoulders uneven, head tilted strongly, one arm lowered near a foreground railing without forced posing. Her hair is blown loosely by wind across part of her face and over her shoulders, with imperfect strands and casual movement. Her expression stays subtle and alive in the wind-shifted moment: relaxed heavy eyelids, a brief camera-aware glance, softly parted lips, and a calm distracted look that matches the tilted head and leaning body. Preserve the source-prompt human moment; do not copy any blank LoRA-reference stiffness, dead-eyed stare, frozen mouth, mannequin neutrality, seductive influencer gaze, or commercial smile.

Preserve the outfit exactly in a realistic worn way: off-white cropped long-sleeve top with a wide neckline slipped off the shoulders, elastic lower band, lightweight slightly sheer sleeves, natural fabric wrinkles and tension from the leaning posture, low-rise faded light blue jeans sitting loosely at the hips, visible thin white string detail, and a silver chain shoulder strap running along one side. Clothing must follow gravity, body contact, and natural fabric compression without reshaping her reference body silhouette.

The background is an ordinary shaded city street with a parked vehicle, dark building façades, graffiti, road surface, railing, and practical urban clutter. Keep the environment physically believable, slightly messy, asymmetrical, and casually captured, with realistic human-to-environment scale, grounding, shadows, object contact, and spatial continuity. The foreground railing should feel physically present near her lowered arm, not floating or pasted in. Feet, lower body, clothing, shadows, and street surface must remain grounded and weight-aware if visible.

All expression, gesture, outfit, pose, camera behavior, lighting, realism treatment, and environmental details remain subordinate to the active LoRA identity reference. The final image must still be unmistakably the exact same LoRA subject in both face and full body identity, not a beautified replacement, not a fashion-model reinterpretation, not a slimmer or longer-legged version, and not a generic attractive woman matching the prompt.

Vertical handheld iPhone-style framing at close social-photo distance, slightly imperfect crop, mild wide-angle phone perspective, casual off-center composition, subtle handheld tilt, realistic smartphone edge distortion only where it does not alter her body identity. Subdued overcast daylight, shaded street illumination, compressed shadows, imperfect auto-exposure, no cinematic lighting, no dramatic color grading. Realistic smartphone optics with small-sensor depth behavior, softly compressed background, uneven sharpness, localized softness, slight denoise, mild compression artifacts, imperfect HDR reconstruction, natural skin texture, real hair softness, non-uniform detail recovery, and ordinary mobile-photo visual entropy.

Avoid cinematic composition, luxury editorial polish, influencer aesthetics, beauty-filter skin, fake HDR, over-clean rendering, DSLR bokeh, perfect symmetry, over-sharpening, plastic skin, porcelain smoothing, artificial facial reshaping, waist slimming, torso narrowing, hip narrowing, thigh reduction, leg elongation, hourglass enhancement, model-like posture, mannequin hands, fused fingers, broken wrists, floating limbs, disconnected shadows, fake railing contact, impossible street perspective, sterile environment, showroom cleanliness, and any smartphone angle that changes the LoRA reference body proportions.

[TôNi Vibe Code @primitive_hd]

GPT-image2 has been optimized for your reference character.
--prompt 👇--

[TôNi Vibe Code @primitive_hd]

@saniaspeaks_ thank for share!

[TôNi Vibe Code @primitive_hd]

@thangonton dụ API X căng lắm :D

[TôNi Vibe Code @primitive_hd]

Creativity in the AI space is limitless once you find the right tool. I'm down to share it with you.

[TôNi Vibe Code @primitive_hd]

Having tried countless image generation tools and even training my own custom LoRas, I have to say @GeminiApp and @NanoBanana hit different. The realism is unmatched. 🔥

[TôNi Vibe Code @primitive_hd]

@miratechtool @higgsfield Yeah, I'm on the same page as you :D

[TôNi Vibe Code @primitive_hd]

@DracoVibeCoding I think you should apply some tricks for te halter top like the reference charater to make it more effective :D