Yesterday was my last day at @LumaLabsAI. Over the last three years, I had the privilege of helping drive the company's transition from 3D AI to video generation and native multimodal foundation models. I am grateful to have worked alongside an extraordinary group of researchers, and I look forward to seeing the next chapter of the company's story unfold.

Most researchers agree that autoregression is best when memory bandwidth is cheap and diffusion is best when FLOPS are cheap. They also admit the future of compute is all FLOPS because memory scaling is hard and scaling FLOPS is easy. So why not go all in on diffusion????

Exciting news: UNI-1.1-Max and UNI-1.1 debuts making @LumaLabsAI the #3 lab in the Image Arena across both Text-to-Image and Image Edit! These are versions released without agentic search. Text-to-Image Arena - UNI-1.1-Max #6 overall (1193), 12 points over MAI-Image-2 - UNI-1.1 #7 overall (1190), 13 points over Reve-v1.5 Multi-Image Edit Arena - UNI-1.1-Max #7 overall (1315), 21 points over Seedream 4.5 - UNI-1.1 #8 overall, (1298) Single-Image Edit Arena - UNI-1.1-Max #7 overall (1337) - UNI-1.1 #11 overall, (1310) on par with Grok-Imagine-Image (20260207) Congratulations to @LumaLabsAI on this solid performance!

personalization is back. most systems still fake it. we went back to our paper from two years ago, rebuilt it from the ground up, applied newer techniques, and replaced the base model with a flow-matching transformer. the result: our pipeline now beats all SOTA personalization approaches on FT-Arena. introducing Person2Person Diffusion 2. code and weights are out now (MIT, commercial use allowed). okaris.github.io/p2p-diffusi…

终于有可以和 Nanobanana Pro 打一打的图像模型了。 @LumaLabsAI 凌晨发布的 Uni-1 图像模型可以画条漫了，指定的中文文字基本不出错。 Prompt in Alt! ▶ 模型详细说明：lumalabs.ai/uni-1

Uni-1 is here! A new kind of model that thinks and generates pixels simultaneously. Less artificial. More intelligent.

Uni-1 is here! A new kind of model that thinks and generates pixels simultaneously. Less artificial. More intelligent.

This implementation came with the Terminal Velocity Matching paper (arxiv.org/abs/2511.19797): github.com/lumalabs/tvm/blob…

We raised $165M at a $1.15B valuation to stop doing demos. 2026 is about 1) deployment and 2) research. We will start shipping Memo with our new frontier models in a few months. Our series-B is led by Coatue, with Thomas Laffont joining the board. ->🧵

Ana da Armas Gemini Nano Banana Pro Prompt: { "image_generation_request": { "framing_and_composition": { "shot_type": "Medium shot", "orientation": "Vertical", "composition": "Mirror selfie, subject centered", "camera_in_shot": "Smartphone visible in reflection, held at chest height", "perspective": "Candid night out" }, "subject_identity": { "reference_name": "Ana de Armas (young)", "skin_tone": "Pale, porcelain", "facial_structure": { "jawline": "Sharp", "cheekbones": "High", "eyes": "Large, almond-shaped, green-hazel", "nose": "Refined, slim" }, "identity_fidelity": "100% face preservation, zero alterations to unique features" }, "expression_and_pose": { "expression": "Sultry, neutral, composed", "gaze": "Directly into the reflected camera lens", "head_pose": "Slightly tilted", "body_language": "Confident, heavy coat draped loosely to reveal shoulder", "hand_detail": "Right hand holding phone, index finger extended, red manicure" }, "styling_details": { "makeup": { "eyes": "Sharp black winged eyeliner, smoked-out lower lash line, heavy volume mascara", "eyebrows": "Well-defined, natural dark", "lips": "Soft matte rose-toned, slightly overlined", "contour": "Subtle, cheekbone-focused" }, "hair": { "color": "Dark espresso", "style": "Long, thick, wavy, voluminous", "texture": "Messy-chic, healthy sheen", "parting": "Slightly off-center" }, "outfit": { "base_layer": "Chocolate-brown metallic one-shoulder bodycon dress with ruching", "outerwear": "Heavy, brown faux-fur mink-style coat, worn off-shoulder" }, "accessories": { "jewelry": "Large, chunky vintage-style gold earrings", "nails": "Long, pointed acrylics, glossy cherry red", "phone_case": "Modern smartphone in a dark case" } }, "physical_attributes": { "silhouette": "Slim, toned hourglass", "details": "Defined collarbones, slender shoulder, narrow waist, feminine curves" }, "environment_and_lighting": { "setting": "Dark minimalist luxury interior (high-end club/lounge)", "background_elements": "Horizontal black tiled walls or polished dark wood panels", "lighting_type": "Hard mirror flash", "lighting_effects": "Central starburst flare, high-contrast highlights, deep shadows", "film_texture": "Subtle film grain, low-light mobile photography look" }, "technical_specifications": { "aesthetic": "Shot on iPhone, ultra-realistic", "resolution": "8k, high-resolution textures, raw photo quality", "artifacts": "Slight motion blur, natural digital noise", "focus": "Sharp focus on facial features despite flash flare" }, "mood_and_style": { "theme": "It-girl nightlife, edgy, glamorous, expensive", "atmosphere": "Intimate, performative, high-fashion vanity" }, "strict_constraints": { "face_integrity": "Do not alter eye shape, lip shape, or facial proportions", "lighting_retention": "Maintain flash flare in mirror", "prohibited_elements": "No smiling", "aspect_ratio": "3:4" } } }