AI Model2026
Unifies multimodal image understanding, text-to-image generation, and instruction-based editing in a single diffusion LLM using a Mixture-of-Experts backbone, SigLIP-VQ discrete tokenizer, and a distilled diffusion decoder enabling fast (8-step) decoding; full-generation needs ~47GB GPU RAM.
AI Model2026
End-to-end multimodal model for native text↔image understanding, interleaved image-text generation, and image editing. Uses the NEO-Unify MoT architecture to avoid separate visual encoders/VAE. Suited for multimodal prototyping, demos, and research (Apache‑2.0).
AI Dataset2026
Provides 104.9M curated image–text pairs with precomputed embeddings, structured annotations and pre-encoded VAE latents for text-to-image pretraining and retrieval. Combines filtered web sources and synthetic samples with multi-model re-captioning, deduplication and safety filters; Apache-2.0.
AI Audio2026
Converts text into natural-sounding speech locally using compact ONNX TTS assets. Optimized for CPU/edge inference (~99M params) with support for 31 languages, expression tags (e.g., <laugh>), and improved stability versus Supertonic 2 — suitable for on-device multilingual TTS.
AI Model2026
Distilled dev checkpoint of an image foundation model that natively unifies raw pixels and text tokens for text-to-image, image editing, long-text rendering, and subject-driven personalization at up to 2048×2048. The Dev variant targets faster (28-step) inference for iterative use and research.
AI Image2026
Generates and edits high-resolution images (up to 2048×2048) from text and reference images, plus subject-driven personalization. Implements a pixel-level unified transformer that encodes raw pixels and text in one token space and includes a reasoning-driven prompt agent for layout and text rendering.
AI Model2026
A ternary-weight (~1.58-bit) 4B text-to-image diffusion transformer optimized for NVIDIA GPUs using Gemlite INT2 and HQQ; it reduces the transformer to ~1.21 GB (4.55 GB CUDA payload) and targets 1024×1024 generation with a 4-step FlowMatch-Euler sampler.
Generates synchronized, streaming spatial audio from panoramic video and text prompts using a causal autoregressive diffusion transformer. Combines Spatial Video-Audio Contrastive (SVAC) alignment and online direct preference optimization (ODPO) to improve spatial perception, plus an automated annotation pipeline and public demos.
AI Dataset2026
Contains a sanitized Claude Code (Fable 5) JSONL transcript of a session that procedurally built a Boeing 747 in Three.js, including assistant messages, tool calls, and base64 screenshots — useful for studying agent trace, tool use, and vision self‑verification workflows.
AI Image2026
Provides ComfyUI-ready repackaged checkpoints of the Krea 2 image model family for local text-to-image workflows. Includes RAW (undistilled base for fine-tuning and LoRA training) and Turbo (8-step distilled checkpoint for fast inference), using a Qwen Image VAE and Qwen3‑VL encoder.
AI Video2026
Converts low‑poly 3D viewport or game/CG renders into photorealistic cinematic video while preserving the input's composition, camera motion and layout; offers Light and Strong LoRA variants to trade fidelity for aggressive photorealism.
AI Image2026
Applies or repositions directional sunlight in outdoor images by using a LoRA trained for Flux2Klein 9B to match a reference sun elevation and rotation. Workflow uses an overcast intermediate and a sphere (ball) reference; includes a ComfyUI node and Blender scene for rendering the reference.