AI Video2026
Generates audio-driven avatar videos from text, images, or audio inputs with production-grade stability (accurate lip sync, identity consistency) and an 8-step distillation inference mode for faster serving; suitable for broadcasting, virtual hosts, animation, and multi-person scenarios.
Synthesizes high-quality targets for real-world image restoration by using multimodal foundation models (MFMs) to convert real low-quality photos into HQ references. Provides GGT-100K (103,707 LQ–HQ training pairs + 500 test pairs) with multi-stage quality control and demonstrates consistent generalization gains for a range of restoration models, especially for finetuning generative restorers.
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 Model2026
Text-to-image model packaged for Diffusers that uses fp8 quantization to lower memory and speed up inference. Delivered as a safetensors checkpoint on Hugging Face with an Ideogram pipeline; created May 30, 2026 — license unspecified.
AI Model2026
NF4-quantized text-to-image diffusion model released as safetensors and compatible with the Diffusers Ideogram4Pipeline — optimized for lower-memory local inference and faster deployments while preserving the original model's text-to-image capabilities.
AI Model2026
Fine-tuned Hugging Face image-generation model that biases Ideogram-style prompts toward photorealistic outputs. Emphasizes natural lighting and realistic materials to reduce prompt tweaking; license not specified.
Adds interleaved text–image generation to existing image generators via a multi-agent pipeline: a planner sequences stepwise instructions, a critic detects and refines failures, and single-step RL (GRPO) reinforces per-step corrections—suited for visual narratives and embodied guidance.
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 Dataset2026
Provides ~2 million instruction-aligned video-edit pairs for training and evaluating instruction-based video editing and generation models. Covers multi-task and structural edits (e.g., camera/subject movement), produced via a synthesis pipeline with progressive filtering; licensed CC BY-NC-4.0.
AI Image2026
Provides 1,503 Krea 2 style LoRAs (original safetensors + ComfyUI builds) trained on fal.ai, each with a short trigger phrase and downloadable weights for quick style transfer or further retraining.
AI Model2026
Enhances KREA-2 Turbo image generations with an aesthetic LoRA trained on a curated 100-image dataset to add stronger composition, richer lighting, softer atmosphere and refined textures; trigger with --preview for art-directed, cinematic outputs in text-to-image pipelines.
AI Video Papers2026
Autoregressively synthesizes long-horizon, playable video worlds conditioned on current state and user actions for real-time interaction. Ships as an open-source, full-stack framework covering data preparation, model architectures, training, inference acceleration, and deployment for interactive generative worlds.