A focused feed of models, agents, research and open-source releases for people building with AI.
Community release puts MiniMax H3 on consumer GPUs via pruned GGUF quantizations. Checkpoints range from 8.9 GB (Q3_K_M, ~12 GB VRAM) up to 21.6 GB (Q8_0 reference). Two modes shipped: FL2VA first/last-frame-to-video-audio and Ref2VA omni-reference generation.
Instagram Live ingest on iOS and Android now runs on Media over QUIC , replacing Meta's in-house RUSH protocol. MoQ is an emerging IETF standard co-developed with Google, Akamai, Cisco, Cloudflare, and academia.
Open source local AI film studio for Mac and NVIDIA DGX Spark, Apache 2.0 licensed on GitHub Runs Qwen-Image-2.1, FLUX3-K, MOSS-Image, MiniMax H3, FastH3, Fish Audio Drama 3, MiniMax Music 3 Custom TensorFold Zig runtime with int8 kernels for Metal and CUDA GB10 tensor cores FastH3 renders 5s
Pika Labs released Pika H3 Flex , open LoRA adapters that run MiniMax H3 in 6 sampling steps instead of 50. Two adapters: FL2VA for text and first/last frame, Ref2VA for up to 12 reference files (images, video, audio).
Pika Labs released Pika H3 Flex , open LoRA adapters on top of MiniMax-H3 for video plus audio generation. Six-step sampling schedule generates a 15-second clip in roughly seven seconds on an H100.
Runway Agent now opens files, runs code, and browses the web beyond pure generation Produces brand launch kits, product shots, ad variations, and motion graphics from references Writes Python code when pixel-exact placement, margins, or typography are required Builds on prior Agent additions:
Openjutsu is an open-source, local Higgsfield Genjutsu alternative for character and object swaps in video. Built on ComfyUI with MiniMax H3 for video, SAM 3.1 for tracking, Qwen3-VL 8B for prompting.
Utopai X now supports image-to-video and ranks #2 on AA-Video-I2V v2.1 , behind Dreamina Seedance 2.5. Only model in the top 2 on both AA-Video-T2V v2.1 and AA-Video-I2V v2.1. Post-trained on MiniMax H3; beats base H3 (768p), Hyperflow H3, and MiniMax H3 Max on I2V.
KAIST's L3G-World generates explorable 3D worlds at 9 FPS from a single image. Each 3D Gaussian stores a VAE latent, rendering directly into the diffusion model's conditioning space. Memory grows with scene extent, not stream length, keeping GPU use flat during long exploration.
Pika released Pika H3 Flex , an open-weight video+audio model post-trained on MiniMax H3. Generates 15-second clips with soundtrack in as little as 7 seconds using a custom 6-step sampling schedule.
Alibaba's Wan team released Wan-Animate-2 , an end-to-end character animation model with native ComfyUI support . No pose extraction or skeleton preprocessing: the driving video goes straight into a redesigned Diffusion Transformer.
Runway launched Character Swap inside App Studio for recasting video characters or locations Preserves original motion using depth-map guided keyframes plus Seedance 2.5 Supports audio transfer or full audio swap to match the new scene Replace people or settings from a reference image or text
Liquid AI's LFM3 family puts six specialized 2B models on one tri-hybrid backbone, with vision, audio, and decision variants that fine-tune on a single GPU.
Artificial Analysis just rolled out AA-Video-I2V v2.1, a 1080p image-to-video benchmark with 58,000+ blind human votes across 10 use cases and 10 capabilities.
Google DeepMind's new world model streams photorealistic, playable 3D environments with native audio, live physics, and Gemini-driven reasoning in real time.
QuantStack's GGUF conversion of Wan2.2-I2V-A14B shrinks a 27B Mixture-of-Experts video model into quantizations that fit on consumer GPUs through ComfyUI.
Tencent Hunyuan open-sourced Hy-Nomas , an 8B interactive video world model under Apache 2.0. Supports free-form multi-turn text prompts and continuous camera control across autoregressive video segments. Outputs 720p at 24 fps, up to 60 seconds, distilled to eight denoising steps.
Runway's App Studio lets anyone describe a creative tool in plain language and get a working app wired to its image, video and audio models.
An open-source agent skill turns one photo into a finished AI talking-head video, with lip-sync, voice unification, and 48 packaging components.
DeepBeepMeep's repack of MiniMax's open-weight H3 video+audio model lands with GGUF quants and new 3-step accelerator LoRAs that make it run on modest GPUs.
NVIDIA expands Cosmos with data factory blueprints, training recipes and faster inference, with Porsche, Mercedes-Benz, Siemens and others building on top.
Tencent's Hunyuan team released Hy-Nomas, an open source interactive video world model with text and camera control that runs on a single RTX 4090.
Alibaba's open-source video model lands in ComfyUI as a single repackaged bundle, crossing 4.2 million downloads with workflows for text, image, and control-driven generation.
A community LoRA for MiniMax-H3 tackles the physics glitches that still plague image-to-video, cutting duplicated objects, clipping, and broken motion.
No stories match these filters.
