All updates

In this quick tutorial, Caleb shows you how to strip the music out of any clip using SAM Audio, Meta’s free sound isolation tool. That way, you get clean sound effects and can add your own music in your editor. It works on regular footage too, not just AI clips. Check. outa full…

The full AI filmmaking workflow behind Planet Hell: Seedance 2.5 on OpenArt, driven over MCP by Claude Code and Codex, Gemini 4 Argon as story editor and colorist in DaVinci Resolve, and After Effects for the fixes the AI couldn't make. A few days ago I released Planet Hell, the…

Manim supports precise, programmatic video generation, but a successfully rendered educational animation can still have visual defects, missing explanations, or incorrect content. Rendering does not directly identify the code changes needed to correct these visual failures, so…

EDGAR is a conditional diffusion framework with a fusion block and Mixture-of-Experts that refines degraded Gaussian head avatars by injecting self-supervised identity features, using refined multi-view renderings as pseudo-targets to optimize a single avatar.

Few-step autoregressive (AR) video diffusion models generate videos chunk by chunk and have made efficient video generation practical. However, further accelerating these models toward real-time generation remains challenging, as few-step distillation leaves little cross-step…

In this tutorial, we'll show you how to create a studio from anywhere in the world. All you need is audio, reference video, and you are good to go. This workflow is the future of video production. Check out the full breakdown here…

Google Deepmind is making Gemini Omni 1.2 Flash generally available. The video-generation model now creates clips up to 15 seconds long, can be edited step by step via conversation, and costs just $0.07 per second at 720p, 30 percent less than its predecessor. Users who draft in…

Text and image to video · 3–15 s · 720p, 1080p, 4K, 360p · 16:9 9:16 · audio · from $0.023/s on OpenRouter

Text "Gemini Introducing Gemini Omni 1.2 Flash" surroudned by images of a beehive, animals in conversation, a squid, and a woman walking down a street

In this video of ComfyUI Nodes Explained, you will learn how ComfyUI sets the size of your image: what the empty latent is, how width and height work, why the same seed gives a new image at a new size, why a bigger image is not always better, why 1080 becomes 1088, how aspect…

Reinforcement learning has become an effective approach for improving video generation, but its success depends heavily on reliable reward models. Existing methods either map videos directly to opaque scalar scores or generate free-form rationales that are not explicitly…

Diffusion models for video generation have achieved remarkable success, yet precise motion control under explicit user guidance remains challenging. Recent noise-warping methods introduce temporal correlations by warping the noise according to the user-provided motion signal…

Text and image to video · 3–10 s · 720p, 1080p, 4K, 360p · 16:9 9:16 · audio · from $0.034/s on OpenRouter

OpenAI is adding a GIF feature to ChatGPT. With the new Images 2.6 model, users can create animated GIFs from text prompts or photos and then adjust speed and individual frames. The model's image consistency is strong enough to keep characters recognizable across frames, making…

AI and vibe coding have changed game development forever. Every second game on Steam is now created with AI. And Itch.io has made a big move to remove AI Spam Games. Claude has limited the use of web coding for games. So what does all of that mean for the future of video games…

Adversarial training enables one- and few-step image and video generation, but conventional adversarial losses supervise critic values without directly specifying the gradients used to update the generator. We present NEXTGAN, which trains a scalar critic by regressing its input…

Embodied video world models predict scene changes caused by robot actions, yet generated object responses may remain inconsistent with task intent and contact dynamics. Critical responses in embodied scenes often concentrate in local regions and specific time intervals. Inspired…

Sparse attention accelerates few-step video diffusion transformers by computing a few key blocks exactly and compensating for the rest. However, existing sparse attention still faces key challenges, including identification overhead from finding critical blocks at every…

Identity-preserving video generation aims to synthesize high-quality and visually realistic videos from textual and visual conditions while faithfully maintaining the subject's identity across diverse motions. Prior methods have extensively introduced reference-guided control…

Digital human e-commerce video generation requires preserving product appearance, human identity, and overall video style during dynamic demonstrations. Although recent models support multiple reference images, their general conditioning schemes do not explicitly distinguish the…

LiveFoley improves streaming video-to-audio generation by using a trailing sliding window for visual alignment and expanded temporal denoising windows for audio quality with minimal latency.

Conversational video characters must generate video as fast as it plays, for one user at a time: at 24 fps, a sustained 166.7 ms per four-frame chunk at batch size one, with only a few chunks of buffering. We describe the system behind Runway Characters, which serves a…

Group Relative Policy Optimization (GRPO) has advanced generative model post-training in verifiable domains such as code and mathematics, but evaluating video quality, especially emotional expression, often depends on subjective aesthetics and has no uniquely correct target…

TurnWise improves streaming video understanding by assigning turn-level credit and balancing decision weights in group relative policy optimization.

In this episode, we test MiniMax H3 in ComfyUI with 25 free workflows, plus 2 bonus workflows. H3 is a video model that makes video with sound, from your images, videos and audio. We test them all, and see what H3 does well and where it struggles. Part 1, change your video: a…

Video generation has progressed from isolated clips to coherent short-form audiovisual sequences, and the bottleneck is shifting from rendering to semantic control. This report summarizes the observations and insights on multimodal understanding gained from successive…

Latent diffusion and flow matching models are ubiquitous in state-of-the-art generative video models. While highly effective, relying on pretrained autoencoders to compress the data into a lower-dimensional latent space also comes with drawbacks. First, training proceeds in two…

Three MiniMax H3 models, three prices. Here's when to use H3 Highspeed, H3 Lite, and H3.

RoboTryOn translates human demonstration videos into robot videos to train control policies without real robot demonstrations, improving success rates and reducing data collection costs.

DreamX leverages a pretrained video diffusion model to learn compact, appearance-invariant latent actions that enable cross-embodiment transfer and efficient policy learning.

PLANET HELL is an AI Sci-FI Short Film expanding on the original AI Film trailer made in Veo-3.1 This is an ongoing series about a prison planet where every inmate gets one bullet. This latest film was made with Seedance 2.5, GPT Image 2 and 2.5, Nano Banana and Midjourney, and…

Pose-driven human video diffusion animates a person from a single reference image and a target pose sequence, yet it struggles to preserve identity, rendering the face and garments unfaithfully as the pose departs from it. Personalization is the standard remedy, but its…

Autoregressive video diffusion models (AR-VDMs) enable real-time, long-horizon video generation but degrade rapidly once the inference horizon outruns the training horizon, due to compounding exposure bias. To stabilize long rollouts, recent methods heuristically adopt frame…

Reinforcement learning (RL) elevates joint audio-video generation, but optimizing heterogeneous, modality-specific audio and video rewards often introduces cross-modal interference. On-policy distillation (OPD) alleviates this issue by transferring the capabilities of…

Existing benchmarks for joint text-to-audio-video (T2AV) generation evaluate perceptual quality and audiovisual alignment, but balanced sound-source sam?pling and separate reporting by shot structure remain limited. This makes it dif?ficult to determine whether a specific sound…