#Video

AINunchux runs MiniMax-H3 on AMD MI355X GPUs, generating 5 seconds of video in 1.3 seconds with up to 26.7x faster inference than SGLang on 8 GPUs. The stack supports streaming generation, letting users change prompts while the video plays. Free access to MiniMax-H3 through Nunchux is coming soon, with a waitlist open.

AIKling AI's blog identifies six limitations of current AI video generation, including temporal consistency, character consistency across shots, unrealistic physics, long-form generation, fine details and text, and prompt control. It recommends workarounds such as reference images, shorter single-action clips, storyboards, and adding text or logos in post. The article says Kling VIDEO 3.0 and VIDEO 3.0 Omni offer reference-based subject consistency to help reduce these problems.

AIGemini 3.8 Flash TTS and Flash-Lite TTS are now available in the Gemini API and AI Studio, with a new feature to replicate your own voice or create one from a sentence. The guide shows recording two clips, one of 15-20 seconds of natural speech and one reading a required consent sentence, then creating a reusable voice ID. It also explains that input text is now spoken word for word, so delivery belongs in speech_metadata.style and short sounds inline.

AIBlack Forest Labs points readers to a dedicated page on its website describing the FLUX 3 action model. The post itself provides no specifics about the model's capabilities, benchmarks, or availability.

AIGoogle Labs released six new Google Flow Tools built by creatives across architecture, sound design, and digital content, including Mondo Sónico, CaptionCast, ThumbnailForge, Surface, CollageMotion Pro, and SwissFlow Studio. Each tool targets a specific workflow, such as generating synchronized audio stems, transcribing and styling captions, or producing animated collages from text prompts. Users can try the tools, duplicate and remix them, or build their own by describing a task in Google Flow.

AIComfy Router is now live on the Comfy Developer Platform, giving developers one API to call frontier image, video, 3D, and audio models. Day one models include Seedance 2.5, MiniMax H3, Nano Banana Pro, GPT Image 2, Kling, and Black Forest Labs, and the provider for each job is selectable. Requests fail rather than silently switching providers, and inputs and outputs are deleted after 24 hours.

Why it matters: The post shows how one API key and a provider parameter let developers swap routes for media models without rewriting calls, with failed requests reporting the provider.

AIKarl's AI Watts (@aiwarts) has open-sourced Awesome Seedance on GitHub, a collection of AI video prompts. It includes 463 cases traced to original posts, 264 cross-model retest runs with public verdicts, 25 copy-ready templates, and 60 installable AI-video Skills.

AIThe author compiled 436 AI videos made with Seedance into a prompt collection and a Skill, now available on GitHub as awesome-seedance. The post asks GitHub users to star the repository to help it reach a thousand stars in a day, and notes the X post has about 400,000 reads.

AIGoogle Flow now has more than 25 million people using it every month to create ideas, stories, and projects. Google is continuing to offer 50 additional daily credits to all users.

AIComfyUI's update makes the MiniMax H3 video VAE encode up to about 2.2x faster and decode 1.4-2.7x faster, cutting a 1344x768, 129-frame round trip on an RTX 5090 from 24.3 to 12.7 seconds. The gains come from a fused encoder kernel enabled by default, fp16 accumulation support in a custom convolution, and an int8 decoder, and the source says the changes are visually lossless to the eye. Users need ComfyUI v0.36.0 or above, and the int8 VAE file is a drop-in replacement for the standard one.

AIA developer connected a Raspberry Pi Zero W2 with a webcam and ambient microphone to MiniCPM-o 4.5, an open-source model running locally on a PC. The setup streams audio and video in real time with full-duplex interaction and no cloud APIs.

AIA community developer integrated the Jev method into MiniMax H3 to sparsify attention, deciding per layer which parts to keep. On an RTX 4070, video generation time dropped from 6 min 7 sec to 3 min 34 sec, a 41.7% reduction. The post notes that Jev selected sparsity rates of 1%, 3%, 5%, and 10% across 49 layers in 4-step generation.

AIA Wan 3.0 feature can change a video's camera angle while keeping the exact same action from the original clip, according to a shared example. The main post only thanks the author for sharing a prompt, so no further details are confirmed.

AIA creator made a game-style video with Wan 3.0 and Nadou Pro, highlighting its quality and especially the consistency between scenes. The main post jokingly suggests the creator may have hit record mid-game, implying the clip is a real gameplay capture.

AIWan (@Alibaba_Wan) promoted its motion control and animation capabilities with a short post, calling the results solid. The post includes no specifications, benchmarks, or availability details. A related Wan 3.0 experiment shared by another account shows a combat sport motion demonstration.

AIAlibaba's Wan account replied to a post praising Wan 3.0, which was shown producing a video in a Higgsfield demo alongside a GPT Image 2.5 "Sunburst" image. The main post itself only says "nice work!" and gives no specs, benchmarks, or availability details.

AIA creator submitted a second entry to the OpenArt AI Ad Awards, made exclusively with Wan 3.0. The post presents the work as a genre-shifting story that showcases the model's range across styles.

AIHailuo AI's post suggests that a single 3x3 storyboard image can be converted into a video using the MiniMax H3 Max r2v model at 480p for 15 seconds. The quoted post describes settings with Quality prompt tuning and standard reference strength, and asks for a 2D animation with panel-to-panel cuts while excluding multiple panels and BGM.

AIWan 3.0's output resolution has been raised by one level, according to a quoted post from @roco_kn_roco. The main post from Wan (@Alibaba_Wan) contains only emoji and adds no further details.

AIWan, the account associated with Qwen, shares a link to video results on the OpenArt arena page. The post provides no model names, scores, or other specific figures.

AIvLLM now supports NVIDIA hardware video decoding through PyNvVideoCodec, moving video decoding off the CPU so multi-GPU video captioning can scale to 8 GPUs. In benchmarks on 8xH100 GPUs, GPU-based decoding provides more than double the throughput of the CPU-based decoder for Qwen/Qwen3-VL-8B-Instruct with 8 single-GPU vLLM replicas. The functionality is included in standard CUDA vLLM releases, and PyNvVideoCodec==2.0.4 is required for custom installations.

AIReplicate invites users to try Pruna AI's p-video-2-pro model at the linked Replicate page. The post offers no further details on capabilities, pricing, or performance.