Elevate your ComfyUI video outputs this fall. 🚀 Launching... with RTX Spark, RTX Video Frame Generation arrives as a ComfyUI node and Python wheel. Multiply frame rates to turn choppy 15-20 fps outputs into smooth, high-quality playback.show more

Turn a simple idea into a storyboard, then generate... the video with Seedance 2.0. This ComfyUI workflow uses LLMs to structure prompts into storyboard-ready scenes that define how the video should play out. The storyboard can be paired with reference images and sent directly into Seedance for video generation. To try this workflow, link below 👇show more

Another local video created with MiniMax H3 on DGX... Spark, it took forever 1 hours and 20 minutes 😱 For: - 1280x736 (16:9) - 15 seconds - DGX Spark - ComfyUI Template Text to Video Thanks MiniMax (official) for this model!show more

Create a storyboard, feed it into Seedance 2.0, and... let an LLM analyze the storyboard to generate better prompts. A practical way to turn visual planning into more controlled and consistent video generation. To try this workflow, link below 👇show more

🧮Turn single image into a custom LoRA model in... one click ! Should work for character and product ! This ComfyUI workflow: → Uses Gemini AI to generate 20 diverse prompts from your image → Creates 20 consistent variations with FLUX.1 Kontext → Automatically builds the dataset + trains the LoRA One image in → Trained LoRA out 🎯 #ComfyUI #LoRA #AIArt #FLUX #AutomatedAI ComfyUI BlackForestLabsAI - Unofficial 🔗 Check it out: This workflow was made for the hackathon organized by ComfyUI in SF yesterdayshow more

Gen-3 Alpha Image to Video now supports using an... image as either the first or last frame of your video generation. This feature can be used on its own or combined with a text prompt for additional guidance. All examples below demonstrate using an image as the last frame. (1/5)show more

Luxury meets cinematic precision ✨ From smooth skin tones... to perfect light and motion, every frame feels like a high-end brand commercial. Creating premium fragrance ads has never been this effortless. Turn your vision into a cinematic masterpiece Hailuo AI-MiniMax Hub #MiniMaxH3show more

Vidu Q2 pro is now live on Pollo AI.... Unlock next-level video generation and editing capabilities. Welcome Vidu Q2 pro Reference-to-Video: Achieve precise control over your visuals. Turn reference footage into consistent, high-quality video. AI Video Editing: Edit, modify, and refine your videos with professional-grade accuracy.show more

Video creation just changed forever 🎬🤯 With Cinema Studio... by Higgsfield AI 🧩, you start from one cinematic frame and turn it into a full film-quality video. Camera moves. Mood. Lighting. Storytelling. No timelines. No keyframes. No pain. This feels less like “AI video” and more like directing a movie. Try it yourself →show more

🎥 Video generation is hitting the memory wall. As... videos get longer, the KV cache quietly explodes — and long-horizon consistency starts to break. We built Quant VideoGen: a training-free KV cache compression method for auto-regressive video diffusion. Instead of storing every KV in high precision, QVG exploits video’s spatiotemporal redundancy with semantic-aware smoothing + progressive residual quantization. 🚀 Up to 7× KV memory reduction ⚡ <4% overhead ✅ Strong long-video quality 🕹️ Deploy HYWorldPlay on your own RTX 5090 locally KV compression is becoming a core scaling primitive — not just for LLMs, but for video generation too. Paper: Code: (1/5)show more

🎉 Congrats to MiniMax (official) on releasing the open... weights for MiniMax H3! Day-0 support in vLLM-Omni! One model reads text, images, video, and audio as a single context and returns video with native stereo audio. Text-to-video, first/last-frame, and multi-reference generation, 4 to 15 seconds at up to 2K and 24 FPS. The MP4 comes back with H.264 video and a synchronized stereo track already muxed in. It serves over the OpenAI-compatible /v1/videos endpoint, synchronous or async with job polling. 🔊 The video ⬇️ was made with H3, served on vLLM-Omni.show more

Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation paper page:... Large text-to-image diffusion models have exhibited impressive proficiency in generating high-quality images. However, when applying these models to video domain, ensuring temporal consistency across video frames remains a formidable challenge. This paper proposes a novel zero-shot text-guided video-to-video translation framework to adapt image models to videos. The framework includes two parts: key frame translation and full video translation. The first part uses an adapted diffusion model to generate key frames, with hierarchical cross-frame constraints applied to enforce coherence in shapes, textures and colors. The second part propagates the key frames to other frames with temporal-aware patch matching and frame blending. Our framework achieves global style and local texture temporal consistency at a low cost (without re-training or optimization). The adaptation is compatible with existing image diffusion techniques, allowing our framework to take advantage of them, such as customizing a specific subject with LoRA, and introducing extra spatial guidance with ControlNet. Extensive experimental results demonstrate the effectiveness of our proposed framework over existing methods in rendering high-quality and temporally-coherent videos.show more

She pulls in $110,000 a month from 15 second... bedroom dance clips. Brands are already dropping real influencers to sign her instead. Luna isn't real. She's a fully synthetic model. Built by an 19 year old student in Canada. Runs the whole thing from his bedroom with Python and an RTX card. The hair physics come from a custom video diffusion layer, frame by frame. The lighting and shadows are rendered so she sits naturally in the room, not pasted in. A fully automated pipeline pulls trending audio, maps her onto it, and posts across 40+ accounts. He never touches a clip. No contracts. No travel. No days off. 40 million views a week. Zero overhead. The wall poster in the background is the only real thing left in the frame.show more

Nano Banana + Linah AI + Markdown prompting is... next-level All of these UGC ads was built entirely with AI no creators, no editors. And the secret? Structured Markdown prompts. They turn a generic input into a brand-consistent, high-precision video every single time. Perfect for DTC founders and creative teams who need ads that actually match their brand guidelines. Instead of writing long, messy prompts and praying for good results… Markdown prompting gives you predictable, repeatable video outputs. Your prompt precision skyrockets → with organized sections for: Camera angles Brand elements Lighting specs Scene transitions Here’s what you get with Markdown + Linah: → Clear creative direction → Consistent UGC-style video ads → Way higher coherence across outputs → No “creative lottery” problem → Scalable video generation that matches your brand The result? Ads you can trust → built at scale, with zero human creators. Want the full Markdown templates we use with Linah? Comment “SYSTEM” + like this post, and I’ll DM them over. (must be following)show more

Bring your videos to life with Akool’s Effect Enhancer.... ✨ Turn ordinary footage into dynamic, eye-catching content in seconds. With smarter visual effects and enhanced motion details, you can instantly elevate your videos without complex editing. Whether you're creating marketing content, storytelling videos, or social media clips, Effect Enhancer helps you add more depth, energy, and polish to every frame. Create smoother visuals. Add stronger impact. Make every video stand out with Akool.show more

A New Era with V3🪄 V3's new engine introduces... significant advancements in output generation. Unlike V2, where the multi-model system processed prompts to produce a single output, V3 is designed to generate multiple outputs and logically link them together. This enhancement effectively removes limitations on output size, enabling more complex and expansive results. Key Features Seamless Multi-Output Generation: V3 has been trained to generate separate outputs and connect them logically. This advancement ensures that there are no longer any limitations on output size. Intelligent Image Creation: V3 improves image generation with better tools, allowing the AI to create as many images as needed and place them within the project’s context. It supports various formats like PNG, JPEG, SVG, and GLB. Web-Integrated Intelligence: V3 can now search the web for documentation and data, providing real-time context and up-to-date references. For example, if you run a restaurant and want to update your website, simply ask Alchemist AI to “generate this website in a more modern style,” and it will update all content accordingly. Improved Creativity and Output Quality: V3's creative capacity has significantly increased. Simple prompts now generate more complete and refined results, with the system efficiently combining multiple elements into cohesive outputs.show more

VEO 3 + "canvas prompting" is soooo good 🤯... These AG1, Jones Road Beauty, & Ridge product videos were created with just 2 uploaded images each. And it's all about the visual context. This canvas prompting technique will take any product photo + model shot... And turn it into cinema-quality UGC videos with solid brand alignment. Perfect for e-comm operators, creative strategists & agencies. Just upload your canvas images + get brand-ready videos with top-notch realism. Here's what canvas prompting gives you: → visual context instead of text descriptions → near-perfect product-model integration → consistent brand-ready video outputs → way higher realism scores Now you've got predictable UGC generation instead of random AI outputs. Again, AI video isn't perfect yet ... but it will be VERY soon. Want the full canvas prompt templates + Loom video walk through? Like + comment "CANVAS" and I'll send it over (must be following so I can DM)show more

STEPS: - Write a simple 10-15 second story idea.... - Use ChatGPT to convert the story into a professional director-level storyboard with strict continuity between every frame. - Generate the storyboard images. - Upload the completed storyboard back into ChatGPT. - Ask ChatGPT to analyze the storyboard and convert every panel into a single cinematic Seedance 2.0 video prompt - Upload the storyboard + generated video prompt to Seedance 2.0. - Generate the final film-quality animated sequence. The biggest improvement came from treating the storyboard as the source of truth and having AI act like a film director rather than a prompt writer.show more

Rumor has it Dreamina is launching the Dreamina Seedance... 2.0 mini on June 15. From what I've heard, Dreamina is preparing a new member of the Seedance family. Dreamina Seedance 2.0 mini could deliver quality close to Seedance 2.0 while being significantly more affordable, making advanced AI video generation more accessible to creators. If the rumors are true, this could be a major win for people who love Seedance but find video generation costs difficult to scale. The bigger trend is clear: high-quality video generation keeps getting cheaper, opening the door for more creators, filmmakers, marketers, and builders to bring their ideas to life. Looking forward to seeing what Dreamina announces next. #dreamina #seedance #dreaminaseedance2minishow more

Okay so someone suggested trying WAN 2.1, a video... model that supports LoRas So I trained a LoRa of myself and it works really really well, super high resemblance, obviously you can't use a Flux LoRa but similar effect, it just works great A few annoying things: - WAN 2.1 FPS is like 16 fps, so jittery, so you have to run it through an interpolator to add another frame to get close to 30fps - Limited to about 5 seconds clips (but that seems to be a bug, see "Bug Fix I2V Frame Count Hardcoded to 81 (!!) and Optional Batch Mode") Here it is with WAN LoRa + my ElevenLabs voice + 2x interpolation + boomerang loop to make it from 5 into a 10 second video Very big potential this is the working solution if I can make this pipeline work 🤯🤯🤯🤯🤯🤯show more

xAI isn't playing around. They just released the Grok... Imagine API, a unified video + image generation toolkit, and it's already sitting at #1 on the Artificial Analysis Video Arena for both Text-to-Video AND Image-to-Video. It's beating: ● Google's Veo 3.1 & Veo 3 ● OpenAI's Sora 2 ● Runway Gen-4.5 ● Kling 2.5 Turbo The Numbers Don't Lie: ● 64.1% win rate against Runway Aleph in blind human evaluations ● 57% win rate against Kling o1 ● Best-in-class latency. Sub-20 second generation for 720p, 8-second videos. (up to 15-second video) ● Native audio generation baked right into video output (dialogue, music, sound effects, all synced) What Makes It Different It's built for real creative workflows: ✅ Text-to-video AND image-to-video in one API ✅ Video editing with prompt-based controls (add/remove objects, restyle scenes) ✅ Camera controls: zoom, pan, timelapse, pull-back ✅ Style transfers: cyberpunk, watercolor, anime, you name it ✅ Performance animation: map your movements onto characters ✅ Native audio-video sync (no post-production needed) Why the focus on speed and cost? The partner feedback that shaped this: "Quality alone isn't enough if latency and cost make iteration painful." So xAI optimized for all three. Speed. Cost. Quality. Already Integrated With: ● fal. ai ● ComfyUI ● InVideo ● Flora ● HeyGen xAI went from underdog to chart-topper. The Grok Imagine API is fast, affordable, and genuinely production-ready. If you're building anything with AI video, this just became the one to beat.show more