Seedance 2.0 is a new AI video model from the Dreamina/CapCut side of ByteDance that’s focused on one thing most video models struggle with consistency across shots Instead of only text-to-video, it supports multimodal references • text • images • video clips • audio clips Dreamina says you can stack up to 12 clips in one project (9 images, 3 videos, 3 audio) and video/audio refs can be up to 15 seconds so you can guide the model with real examples, not vibes What this unlocks for creators • the same character staying stable across multiple shots • smoother scene transitions and camera switches • better audio + visuals lining up like an edited sequence Check out the video I've attached👇

Curious what everyone here is actually using day to day There are a lot of tools now, but most people tend to rely on just one or two as their main workflow. Vote below for the one you use the most at the moment:

Pomelli is an experimental AI tool focused on marketing and brand creation Instead of just generating random images or text, it first analyses a business or brand — things like visual style, tone, colours and messaging — and builds a kind of “brand profile”. From there, it can generate campaign ideas, social visuals, and marketing assets that actually stay consistent with that identity The interesting part is that it’s less about single prompts and more about AI understanding a brand over time, then creating content that fits automatically It’s still early and experimental, and depending on your location it might not be available yet, but it’s a good example of where AI tools are heading — from generation tools to creative systems https://labs.google.com/pomelli/about/ Worth checking out if you’re interested in AI + marketing workflows or brand consistency

Tested Kling 3.0 and honestly — this looks like a proper movie scene. The lighting, motion, and camera behaviour feel professional rather than “AI-generated” What stands out most: - Natural movement and pacing - Cinematic camera motion - Realistic lighting and depth - Scenes that feel directed, not generated This is where AI video starts becoming usable for real social content, ads, and storytelling — not just experiments Right now it’s accessible through Higgsfield, which is useful because you get access to multiple models (Kling, Veo 3.1 and others) in one workflow instead of jumping between tools. Check out the clip attached Prompt used 👇 Shot 1: A profile medium shot of a woman in a dark coat standing under an overhang during a rainstorm in a city. She lights a cigarette with a lighter, the orange flame illuminating her face against the cold, blue architectural background of a city street. Shot 2: A rapid, blurred tracking shot following a motorcycle speeding past old brick buildings. The camera is low and shaky, capturing the sense of extreme speed. Shot 3: A low-angle ground shot as a motorcycle speeds through a narrow alley. Small explosions and debris burst from the sides of the buildings as the bike passes, filling the air with dust and smoke. Shot 4: A close-up, low-angle shot from the rear of the motorcycle, focusing on the rider’s boot and the mechanical chain as they accelerate. In the background, a large fireball explosion erupts on the city street. Shot 5: A wide shot of two motorcyclists in helmets and leather jackets weaving through city traffic. Small fire bursts erupt from manholes and the pavement around them as they flee through heavy smoke. Shot 6: A dramatic wide shot of a motorcyclist driving directly toward the camera. Behind them, a massive explosion occurs, causing a large portion of a building facade to collapse in a shower of sparks, fire, and heavy gray smoke.

Simple prompt structure for generating clean, commercial-quality product images that look like real brand photography Designed to keep lighting natural, materials realistic, and packaging sharp while avoiding the typical AI look Works well for food, drinks, supplements, and consumer products where realism and clarity matter most The Prompt👇 Premium minimalist product photography. A [BRAND] [PRODUCT] featuring [PACKAGING/LOGO DETAILS] placed at the center of the frame. The product rests on [SURFACE] surrounded by [RELEVANT PROPS]. Clean matte [COLOR] background with subtle gradient. Soft diffused lighting with gentle rim light creates a luminous glow highlighting [KEY FEATURES]. Sharp focus, high clarity, realistic textures, luxury advertising style, modern branding, ultra-realistic, 8K detail, high dynamic range. Negative Prompt: hands, people, faces, clutter, harsh reflections, label distortion, unreadable text, warped product, hard shadows, grain, noise, low resolution, CGI look, cartoon style, messy spills, uneven lighting, watermark