DStudioproject
@D_studioproject • 10,195 subscribers
Ambassador Higgsfield • Openart • LTX • Elevenlabs | Partner : Hailuo • Topazlabs • Wan • Vidu • Dreamina • Florafauna • Invideo • Kling • Pikalabs
Shorts
Videos
Here are some of my experiments with AI generated filmmaking, pushing realism, narrative texture, and visual continuity as far as current tools allow. I combined multiple models for this and honestly, I’m pretty satisfied with how far it’s come. There are still rough spots, especially in transition seams between start and end frames, but compared to what was possible back in January, the progress feels massive. All the color and sound were manually adjusted I’m genuinely excited to see how far we can go in 2026. For this project, I call it Subject 168. I’d love to hear your feedback. To help maintain all the production costs, I used WaveSpeedAI for this one.
DStudioproject219,350 次观看 • 6 个月前
As I promised, I’ve been exploring more with Ray 3. And honestly… every single crazy dream prompt I throw in, Luma Ray 3 nails it. Feels like I’m testing the limits of my own imagination and it just keeps delivering. This engine makes the wild side of my creativity come alive😂 thanks Luma
DStudioproject262,176 次观看 • 8 个月前
My first experiment with Kling O1 is quickly proving to be a major breakthrough in AI video creation. Instead of manually editing individual images, you can now refine an entire video sequence simply through prompting. This significantly reduces the time spent on adjustments, cuts down manual workflow, and saves credits by eliminating unnecessary regeneration. With this update, the technical limitations shrink even further, what truly defines the final result is your creativity and how you choose to guide the model. Invideo x Kling AI
DStudioproject184,946 次观看 • 6 个月前
Every person has a chance to feel alive, in quiet solitude, with friends, a lover, or family. Life doesn’t need to be grand to be beautiful. In the ordinary, we always find something special, a small heartbeat that reminds us we’re alive. I love creating moments that capture that simplicity, no epic effects, just honesty and warmth. Brought to life with WaveSpeedAI using WAN 2.5 Wan #heartbeat #wanmuse #wan
DStudioproject162,497 次观看 • 7 个月前
currently experimenting with WAN 2.6 I2V on GMI Cloud in this test, I’m comparing two audio workflows and honestly both perform really well. one scene uses audio generated directly from the prompt, while the other uses manually uploaded audio taken from the film 300. visually, both deliver strong motion and solid performance. however, the version with audio coming straight from the prompt feels slightly more refined, camera movement is smoother, transitions flow more naturally and the sync between voice, facial motion, and pacing feels more cohesive. lip sync, especially for Chinese dialogue also comes across a bit cleaner. you can choose single shot for a clean, focused moment or multi shot if you want more cinematic transitions, even when working from just one reference image. one important note: always turn on prompt extension. it makes a noticeable difference in how well the model understands motion, transitions and overall scene flow. both audio approaches are totally usable, but if you’re building dialogue driven or cinematic scenes, starting with audio from the prompt gives WAN 2.6 a bit more context to work with. I’ll be pushing this further with more dynamic camera movement and transitions next. more experiments coming soon ✨ Wan
DStudioproject96,950 次观看 • 5 个月前
