CoffeeVectors
@CoffeeVectors
Followers
39K
Following
57K
Media
953
Statuses
28K
More Wan 2.2 tests on Here I wanted to compare it directly to Veo 3 and also see how tight into the eye I could get with complex zooms. Again I’m really surprised by what Wan 2.2 can do. The prompts are the same across models, so Wan seems to be able to
24
66
625
It’s really useful to do your own projects start to finish. Not only do you get a sense of the full labor and problem space involved, but if you’re also distributing and promoting, you get a sense of the “why” of everything. You’re not as dependent on single jobs in the pipeline.
0
0
6
RT @CoffeeVectors: Poser // Initial tests with Nano-Banana and @midjourney HD video. Music in @suno. There's some face and wardrobe drift i….
0
19
0
RT @martinleblanc: Ok, this is crazy 🍌. Google’s new image model, Nano Banana, can actually read the text inside an image and use it as par….
0
27
0
RT @StelfieTT: been working on this cool fight scene with @Google nanobanana and start frame/end frame. Will make a post to explain the pro….
0
98
0
Need a job? Join ICE today. ICE offers competitive salaries & benefits like health insurance and retirement plans.
3K
6K
34K
RT @SamuelBeek: Lip Sync of Veo 3 and VEED Fabric 1 side by side; .we're 50x cheaper, and quality = better .Moore's law for AI is happening….
0
84
0
RT @TencentHunyuan: HunyuanWorld-Voyager is here and fully open-source! The world’s first ultra-long-range world model with native 3D recon….
0
287
0
RT @StevieMac03: Damn I love Veo3 image to video 😍 - Created in @runwayml. Time to get stitching and make some longer stuff this week!.🔊🔊🎧….
0
29
0
If we can solve transferring motion at the end of a clip into the start of the next clip through the key frame, we unlock so much possibility. Maybe instead of a single image there’s an option to extract some range of images from a clip and grab some motion vectors? It feels like.
1
0
6
RT @jerrod_lew: Am encountering more and more issues with Nano Banana today. Some of the functionalities it was showing earlier in the wee….
0
5
0
Poser // Initial tests with Nano-Banana and @midjourney HD video. Music in @suno. There's some face and wardrobe drift if you gen new frames from wide and closeup shots so there's still some craft on selecting what input images to use and what to prompt for.
6
19
190
RT @eyishazyer: The new Nano banana is like a Photoshop on steroids. It lets you do INSANE things that weren't possible before. Her….
0
649
0
RT @cfryant: First test with @Hailuo_AI's new start and end frame. Thoughts? Have you tried it yet?. Drop your tests below! https://t.co/….
0
19
0
RT @ZHO_ZHO_ZHO: 🍌nano-banana 对姿势的参考非常好！准确度高，不过有概率抽卡. 这下棚拍能省不少时间了！. ZH25O｜创意系列｜Gemini2.5FlashImg. nano-banana 没啥 AI 感，观看信任度真好！. 而且由于一致性好，所以….
0
310
0
RT @minchoi: Wild Nano Banana prompt you must try this weekend. Bookmark this. PROMPT: Create 4-panel montage of b-roll footage of this pe….
0
22
0
RT @maxescu: You've seen these paintings a million times. But never like this. Using nano-banana, Seedance, and Kling, I brought them int….
0
1K
0
RT @venturetwins: Swap your haircut with AI ✨. Fun new workflow that (1) takes a selfie, (2) transforms your hair with nano-banana, and (3)….
0
41
0
Cortensor: Pioneering Decentralized AI Inference, Democratizing Universal Access. Cortensor is not just an AI inference platform — it’s mineable AI, powered by a decentralized network of nodes that contribute computing power and get rewarded.
0
0
17
RT @venturetwins: Pose control with nano-banana is shockingly good. Upload characters + a sketch of a pose and ask to combine. Prompt: "t….
0
135
0
RT @mreflow: So Time Magazine put out a list of the 100 most influential people in AI. People NOT on the list:.- Demis Hassabis.- Mustaf….
0
35
0
RT @janusch_patas: FastAvatar: Instant 3D Gaussian Splatting for Faces from Single Unconstrained Poses. Abstract (excerpt):.We present Fast….
0
23
0