Albert Kim

The 20th edition of The Vision Debugged is LIVE now! https://lnkd.in/gZxS5mPN In this edition, Sandra Anil & I dive deep into the HOTTEST new AI video generator: Luma Labs' 𝐃𝐫𝐞𝐚𝐦 𝐌𝐚𝐜𝐡𝐢𝐧𝐞. 𝐖𝐡𝐲 𝐬𝐡𝐨𝐮𝐥𝐝 𝐲𝐨𝐮 𝐜𝐚𝐫𝐞? ✅ Turn text into hyper-realistic video clips in MINUTES (think: dev demos, product mockups, crazy marketing ideas) ✅ Free option available! (who doesn't love that?) ✅ MVP alert! Learn how Luma Labs is using this to gather user feedback & build a killer product (perfect for product managers ) Plus, we compare Dream Machine to other AI video tools & tell you which one is best for YOUR needs. Don't miss out! Click the link to snag this edition. ➡️ https://lnkd.in/gZxS5mPN PS: We crossed 600 readers this week 🙏 🎉Thanks to all our amazing subscribers for their consistent support, feedback & curiosity! If you find our newsletter useful, please share it with a friend and consider subscribing if you haven’t already 👉 https://lnkd.in/gwUNCBdJ

99

댓글 2

SREF Animations with Luma AI I am always looking for new workflows and ways to showcase what we’re able to do with these tools. MidJourney produces 4 images per prompt, so I wondered what they would look like if I stitched them together using Luma AI. Loved how these came out. Workflow: MidJourney prompt: “a woman made out of porcelain, in the style of balanced symmetry, white and blue/gold, detailed facial features, organic forms, extreme detail, 4k, high octane render, realistic, meticulous portraiture, complex patterns” Luma: Drop in images sequentially per SREF 1-2, 2-3, 3-4, 4-1 so it creates a seamless loop After Effects: Stitch animations sequentially to loop If you’re interested, the MidJourney SREF codes are: • 2988814434 • 195019361 • 2059483505 • 573292149

33

댓글 13

Nomic AI Releases Nomic Embed Vision v1 and Nomic Embed Vision v1.5: CLIP-like Vision Models that Can be Used Alongside their Popular Text Embedding Models Nomic AI has recently unveiled two significant releases in multimodal embedding models: Nomic Embed Vision v1 and Nomic Embed Vision v1.5. These models are designed to provide high-quality, fully replicable vision embeddings that seamlessly integrate with the existing Nomic Embed Text v1 and v1.5 models. This integration creates a unified embedding space that enhances the performance of multimodal and text tasks, outperforming competitors like OpenAI CLIP and OpenAI Text Embedding 3 Small. Nomic Embed Vision aims to address the limitations of existing multimodal models such as CLIP, which, while impressive in zero-shot multimodal capabilities, underperform tasks outside image retrieval. By aligning a vision encoder with the existing Nomic Embed Text latent space, Nomic has created a unified multimodal latent space that excels in image and text tasks. This unified space has shown superior performance on benchmarks like Imagenet 0-Shot, MTEB, and Datacomp, making it the first weights model to achieve such results. Quick read: https://lnkd.in/ge_CA39W Check out the models: https://lnkd.in/gh9G4evm Nomic AI Brandon Duderstadt Andriy Mulyar

43

My first try with Luma AI Dream Machine: - It seems like the result can be more realistic in movements, and animatics with real-time speed, unlike other AI video gen - Great move by letting people experiment with the prompts at an early stage. Kudos! It beats others who are just doing demos... - Very promising to be used for advanced AI filmmaking, I could make entire AI film with it :D In this clip, I tried to generate a scene for my horror film. The camera movement is more cinematographic. What do you think? Have you tried Dream Machine? #ai #aifilms #contentcreator #lumalabs #dreammachine #aimovies #lumaai

3

댓글 2