> a photo of messy handwriting in blue ink saying "this is what handwriting looks like in seedream", on lined paper, the words are small, there are doodles and sketches of people in blue ink
MULTIMODAL AI
-
AI generates talking cat video with creative prompt
By
–
@AskPerplexity Make me a video of a talking cat that's sitting next to a taco and saying "subscribe to Matt Wolfe."
-
Ask Perplexity Bot Video Generation Capabilities Status
By
–
@AskPerplexity Is the Ask Perplexity bot still capable of generating videos? The last few video requests I saw never seemed to process.
-
Perplexity Ask bot image generation feature stops working
By
–
@AskPerplexity is the Ask Perplexity bot still capable of generating images? It no longer appears to be working.
-
Video Generation AI Models: Hailuo 2 and Seedance 1 Challenge Veo 3
By
–
The video generation market is heating up: recent models like Hailuo 2 and Seedance 1 offer big quality gains at ~3-4x cheaper than Veo 3. Veo 3's unique native audio capability might set a new standard if others follow. Elo Data from @ArtificialAnlys Pricing from @FAL and
-
AI Video Generation: Talking Cat Creative Content Tool
By
–
@AskPerplexity Make me a video of a talking cat that's sitting next to a taco and saying "subscribe to Matt Wolfe."
-
Seedream 3.0 Generates Panoramic AI Image at 4:1 Ratio
By
–
Seedream 3.0 at 2048×512 (4:1), prompt: "A panoramic view"
-
AI Character Creation by Artist Plouz
By
–
characters created by plouz.https://t.co/yIgka8Lsqu pic.twitter.com/J7E21ly0yd
— KREA AI (@krea_ai) 25 juin 2025characters created by plouz. https://
krea.ai/user/plouz -
Nanonets-OCR-s: Advanced Vision-Language Model for Document Understanding
By
–
Nanonets-OCR-s: Enabling Rich, Structured Markdown for Document Understanding Upgrade your document workflow with Nanonets-OCR‑s! Discover how this cutting‑edge Vision‑Language Model preserves images, layout, and semantic structure for unbeatable accuracy. Read the full
-
ByteDance’s Seedream 3.0 Text-to-Image Model Available on Replicate
By
–
ByteDance's Seedream 3.0 text-to-image model is now on Replicate. It makes stunning 2048×2048 images natively, and is the second best image model as ranked by ELO on the Artificial Analysis leaderboard. Just $0.03 per image too. https://
replicate.com/bytedance/seed
ream-3
…