AI vectorization works so freaking well left: low quality... jpg (input) right: high quality svg (output)show more

Low quality video but high quality moment

low quality video of a high quality MAN.

low quality video but very high quality woman

low quality video of a very high quality MAN

Low-quality video, but he’s high quality. 😭🔥

This is a village in Norway, while the video... below is a major city in Nigeria. Low quality human beings will always create low quality societies, while high quality human beings will always create high quality societies.show more

left input-image(midjourney) right output-video(wanvideo) music & dance UNDEAD

low quality videos always dey go well😂😂

Left: Image input, Right: Spell AI 3D Volume

Idk why that shi was low quality, so here’s... a higher quality version to see Gohan aura farmingshow more

Here's a Veo2 prompt enhancer GPT. Link in thread... 🧵 It works well for other GenAI platforms, too! Give it a simple prompt, and it will output an enhanced one. It does this by referencing many high-quality example prompts. It also helps with character consistency.show more

Spell AI generating 3D humans. Left: Input image, Right:... GS Volumeshow more

Comfy workflow vs FAL for WanAnimate Feels fairly identical... in quality output tbh as I suspect the backend is nearly identical (which is obvious from their input sliders) Either way for those afraid of Comfy... this works for this specific use case at leastshow more

Introducing prompt-kit A set of high-quality, customizable components for... building AI interfaces. Built on top of shadcn/ui, starting with PromptInput, a flexible input field for chatting with AI models. New components coming soon!show more

NVIDIA introduces Edify 3D AI model You can generate... high quality 3D assets from text or image input under 2 minutes! With PBR materials, quad-mesh topologies, and 4k textures. 6 wild examples:show more

This is so well done, the quality is next-level!