原创 歸藏的 AI 工具箱 2024-11-22 22:43 北京
我去，这两天开源生态过年了？
Lightricks 开源实时视频生成模型 LTX-Video。
视频生成速度比观看速度还快！！！
真的麻了，昨天FLUX发布了官方套件，今天 Lightricks 开源实时视频生成模型 LTX-Video。
LTXV 是唯一一个能够实时生成高质量视频的基于2B参数DiT 的视频生成模型（H100）。它以 768x512 分辨率生成 24 FPS 视频，速度比观看视频的速度要快。
LTXV 旨在保持精度和视觉质量，而不影响速度或内存效率。它针对 RTX 4090 等广泛使用的 GPU 进行了优化，并利用 bfloat16 精度实现高效内存使用，而不牺牲质量。
另外模型能够生成质量一致的长视频。
而且ComfyUI一贯的快速，现在已经支持了 LTXV 模型。
来看一些演示
The waves crash against the jagged rocks of the shoreline, sending spray high into the air.The rocks are a dark gray color, with sharp edges and deep crevices. The water is a clear blue-green, with white foam where the waves break against the rocks. The sky is a light gray, with a few white clouds dotting the horizon.
A man in a dimly lit room talks on a vintage telephone, hangs up, and looks down with a sad expression. He holds the black rotary phone to his right ear with his right hand, his left hand holding a rocks glass with amber liquid. He wears a brown suit jacket over a white shirt, and a gold ring on his left ring finger. His short hair is neatly combed, and he has light skin with visible wrinkles around his eyes. The camera remains stationary, focused on his face and upper body. The room is dark, lit only by a warm light source off-screen to the left, casting shadows on the wall behind him. The scene appears to be from a movie.
本地使用
目前ComfyUI已经支持文生视频和图生视频流程。
只需要从这里下载模型文件：https://huggingface.co/Lightricks/LTX-Video/blob/main/ltx-video-2b-v0.9.safetensors
然后从这里获取工作流就行：https://comfyanonymous.github.io/ComfyUI_examples/ltxv/?ref=blog.comfy.org
