Mục đầu tiên luôn là nguồn của ghim. Độ tin cậy tổng thể là trung bình có trọng số về mức độ mỗi tài liệu ủng hộ thời điểm bắt đầu và kết thúc được dùng ở trên; một tài liệu được tính giảm một nửa cho mỗi 180 ngày cũ hơn tài liệu mới nhất.
The Verge (15 Feb 2024, 18:50 UTC), Wired[2] (15 Feb), NBC News[4] (15 Feb) and MIT Technology Review[5] all report OpenAI unveiling Sora on Thursday 15 February 2024; Wikipedia[6] gives the same date.
Steven Levy saw four demo clips (the longest 17 seconds), calls the photorealism something he had not seen in competitors, notes a Tokyo scene whose sidewalk dead-ends, and says researchers would only describe render time as nearer 'going out for a burrito' than days.[1]
Says Sora is 1920x1080, holds a subject consistent for up to 60 seconds, extends videos or animates stills, and has no synchronized sound yet; frames it as a diffusion transformer built on DALL-E 3 style recaptioning.[1]
Reports clips up to a minute, Sam Altman generating viewer-prompted videos on X, an OpenAI spokesperson saying the model will not be broadly available soon, and the weaknesses OpenAI listed (physics, cause and effect, a person running the wrong way on a treadmill).[1]
Says OpenAI briefed it under embargo, has no plan to release Sora, started third-party safety testing, and that the samples were probably cherry-picked; Tim Brooks admits people who leave the frame for long 'won't come back'.[1]
Estimate from the version's published specs and reviews, 0-5; scores are only comparable within one criteria year. Scored as previewed (Feb 2024 research preview, never sold): 1920x1080 and up to 60 s per Ars Technica, text and image input plus extending or filling in an existing video per The Verge, silent per Ars ('no synchronized sound yet'). Speed is null: OpenAI gave no render time and Wired was told only 'going out for a burrito'. Realism is from curated OpenAI demo clips only, since no outside reviewer could enter prompts; all five reviews praise the look and note artifacts or cherry-picking, so 4 is capped by that caveat.[1]
OpenAI says that Sora is distinguished by its striking photorealism—something I haven’t seen in its competitors—and its ability to produce longer clips than the brief snippets other models typically do, up to one minute.
there are issues — basketballs go through the sides of metal hoops, dogs pass through each other while walking, and hands are.... not always hands.
It’s high-resolution (1920×1080), can generate video with temporal consistency (maintaining the same subject over time) that lasts up to 60 seconds, and appears to follow text prompts with a great deal of fidelity.
Impressive as they are, the sample videos shown here were no doubt cherry-picked to show Sora at its best.
The blog explains that Sora-generated videos “may struggle with accurately simulating the physics of a complex scene, and may not understand specific instances of cause and effect.”
Thiếu hay sai điều gì? Hãy nói bằng lời của bạn: một liên kết củng cố ghim này, một ngày bắt đầu hoặc kết thúc khác kèm lý do, hoặc một thông tin còn thiếu hay sai. AI đối chiếu với các nguồn của ghim này, tìm nguồn tốt hơn và thêm mọi trang ủng hộ bạn. Các nguồn của chính ghim vẫn được tính nhiều nhất. Hình ảnh thể hiện nội dung khác hoặc thể hiện kém cũng được xem xét, rồi bị hạ xuống hoặc thay thế.