Sora Reviews

StableDiffusionWeb.com Reviews

Sora mentions (4)

• 11th Dec 2024 — OpenAI's Kubernetes Outage Explained

  Last week, December 11th, 2024, OpenAI faced an SRE nightmare. A major platform outage lasting four hours affected ChatGPT and SORA (OpenAI's video generation model) due to faulty service deployment, bringing down their largest Kubernetes clusters to the knees. On-call engineers were locked out of the cluster, preventing them from running kubectl. - Source: dev.to / over 1 year ago

• A state of AI in 2024

  Sora, OpenAI's tool for generating video, unveiled a fairly impressive video in Japan, even if some imperfections were detected. - Source: dev.to / about 2 years ago

• Vision Transformers Need Registers

  3. Minimize cross-entropy loss between predicted and actual next tokens. (This is equivalent to trying to minimize encoding length.) ViT don't have quantization baked into the algorithm, but NNs are being moved towards quantization in general. ----- I think it's pretty interesting how closely related generation and compression are. ClosedAI's Sora[^1] model uses a denoising vision transformer, and is the... - Source: Hacker News / about 2 years ago

• StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Gen

  Did you miss the fish?[0] You should see the error in first viewing What about the woman with glasses? Her face literally "jumps"[1] Same with this guy's hands[2] Interesting, we notice that [1] has "sora" in the name though I think it is a reference to the main image on sora[3] Not sure if the gallery is weird to anyone else, but it doesn't exactly show new images and the position indicator is wonky. The thing... - Source: Hacker News / about 2 years ago

StableDiffusionWeb.com mentions (31)

• Prompt Engineering with Serverless AI

  The process of structuring text that can be interpreted and understood by a generative AI model is called Prompt Engineering. This can apply to text-only models such as Llama2 and image generation models such as Stable Diffusion. Often, the key to generating an appropriate piece of text or an accurate image comes down to how the prompt is engineered. - Source: dev.to / over 2 years ago

• Funny logo results of AI Image Generator Stable Diffusion

  The images created by AI Image Generators like Midjourney or Stable Diffusion are quite impressive. In the last few days, I have been testing with Stable Diffusion's AI Image Generator (text-to-image) to create a futurebucket logo. For me as a beginner, I am quite satisfied with the results. Please let me know which one you prefer. Source: over 2 years ago

• Old version of stable diffusion UI

  Hey guys, I used to use this stable diffusion UI a lot (https://stablediffusionweb.com/). It used to be much simpler though, a single line for a prompt and would generate 4 images in usually 10 second. Source: almost 3 years ago

• Older Versions of Stable Diffusion Web?

  I got acquainted with stablediffusionweb.com and the Playground option it had back in May 2023 and made some good use of it from there to mid-July or so. Got busy, hadn't used it until late August, now I come back and see the Playground is a different thing entirely now that it's "Stable Diffusion XL 1.5" or something. Not only does it now only output 1 image as opposed to 4 images, it takes 8 times longer and the... Source: almost 3 years ago

• automatic1111 for the one without a GPU

  The web site I did try, including https://stablediffusionweb.com/ or Artroom do not have all the option and flexibility I see in automatic 1111, explacially for fine tuning and manually guide further elaboration. Source: about 3 years ago