After giving it a try, the result was quite good for me, a new image generated with the suggested prompt was looking very very close. Btw, this feature should be available to everybody
GENERATIVE AI
-
ChatGPT Image View Now Includes Prompt Generation Feature
By
–
ICYMI: Now you can open a side tab on the image view to see the prompt which can be used to generate a similar image. Note that this is not a prompt you've been submitting – it is a ChatGPT-generated prompt.
-
Claude 3 Outperforms ChatGPT in Game Development Tasks
By
–
Claude 3 is really really good. I was super impressed with even the free (Sonnet) version of Claude 3. The paid version (Opus) built a working mini-game for me in a single prompt. Sonnet built the same game in 2-prompts. ChatGPT struggled still after several prompts. Both
-
Stable Diffusion 3 MMDiT Architecture Enhances Text Understanding
By
–
(3/3) Our new Multimodal Diffusion Transformer (MMDiT) architecture uses separate sets of weights for image and language representations, which improves text understanding and spelling capabilities compared to previous versions of SD3. Read the full blog post and access the
-
Stable Diffusion 3 Outperforms DALL-E 3 and Midjourney
By
–
(2/3) Stable Diffusion 3 outperforms state-of-the-art text-to-image generation systems such as DALL·E 3, Midjourney v6, and Ideogram v1 in typography and prompt adherence, based on human preference evaluations. With SD3 as a baseline, this chart outlines the areas it wins against
-
Stable Diffusion 3 Research Paper Released
By
–
(1/3) Today, we're publishing our research paper that dives into the underlying technology powering Stable Diffusion 3. Prompt: A beautiful painting of flowing colors and styles forming the words “The SD3 research paper is here!”, the background is speckled with drops and
-
AI News platform powered by GPT-4 launched open-source
By
–
AI News is created and run by @swyx and friends; powered by GPT-4 (I think).
Code is open-source: https://
github.com/smol-ai/talk
Thanks y'all for creating this!
(i realized too late that I didn't call out the people behind it, couldn't edit my tweet) -
Sydney AI Article: Convincing Generated Content Example
By
–
This can be very convincing. See the infamous Sydney article.
-
LLMs Emulate Consciousness: Cold Reading Not Reality
By
–
Every time a new chatbot comes out, Twitter is filled with tweets of the AI insisting it is somehow conscious. But remember that LLMs are incredibly good at "cold reads" by design – guessing what kind of dialogue you want from clues in your prompts. It is emulation, not reality.
-
LLMs vs Image Generators: Understanding Distinct Capabilities
By
–
AI image generators, and their errors, tell you very little about LLMs & their capabilities. When you ask ChatGPT or Bard to produce an image, the LLM is just writing prompts (often inexpertly) and those prompts are then processed separately by the relatively dumb image makers.