由 Flux1.1 Pro 生成的 FLUX AI 图像
![A wide image taken with a phone of a glass whiteboard, in a room overlooking the Bay Bridge. The field of view shows a woman writing, sporting a tshirt wiith a large OpenAI logo. The handwriting looks natural and a bit messy, and we see the photographer's reflection.
The text reads:
(left)
"Transfer between Modalities:
Suppose we directly model
p(text, pixels, sound) [equation]
with one big autoregressive transformer.
Pros:
* image generation augmented with vast world knowledge
* next-level text rendering
* native in-context learning
* unified post-training stack
Cons:
* varying bit-rate across modalities
* compute not adaptive"
(Right)
"Fixes:
* model compressed representations
* compose autoregressive prior with a powerful decoder"
On the bottom right of the board, she draws a diagram:
"tokens -> [transformer] -> [diffusion] -> pixels"](/_next/image?url=https%3A%2F%2Ffal.media%2Ffiles%2Fkoala%2F52hMqgpIzA_5GgMXMPfSC_52fe180ff1e0444ba425c7e9bfb21d96.jpg&w=3840&q=75)
迅速的
A wide image taken with a phone of a glass whiteboard, in a room overlooking the Bay Bridge. The field of view shows a woman writing, sporting a tshirt wiith a large OpenAI logo. The handwriting looks natural and a bit messy, and we see the photographer's reflection. The text reads: (left) "Transfer between Modalities: Suppose we directly model p(text, pixels, sound) [equation] with one big autoregressive transformer. Pros: * image generation augmented with vast world knowledge * next-level text rendering * native in-context learning * unified post-training stack Cons: * varying bit-rate across modalities * compute not adaptive" (Right) "Fixes: * model compressed representations * compose autoregressive prior with a powerful decoder" On the bottom right of the board, she draws a diagram: "tokens -> [transformer] -> [diffusion] -> pixels"
