GPT Image 2 — 真正會思考的 AI 影像生成器

Chubby♨️

@kimmonismus·在 X 上關注

Holy, GPT Image 2 will crush everything. I remember when everyone laughed at the GPT image because it couldn't generate a proper world map. Those days are over. And even the YouTube image is now indistinguishable from reality. Holy moly.

@levelsio

@levelsio·在 X 上關注

the new image model GPT Image 2 has leaked. It seems to have extremely good world knowledge and great text rendering. Possibly better than Nano Banana Pro. It's on @arena under code names: - maskingtape-alpha - gaffertape-alpha - packingtape-alpha

Blake Robbins

@blakeir·在 X 上關注

people are speculating GPT-Image-2 is testing on @arena. the early examples being posted are pretty mind-boggling. all three of these images are AI generated. h/t @sawlygg @synthwavedd

Mark Kretschmann

@mark_k·在 X 上關注

GPT-Image-2 is insanely good with text rendering. These images are from @arena, where the new model family was tested under various codenames (it's no longer available). This appears to be the new multimodal model.

Dan McAteer

@daniel_mac8·在 X 上關注

The most amazing thing about modern image models like GPT-Image-2 isn't the image quality, which IS amazing enough. It's the fact that they can do correct abstract reasoning in visual form.

すぐる | ChatGPTガチ勢

@SuguruKun_ai·在 X 上關注

【速報】次世代画像生成AI「GPT Image 2」あまりにも性能が高すぎて話題に... ① テキスト描画の精度が異次元 →曲面の上でも文字が崩れない ② 世界知識（地図・解剖図）が大幅向上 →ラベルの位置がまともになった ③ 写実性が Nano Banana Pro 超え

KAWAI

@kawai_design·在 X 上關注

やってる GPT Image 2 がすごい... しかもこれ、1枚の画像で4種類の広告を生成しています。それなのに、この描画の精度。 正直、今私が感じているのがワクワクなのか、恐れなのかはわかりません😂 とりあえず、お腹がグワングワンなります。

Sad AlbertX

@SadAlbert10·在 X 上關注

GPT image V2 is wayyy to powerful... This is the reason there's so much delay, I can't post live examples but it has a mind of its own! You can talk to it, help you explain stuff and what not... And live correct maths stuff and codes also! Through image gen!

Image Arena

@arena·在 X 上關注

GPT Image 2 has claimed the #1 spot across all Image Arena leaderboards. Text-to-image: 1512 Elo Single-image edit: 1513 Elo +242 Elo lead on text-to-image over the next model. A new state of the art.