Stable Diffusion v1.5
The Stable-Diffusion-v1-5 checkpoint was initialized with the weights of the Stable-Diffusion-v1-2 checkpoint and subsequently fine-tuned on 595k steps at resolution 512x512 on "laion-aesthetics v2 5+" and 10% dropping of the text-conditioning to improve classifier-free guidance sampling. v1-5-pruned-emaonly.ckpt - 4.27GB,
ema-only weight. uses less VRAM - suitable for inference
v1-5-pruned.ckpt - 7.7GB,
ema+non-ema weights. uses more VRAM - suitable for fine-tuning
v1-4が 225,000 stepsに対し
v1-5は 595,000 steps🎉多いw
@FakeKamaboco: Stable Diffusion 1.5、一ヶ月以上前のStable Diffusion 1.4用のプロンプトを引っ張り出して出力してみた。一枚目と二枚目をそのままップロード。ネガティブとか最近のやつは一切未使用でこれ。これはかなりいけそう #stablediffusion
https://pbs.twimg.com/media/FfheQIWUAAEeFgY.pnghttps://pbs.twimg.com/media/FfheR2fVsAEO1X5.png