japanese-stable-diffusion
japanese-stable-diffusion copied to clipboard
rinnakk
Japanese Stable Diffusion is a Japanese specific latent text-to-image diffusion model capable of generating photo-realistic images given any text input.
Hello, I'm trying to train a latent diffusion model using huggingface's pipeline, but the model doesn't converge. I've set it up like a vanilla ddpm and replaced image inputs with...
Hi, thanks very much for your excellent work. I'm very curious about the hardware (which and how many GPU cards ... )that you used , and how much time did...
Hi, do you train your text encoder in CLIP way without latent diffusion. Or maybe train it with the diffusion model, how's the loss function and other detail? Would you...
こんにちは。 トレーニング、チューニングコードを共有できますか？ もし都合が悪ければ、プライベートメール（我的邮箱是[email protected],不胜感激)を送ってください
