Stable Diffusion 2.0-v 공개
v-prediction 모델이라 불리는 Stable Diffusion 2.0-v가 공개됨.
5.85억 CLIP-filtered 이미지-텍스트 쌍으로 학습. 바닥부터 새로 학습했다고 함.
개선 사항은 다음과 같음.
- 2048x2048 이상의 해상도를 가진 결과물 생성 가능
- depth-guided stable diffusion model
- Brand new text-guided inpainting model
소스코드는 아래 github 사이트에서 다운 받을 수 있고..
https://github.com/Stability-AI/stablediffusion
GitHub - Stability-AI/stablediffusion: High-Resolution Image Synthesis with Latent Diffusion Models
High-Resolution Image Synthesis with Latent Diffusion Models - GitHub - Stability-AI/stablediffusion: High-Resolution Image Synthesis with Latent Diffusion Models
github.com
학습된 ckpt 파일은 아래 링크에서 다운 받을 수 있음. (5.09G)
https://huggingface.co/stabilityai/stable-diffusion-2/blob/main/768-v-ema.ckpt
768-v-ema.ckpt · stabilityai/stable-diffusion-2 at main
Detected Pickle imports (4) "collections.OrderedDict", "torch.FloatStorage", "torch._utils._rebuild_tensor_v2", "torch.IntStorage" What is a pickle import?
huggingface.co
그렇다면, 이걸 가지고 사용하기 쉽게 WebUI 만드는 그룹에서는 어떻게 반응했는가를 봐야겠지?
역시... 우리 병아리들 벌써 작업 들어 갔어~!
https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/5011
[Feature Request]: Support for new 2.0 models | 768x768 resolution + new 512x512 + depth + inpainting · Issue #5011 · AUTOMATI
Is there an existing issue for this? I have searched the existing issues and checked the recent builds/commits What would your feature do ? Support the new 768x768 model 2.0 from Stability-AI and a...
github.com
출장 다녀와서 조금 만지작 거려봐야겠음.
References
https://medium.com/mlearning-ai/stable-diffusion-v2-0-released-this-is-massive-718072bc57e1
Stable Diffusion V2.0 Released — This Is Massive
Stable Diffusion 2.0 is released with brand new features including an image depth recognition.
medium.com