mirror of
https://github.com/Stability-AI/generative-models.git
synced 2025-12-20 06:44:22 +01:00
Fix link (#24)
This commit is contained in:
@@ -28,7 +28,7 @@ Modularity is king. This repo implements a config-driven approach where we build
|
|||||||
|
|
||||||
### Changelog from the old `ldm` codebase
|
### Changelog from the old `ldm` codebase
|
||||||
|
|
||||||
For training, we use [pytorch-lightning](https://www.pytorchlightning.ai/index.html), but it should be easy to use other training wrappers around the base modules. The core diffusion model class (formerly `LatentDiffusion`, now `DiffusionEngine`) has been cleaned up:
|
For training, we use [PyTorch Lightning](https://lightning.ai/docs/pytorch/stable/), but it should be easy to use other training wrappers around the base modules. The core diffusion model class (formerly `LatentDiffusion`, now `DiffusionEngine`) has been cleaned up:
|
||||||
|
|
||||||
- No more extensive subclassing! We now handle all types of conditioning inputs (vectors, sequences and spatial conditionings, and all combinations thereof) in a single class: `GeneralConditioner`, see `sgm/modules/encoders/modules.py`.
|
- No more extensive subclassing! We now handle all types of conditioning inputs (vectors, sequences and spatial conditionings, and all combinations thereof) in a single class: `GeneralConditioner`, see `sgm/modules/encoders/modules.py`.
|
||||||
- We separate guiders (such as classifier-free guidance, see `sgm/modules/diffusionmodules/guiders.py`) from the
|
- We separate guiders (such as classifier-free guidance, see `sgm/modules/diffusionmodules/guiders.py`) from the
|
||||||
|
|||||||
Reference in New Issue
Block a user