Commit History
-
Fix deprecated float16/fp16 variant loading through new `version` API.
Hey ckpt 👋, Your model repository seems to contain a [`fp16` branch](https://huggingface.co/ckpt/sd15/tree/fp16) to load the model in float16 precision. Loading `fp16` versions from a branch instead of the main branch is deprecated and will eventually be forbidden. Instead, we strongly recommend to save `fp16` versions of the model under `.fp16.` version files directly on the 'main' branch as enabled through this PR.This PR makes sure that your model repository allows the user to correctly download float16 precision model weights by adding `fp16` model weights in both safetensors and PyTorch bin format: ```py pipe = DiffusionPipeline.from_pretrained(ckpt/sd15, torch_dtype=torch.float16, variant='fp16') ``` For more information please have a look at: https://huggingface.co/docs/diffusers/using-diffusers/loading#checkpoint-variants. We made sure you that you can safely merge this pull request. Best, the 🧨 Diffusers team.d649632
-
Fix deprecation warning by changing `CLIPFeatureExtractor` to `CLIPImageProcessor`. (#2)
- Fix deprecation warning by changing `CLIPFeatureExtractor` to `CLIPImageProcessor`. (239a6abd7e94e45b7784e94b80f75a3ff5518986)97b7bf7
-
Add `scale_factor` to vae config. (#1)
- Add `scale_factor` to vae config. (d2ce79b757a160f39f451dc73792df50f26f3ea5) Co-authored-by: Suraj Patil <valhalla@users.noreply.huggingface.co>0b6650d
-
PyTorch
438772f
-
Update README.md
bbc4a08
-
no pickle please
916b2e7
-
license
d62866a -
Initial commit
c1fedb2 -
sd15
665979a -
initial commit
29c5442