averad
averad
@muhademan how much Vram and System ram do you have? Generating a 512x768 image takes more than 8GB of Vram and 16GB of System Ram using Onnx and DmlExecutionProvider. @GreenLandisaLie...
@anton-l I ran the FP32 to FP16 @tianleiwu provided and was able to convert a Onnx FP32 Model to Onnx FP16 Model. Windows 11 AMD RX580 8GB Python 3.10 Diffusers...
DPMSolverMultistepScheduler wasn't [merged ](https://github.com/huggingface/diffusers/pull/1132) into the 0.7.2 patch. The available schedulers in 0.7.x are [here ](https://huggingface.co/docs/diffusers/v0.7.0/en/api/schedulers) DPMSolverMultistepScheduler is [included ](https://huggingface.co/docs/diffusers/main/en/api/schedulers#diffusers.DPMSolverMultistepScheduler) in the current [0.8.0dev0](https://github.com/huggingface/diffusers/blob/main/src/diffusers/schedulers/scheduling_dpmsolver_multistep.py) files
@WASasquatch use `pip install git+https://github.com/huggingface/diffusers.git`
That is really strange, pulling the diffusers repo using git should result in the scheduler being available. Did you verify the diffusers version is showing as 0.8.0dev0 using `diffusers-cli env`...
I tested the reported issue and was unable to get an error where import_utils.py gave an error that directml was not available when using `provider="DmlExecutionProvider"`. 1. pip install [ort_nightly_directml](https://pypi.org/project/ort-nightly-directml/) will...
Please share your system info with us. You can run the command `diffusers-cli env` and copy-paste its output below.
# 🤗 Diffusers with Stable Diffusion 2 is live! [anton-l](https://github.com/anton-l) commented (https://github.com/huggingface/diffusers/issues/1388#issuecomment-1327731012) `diffusers==0.9.0` with Stable Diffusion 2 are live! Installation `pip install diffusers[torch]==0.9 transformers` Release Information https://github.com/huggingface/diffusers/releases/tag/v0.9.0 Contributors @kashif @pcuenca...
768x768 weights released: - https://huggingface.co/stabilityai/stable-diffusion-2/tree/main fp16 and other versions of the models appear to being being worked on and uploaded.
Are you referring to the following code? https://huggingface.co/docs/diffusers/training/text2image#finetuning-example