-
Notifications
You must be signed in to change notification settings - Fork 7.2k
All issues
Issue creation is restricted in this repository
Issues
is:issue state:open
is:issue state:open
Search results
pipe.to(device) corrupts custom quantized (uint8 packed) module buffers
bugSomething isn't workingSomething isn't workingStatus: Open.#14449聽In huggingface/diffusers;- Status: Open.#14442聽In huggingface/diffusers;
SDXL + enable_model_cpu_offload() produces all-black images on MPS (Apple Silicon)
bugSomething isn't workingSomething isn't workingStatus: Open.#14438聽In huggingface/diffusers;Title: Group offloading with use_stream=True fails on torchao int8 version=2 (pin_memory on CUDA qdata)
bugSomething isn't workingSomething isn't workingStatus: Open.#14433聽In huggingface/diffusers;[SD3 DreamBooth] Cached latents can be paired with the wrong per-image captions when shuffle=True
bugSomething isn't workingSomething isn't workingStatus: Open.#14430聽In huggingface/diffusers;VaeImageProcessorLDM3D ignores constructor configuration arguments
bugSomething isn't workingSomething isn't workingStatus: Open.#14429聽In huggingface/diffusers;VaeImageProcessorLDM3D.preprocess fails for batched NumPy RGB/depth inputs
bugSomething isn't workingSomething isn't workingStatus: Open.#14428聽In huggingface/diffusers;- Status: Open.#14420聽In huggingface/diffusers;
Division by 0 bug when only one denoising step
bugSomething isn't workingSomething isn't workingStatus: Open.#14411聽In huggingface/diffusers;- Status: Open.#14410聽In huggingface/diffusers;
- Status: Open.#14405聽In huggingface/diffusers;
- Status: Open.#14403聽In huggingface/diffusers;