Only 512x512 images

[Spitfire035]

Hi, it only works for me on 512x512 . If I move the sliders it gives some errors and then never finishes the image generation. Any solution?

[dan-garvey]

can you paste the errors? What gpu do you have?

[Spitfire035]

Hi, here is the error. It does an additional line after some time, but it takes time. I can leave it and add later.

vulkan devices are available.

cuda devices are not available. Running on local URL: http://0.0.0.0:8080

To create a public link, set share=True in launch(). Found device AMD Radeon RX 6700 XT. Using target triple rdna2-unknown-windows. Tuned models are currently not supported for this setting. torch\jit_check.py:172: UserWarning: The TorchScript type system doesn't support instance-level annotations on empty non-base types in __init__. Instead, either 1) use a type annotation in the class body, or 2) wrap the type in torch.jit.Attribute. warnings.warn("The TorchScript type system doesn't support " No vmfb found. Compiling and saving to C:\Users\Hesus\Desktop\Shark SD\euler_scale_model_input_1_728_728fp16.vmfb Using target triple -iree-vulkan-target-triple=rdna2-unknown-windows from command line args Saved vmfb in C:\Users\Hesus\Desktop\Shark SD\euler_scale_model_input_1_728_728fp16.vmfb. WARNING: [Loader Message] Code 0 : windows_read_data_files_in_registry: Registry lookup failed to get layer manifest files. No vmfb found. Compiling and saving to C:\Users\Hesus\Desktop\Shark SD\euler_step_1_728_728fp16.vmfb Using target triple -iree-vulkan-target-triple=rdna2-unknown-windows from command line args Saved vmfb in C:\Users\Hesus\Desktop\Shark SD\euler_step_1_728_728fp16.vmfb. WARNING: [Loader Message] Code 0 : windows_read_data_files_in_registry: Registry lookup failed to get layer manifest files. Compiling all the models with the fetched base model configuration. Cannot initialize model with low cpu memory usage because accelerate was not found in the environment. Defaulting to low_cpu_mem_usage=False. It is strongly recommended to install accelerate for faster and less memory-intense model loading. You can do so with:

pip install accelerate

.

[Spitfire035]

after 3min:

torch\fx\node.py:250: UserWarning: Trying to prepend a node to itself. This behavior has no effect on the graph. warnings.warn("Trying to prepend a node to itself. This behavior has no effect on the graph.") No vmfb found. Compiling and saving to C:\Users\Hesus\Desktop\Shark SD\unet1_64_728_728_fp16_stable-diffusion-v1-4_vulkan-00000000-0600-0000-0000-000000000000.vmfb Using target triple -iree-vulkan-target-triple=rdna2-unknown-windows from command line args

[Spitfire035]

Sorry I forgot - rx6700xt

[dan-garvey]

Thats actually not an error. If you wait longer it should compile the other models as well.