gadersd / stable-diffusion-xl-burn Goto Github PK

The third-party SD ecosystem has mostly shifted to the safetensors format for distributing models, as the Python pickle format allows for arbitrary code execution on deserialization. Safetensors is safe, and easy and fast to load as well.

Using export TORCH_CUDA_VERSION=cu113 I get an error downloading https://download.pytorch.org/libtorch/cu113/libtorch-cxx11-abi-shared-with-deps-2.0.0%2Bcu113.zip.

The route is status code 403.

I'm trying to reproduce the example provided. Everything is downloaded and ready, but I can't seem to make it work. My Rust version is 1.71.1. Here's what I get in my windows powershell :

thread 'main' panicked at 'called Result::unwrap() on an Err value: Unknown("Unable to load record.\nError: Unknown("Io { inner: Error { kind: UnexpectedEof, message: \"failed to fill whole buffer\" }, additional: 2 }")")', src\bin\sample\main.rs:113:70

stack backtrace:
0: 0x7ff61c56ffec - std::sys_common::backtrace::_print::impl$0::fmt
at /rustc/eb26296b556cef10fb713a38f3d16b9886080f26/library\std\src\sys_common\backtrace.rs:44
1: 0x7ff61c58831b - core::fmt::rt::Argument::fmt
at /rustc/eb26296b556cef10fb713a38f3d16b9886080f26/library\core\src\fmt\rt.rs:138
2: 0x7ff61c58831b - core::fmt::write
at /rustc/eb26296b556cef10fb713a38f3d16b9886080f26/library\core\src\fmt\mod.rs:1094
3: 0x7ff61c56d759 - std::io::Write::write_fmtstd::sys::windows::stdio::Stderr
at /rustc/eb26296b556cef10fb713a38f3d16b9886080f26/library\std\src\io\mod.rs:1713
4: 0x7ff61c56fd9b - std::sys_common::backtrace::_print
at /rustc/eb26296b556cef10fb713a38f3d16b9886080f26/library\std\src\sys_common\backtrace.rs:47
5: 0x7ff61c56fd9b - std::sys_common::backtrace::print
at /rustc/eb26296b556cef10fb713a38f3d16b9886080f26/library\std\src\sys_common\backtrace.rs:34
6: 0x7ff61c5725a9 - std::panicking::default_hook::closure$1
at /rustc/eb26296b556cef10fb713a38f3d16b9886080f26/library\std\src\panicking.rs:269
7: 0x7ff61c57225f - std::panicking::default_hook
at /rustc/eb26296b556cef10fb713a38f3d16b9886080f26/library\std\src\panicking.rs:288
8: 0x7ff61c572aae - std::panicking::rust_panic_with_hook
at /rustc/eb26296b556cef10fb713a38f3d16b9886080f26/library\std\src\panicking.rs:705
9: 0x7ff61c57299d - std::panicking::begin_panic_handler::closure$0
at /rustc/eb26296b556cef10fb713a38f3d16b9886080f26/library\std\src\panicking.rs:597
10: 0x7ff61c570969 - std::sys_common::backtrace::__rust_end_short_backtracestd::panicking::begin_panic_handler::closure_env$0,never$
at /rustc/eb26296b556cef10fb713a38f3d16b9886080f26/library\std\src\sys_common\backtrace.rs:151
11: 0x7ff61c5726a0 - std::panicking::begin_panic_handler
at /rustc/eb26296b556cef10fb713a38f3d16b9886080f26/library\std\src\panicking.rs:593
12: 0x7ff61c5f42c5 - core::panicking::panic_fmt
at /rustc/eb26296b556cef10fb713a38f3d16b9886080f26/library\core\src\panicking.rs:67
13: 0x7ff61c5f47d3 - core::result::unwrap_failed
at /rustc/eb26296b556cef10fb713a38f3d16b9886080f26/library\core\src\result.rs:1651
14: 0x7ff61c3cbaa7 - <burn_tch::backend::TchBackend as stablediffusion::backend::Backend>::qkv_attention::hdbe6096db726169c
15: 0x7ff61c3da1b6 - stablediffusion::model::autoencoder::Autoencoder::decode_latent::h3e800603716f0d65
16: 0x7ff61c3da1cc - std::rt::lang_start::{{closure}}::h34430c21a9efe000
17: 0x7ff61c568368 - std::rt::lang_start_internal::closure$2
at /rustc/eb26296b556cef10fb713a38f3d16b9886080f26/library\std\src\rt.rs:148
18: 0x7ff61c568368 - std::panicking::try::do_call
at /rustc/eb26296b556cef10fb713a38f3d16b9886080f26/library\std\src\panicking.rs:500
19: 0x7ff61c568368 - std::panicking::try
at /rustc/eb26296b556cef10fb713a38f3d16b9886080f26/library\std\src\panicking.rs:464
20: 0x7ff61c568368 - std::panic::catch_unwind
at /rustc/eb26296b556cef10fb713a38f3d16b9886080f26/library\std\src\panic.rs:142
21: 0x7ff61c568368 - std::rt::lang_start_internal
at /rustc/eb26296b556cef10fb713a38f3d16b9886080f26/library\std\src\rt.rs:148
22: 0x7ff61c3cda5c - main
23: 0x7ff61c5e5ba0 - invoke_main
at D:\a_work\1\s\src\vctools\crt\vcstartup\src\startup\exe_common.inl:78
24: 0x7ff61c5e5ba0 - __scrt_common_main_seh
at D:\a_work\1\s\src\vctools\crt\vcstartup\src\startup\exe_common.inl:288
25: 0x7ffdbd5d257d - BaseThreadInitThunk
26: 0x7ffdbe44aa78 - RtlUserThreadStart

tracel-ai/burn#243

Is possible to run stable-diffusion-xl-burn on AMD ?
https://pytorch.org/docs/stable/notes/hip.html

I can not figure out how to add negative prompts.
I would be excited to learn how to send a PR for that if you like.

Can you suggest some reading to help me learn about what's going on here?

I have worked in Rust a bit.
I need to understand the torch part.