Jonathan

After setting determinism on with `torch.use_deterministic_algorithms(True)` and doing as the error message suggests, images generated in succession are identical to each other, and image generation times look to be maybe...

On the plus side, even with those deterministic algorithms in use, I can now generate *really* large images until I get to the decoding step.

Maybe somewhere in `CLI.py` (or another place/places), we do: `os.environ["CUBLAS_WORKSPACE_CONFIG"] = ":4096:8"`? As long as that hits before torch and friends load up, I imagine that will work.

> There's been no activity on the PR for several days. Seems to me we should just go ahead with this? I thought you disliked non-deterministic behavior? I think we...

@psychedelicious @lstein We need to do more than that just to get deterministic behavior - and we should have the option to do so. See above. All of this makes...

I've also noticed that negative prompt weights can result in images that resemble noise or have other strange artifacts. Since I'm useless at GitHub, I'm proposing my patch here: ```...

See #56

The same has happened to me: ```^CTraceback (most recent call last): File "/mnt/AI/InvokeAI3/.venv/bin/invokeai-web", line 12, in sys.exit(run_app()) ^^^^^^^^^ File "/mnt/AI/InvokeAI3/src/invokeai/app/run_app.py", line 86, in run_app loop.run_until_complete(server.serve()) File "/mnt/AI/InvokeAI3/uv/python/cpython-3.11.11-linux-x86_64-gnu/lib/python3.11/asyncio/base_events.py", line 641, in...

Setting the minimum dimension to 512 produces duplication and other artifacts when your target image is extra wide, e.g. 2.4:1 aspect. Exposing the multiplier makes far more sense to me...

> In the case of such aspect ratios, where the larger side of the initial image needs to exceed 768 pixels in order to keep the smaller side at 512,...