rabidcopy

It's kinda fun to have Flux cause issues for people not even inferencing it. Everything was fine before it was implemented. Oh well.

Cascade is still 1.5-2 seconds per iteration slower on DirectML on a 4GB RX 570. I don't expect a meaningful fix because DirectML support feels a bit like an afterthought...

> Edit2: [d420bc7](https://github.com/comfyanonymous/ComfyUI/commit/d420bc792af0b61a6ef7410c65fa2d4dcc646c56) is the exact commit that I start having speed degradation on Cascade. My speed and OOM issue goes away on latest commit simply reverting `model_base.py` to https://github.com/comfyanonymous/ComfyUI/raw/1589b58d3e29e44623a1f3f595917b98f2301c3e/comfy/model_base.py...

Just adding this also seems to be the case for me. Loras applied in ComfyUI don't match how the lora is expected to perform. Seems very weak. Same lora applied...

Wanted to add 83f3431 also resolved the issue I had. Not sure if https://github.com/comfyanonymous/ComfyUI/commit/bb222ceddb232aafafa99cd4dec38b3719c29d7d was still necessary. (haven't tried it)

Can't say I can reproduce the missing/black materials on my RX 570, though performance of the game does seem a bit rough. Long pauses/loading between pausing and unpausing the game....

Possibly not enough RAM/swap/pagefile to load the model at the given precision? Usually when a process is "Killed" in Linux, it's to prevent an out of memory situation that would...

Then I can only suggest running `git reflog` and go back on commits until it works again. It should be fairly easy to determine which commit issues started.

Alternatively the problem may be occurring by being on a commit that came just before https://github.com/comfyanonymous/ComfyUI/commit/b334605a6631c12bbe7b3aff6d77526f47acdf42 as this commit addresses OOMs dealing with erroneous model loading.

Generally negative prompts are ineffective on Hyper/Turbo/Lightning models with the exception of the CFG-preserved Hyper-SD loras which are meant to be used with non-1 CFG. At 1 CFG negative prompts...