stable-diffusion-webui-forge icon indicating copy to clipboard operation
stable-diffusion-webui-forge copied to clipboard

Forge crashes with Flux dev on 3090

Open vitangames opened this issue 1 year ago • 6 comments

I have RTX 3090 with 24gb vram and 32gb of RAM. Any other UIs are working perfectly well, but I cannot make forge working. I`ve tried changing GPU Weights to 23000, but no luck - the same error. Please help.

Here`s my setting: image

and here`s the error I get: image

vitangames avatar Sep 23 '24 17:09 vitangames

Refer to: https://github.com/lllyasviel/stable-diffusion-webui-forge/discussions/981

Haoming02 avatar Sep 24 '24 01:09 Haoming02

Keep the GPU weights about 23500, and check if your Page File settings in windows allows for about 40GB, or set to auto management but expect this sort of size or more.

HMRMike avatar Sep 24 '24 12:09 HMRMike

@HMRMike thanks. Works now, but speed is very low. In ComfyUI 1 image in 20 steps take 45 sec, here it takes a couple of minutes, while system moves models and stuff to free memory. That`s odd.

vitangames avatar Sep 24 '24 17:09 vitangames

@HMRMike thanks. Works now, but speed is very low. In ComfyUI 1 image in 20 steps take 45 sec, here it takes a couple of minutes, while system moves models and stuff to free memory. That`s odd.

The initial loading+first image do take a while. I tested right now with a 3090 also- (with t5 GGUF Q8 instead of fp8) and it indeed took 2:20 min. for 1024X1024 at 20 steps. But subsequent images will be faster. Changing the prompt completely- finished an image in1 minute. Different seeds per same prompt took at most 41 sec. I don't know how comfy manages that stuff but It would be quite a feat if it did all that initial loading twice as fast

HMRMike avatar Sep 24 '24 21:09 HMRMike

You can also try https://github.com/Juqowel/GPU_For_T5 for speed up second+ image with cpu load. But t5 gguf - unsupported.

Juqowel avatar Sep 26 '24 06:09 Juqowel

Keep the GPU weights about 23500, and check if your Page File settings in windows allows for about 40GB, or set to auto management but expect this sort of size or more.

bummmer, i did a w hole installation on COMFY UI to test and compare to FORGE using FLUX DEV fp8 and GGUF q8, and FORGE renders wayyyy faster for about 6/23 seconds per iteration and comfy was 9 seconds per iteration !!!

LIQUIDMIND111 avatar Sep 26 '24 20:09 LIQUIDMIND111