by the way, i love our content, learned a ton from you. thanks
by the way, i love our content, learned a ton from you. thanks
Fthank you so much
Fi never trained
Fbut you can achieve that in 1 training
Fput all images into same folder
Fenable bucketing
Fdifferent resolutions
SAnyone look into Stable Cascade yet?
Fyou mean training?
SJust in general, I heard something about them limiting it vs other models
PFloat16
PFloat8
Fi think no quality loss
Fbut float8 must be slower
P15.6s 30steps
Ffp16?
Pfloat8
Pfloat16 15.8s haha
Fwow nice
Fon llms
Fthere is huge difference
Fdid you see reduced vram?
Finteresting
PFloat 8 EulerDiscreter 30steps 15.6, Average image time: 15.6 Max. memory used: 7.1 GB with TyneVaeEncoder.
Fauto1111 changed output folder name :d
Ffrom outputs to output
Piam not testing in A1111
Psorry now i fixed fp8 in diffusers
P18.8s
P15.8s fp16
Fok this looks more accurate
Pwow 4.6GB
Pin cuda
Pwithout cpu offload
Pi will enable cpu offload to see how much will decrease
Fso we can apply this to instant id?=
Pno benefit with cpu offload for just one image, in fact it increased the time to 20s, memory remains the same.
PI think that because I can only apply float8 to unet and in cpu offload, unet is already the only one that remains in the cuda, so nothing changes if the memory consumption is lower than the total available of the video card.
Pwe need test,
Pi dont tested with controlnet yet
PFloat 8 + freeu we recover the quality result
Pbut increase inference to 19.2
Pnow fp8 + freeu + deep cache 9.3s inference
Pbut images changes
VHi Furkan, possible to change the modified date on your patreon posts when you edit the post?
VWhen viewing chronologically, I find a post from mid 2023 that was commented on a couple of weeks ago. But if I had not been paying attention to the notifications on my email i wouldnt have known.
Fi wish patreon had added it
Fbut i have last updated date here
FGitHub
Stable Diffusion, SDXL, LoRA Training, DreamBooth Training, Automatic1111 Web UI, DeepFake, Deep Fakes, TTS, Animation, Text To Video, Tutorials, Guides, Lectures, Courses, ComfyUI, Google Colab, R...
Fi sort here my self