I assume the PyTorch_Cuda_Alloc_Config command needs to be added before starting SD and not during X
I assume the PyTorch_Cuda_Alloc_Config command needs to be added before starting SD and not during XD
Fyes. this is for low vram problem having people
GI am now following your guide to the letter incuding the images. I will train styles later
GThese images that are being sampled do not seem right
GI am expecting images of me or is this not the case?
GThe face and hair looks kinda like me.. Am I being hopfull XD
G
G
GI am getting really cool accurate ish looking images
Fgreat
Fi added a spanish subtitle can anyone test it who knows spanish? https://www.youtube.com/watch?v=m-UVVY_syP0
YouTubeSECourses - Software Engineering Courses
RunPod: https://bit.ly/RunPodIO. Discord : https://bit.ly/SECoursesDiscord. Get your own #Midjourney level model for free via Style Teaching. If I have been of assistance to you and you would like to show your support for my work, please consider becoming a patron on 
https://www.patreon.com/SECourses
Playlist of #StableDiffusion Tutorials, Au...
https://www.patreon.com/SECoursesPlaylist of #StableDiffusion Tutorials, Au...
Fnow translating to french
SI let my embed run all night and it is still a monster! This is tough.
Fcould be overtraining. you are following this video right? https://www.youtube.com/watch?v=dNOpWt-epdQ
YouTubeSECourses - Software Engineering Courses
Our Discord : https://discord.gg/HbqgGaZVmr. Grand Master tutorial for Textual Inversion / Text Embeddings. If I have been of assistance to you and you would like to show your support for my work, please consider becoming a patron on https://www.patreon.com/SECourses
Playlist of Stable Diffusion Tutorials, Automatic1111 and Google Colab Guide...
https://www.patreon.com/SECoursesPlaylist of Stable Diffusion Tutorials, Automatic1111 and Google Colab Guide...
G@Furkan Gözükara SECourses The command you gave does not seem to wrk
Fwhich one
G
G
Galso, with Lora my face does not look close to as good as your images you get to generate. I will now try with normal Dreambooth without Lora and then try the XYZ picking
Fyou need to put set to front
Fdreambooth better than lora
SI could not find an embedding video from you! Hooray I am saved. Thank you!
F
KHi, i'm having issues with setting up xformers with the A5000 GPU in SD Dreambooth
Whenever i click Generate Class Images i'm getting :
Exception generating concepts: No operator found for memory_efficient_attention_forward with inputs: query : shape=(1, 2, 1, 40) (torch.float32) key : shape=(1, 2, 1, 40) (torch.float32) value : shape=(1, 2, 1, 40) (torch.float32) attn_bias : p : 0.0 flshattF is not supported because: xFormers wasn't build with CUDA support dtype=torch.float32 (supported: {torch.bfloat16, torch.float16}) tritonflashattF is not supported because: xFormers wasn't build with CUDA support dtype=torch.float32 (supported: {torch.bfloat16, torch.float16}) triton is not available requires A100 GPU cutlassF is not supported because: xFormers wasn't build with CUDA support smallkF is not supported because: xFormers wasn't build with CUDA support max(query.shape[-1] != value.shape[-1]) > 32 unsupported embed per head: 40
I've set everything based on your youtube tutorial here https://www.youtube.com/watch?v=Bdl-jWR3Ukc&t=158s
Whenever i click Generate Class Images i'm getting :
Exception generating concepts: No operator found for memory_efficient_attention_forward with inputs: query : shape=(1, 2, 1, 40) (torch.float32) key : shape=(1, 2, 1, 40) (torch.float32) value : shape=(1, 2, 1, 40) (torch.float32) attn_bias : p : 0.0 flshattF is not supported because: xFormers wasn't build with CUDA support dtype=torch.float32 (supported: {torch.bfloat16, torch.float16}) tritonflashattF is not supported because: xFormers wasn't build with CUDA support dtype=torch.float32 (supported: {torch.bfloat16, torch.float16}) triton is not available requires A100 GPU cutlassF is not supported because: xFormers wasn't build with CUDA support smallkF is not supported because: xFormers wasn't build with CUDA support max(query.shape[-1] != value.shape[-1]) > 32 unsupported embed per head: 40
I've set everything based on your youtube tutorial here https://www.youtube.com/watch?v=Bdl-jWR3Ukc&t=158s
Fgenerate class images with txt2img
Fmuch faster better
GWith or without the --
Fi think like this can you test?
Gdoes not work
Gwith the --
Fthere is no -- the command.
Gtrying without the --. I thought that is how the args are being separated
Gnope
Gdoes not work
Flet me show you
Fyou are writing incorrectly
Goh
GI see now
Gahahah
F
GYup
GI was being stupid
Gfingers crossed this works
Gthen I will try train again with drambooth, set some checkpoints and then XYZ select from the checkpoints
Fi think dreambooth still wouldnt work on 8 gb :d
Fbut worth to try let me know
Gwill do
GI am just finding that runpod is harder than running it locally on windows
Gbut I don't get close to the image quality your SD is producing
KOn text2img im still getting the same error
NotImplementedError: No operator found for
Time taken: 1.82sTorch active/reserved: 2230/2246 MiB, Sys VRAM: 3577/24257 MiB (14.75%)
What could be wrong? I'm using SD 1.5.ckpt, and probably the text2img has nothing to do with Dreambooth
NotImplementedError: No operator found for
memory_efficient_attention_forward with inputs: query : shape=(2, 4096, 8, 40) (torch.float16) key : shape=(2, 4096, 8, 40) (torch.float16) value : shape=(2, 4096, 8, 40) (torch.float16) attn_bias : <class 'NoneType'> p : 0.0 cutlassF is not supported because: xFormers wasn't build with CUDA support flshattF is not supported because: xFormers wasn't build with CUDA support tritonflashattF is not supported because: xFormers wasn't build with CUDA support triton is not available requires A100 GPU smallkF is not supported because: xFormers wasn't build with CUDA support dtype=torch.float16 (supported: {torch.float32}) max(query.shape[-1] != value.shape[-1]) > 32 unsupported embed per head: 40Time taken: 1.82sTorch active/reserved: 2230/2246 MiB, Sys VRAM: 3577/24257 MiB (14.75%)
What could be wrong? I'm using SD 1.5.ckpt, and probably the text2img has nothing to do with Dreambooth
Kpython: 3.10.6 • torch: 1.13.1+cu117 • xformers: 0.0.17+6d62b0e.d20230322 • gradio: 3.16.2 • commit: a9fed7c3 • checkpoint: 4c86efd062
I'm currently new to this, apologies if i ask pretty basic questions.
I'm currently new to this, apologies if i ask pretty basic questions.
