big-sleep

big-sleep copied to clipboard

I fixed and improved the Colab Notebook overall immensely, with new features (mount gdrive) and explanations (afaik)

1

Talking about this notebook: https://colab.research.google.com/drive/1MEWKbm-driRNF8PrU7ogS5o3se-ePyPb?usp=sharing There were issues when using symbols like "\\" (for multiple phrases to be trained on) or any other symbol in the TEXT variable. I also...

LtqxWYEG

What GPU is required to run it ?

20

I tried executing the dream command on my laptop computer with a Quadro P2000 with 4 GB of vram. I got a CUDA out of memory error.

remdu

Run on multiply gpus

2

Hi ive tried to add multiply gpu support by nn.DataParallel Now its looks like this ` import os import sys import subprocess import signal import string import re from datetime...

AlexWortega

Hi There! I was wondering if you can input a specific file to the model (via dream.train_step()) each iteration, so effects like cropping can be applied between each iteration before...

Ednaordinary

Is it possible to run offline?

3

It appears to need internet connection, and i would like this to run offline. Is this currently possible?

odog8

Only possible run in colab or in Ubuntu droplet?

16

johnfelipe

RuntimeError: CUDA error: CUBLAS_STATUS_EXECUTION_FAILED when calling `cublasGemmEx( handle, opa, opb, m, n, k, &falpha, a, CUDA_R_16F, lda, b, CUDA_R_16F, ldb, &fbeta, c, CUDA_R_16F, ldc, CUDA_R_32F, CUBLAS_GEMM_DFALT_TENSOR_OP)`

7

I found an error `RuntimeError: CUDA error: CUBLAS_STATUS_EXECUTION_FAILED when calling `cublasGemmEx( handle, opa, opb, m, n, k, &falpha, a, CUDA_R_16F, lda, b, CUDA_R_16F, ldb, &fbeta, c, CUDA_R_16F, ldc, CUDA_R_32F, CUBLAS_GEMM_DFALT_TENSOR_OP)``...

LukeKnutson9

Save restore latent

4

A slight update to the latents functionality added by @LoudMurmur. This adds the arguments to the CLI, supports saving latents without also needing save_progress=True, and supports resetting the optimizer when...

wolfgangmeyers

If I interrupt the process in windows using CTRL+C and then attempt to run it again I get the following error `Imagining "Galaxy_of_ghosts" ... c:\programdata\anaconda3\lib\site-packages\torch\nn\functional.py:718: UserWarning: Named tensors and all...

vectris-dev

Sample results, Tooling on top of big-sleep

40

**big-sleep** is GORGEOUS. We need to explore what it can do, where it shines, and what to avoid. Adding a few pics down below, but I'm still in early experimentation...

enricoros