I am not as strong in ML engineering as I thought I was, so if someone can help me clarify what I am getting at or tell me where I am wrong in this explanation/approach, I would highly appreciate it and close the issue. The challenge is that image generation occurs over multiple iterations of the same base seeded image, essentially procedurally generates the next layer, so you can't neatly split the "dataset" like in other ML workloads.
Is there a way to map a single generation job across multiple, distributed or local, GPUs? This question has been raised in issues before, such as #24 and #47, but I want to bring it back. The hard part I have been trying to examine is the draw time. You can keep a map of active jobs on the visible GPUs and a queue of prompts to distribute among them, spinning up a new generate.py process for each available GPU. Parallel prompt generation is more straightforward to accomplish.
I want to be able to scale the image generation workload by either running multiple prompts simultaneously or pool the generation across multiple gpus to reduce the draw time to sub 5 minutes. This is quite a long runtime, especially with expensive AWS instances. The result is similar on P2.8XL instance, with 8 available GPUs. It takes at least 20 minutes to generate a default 512x512 image, and maybe 15 minutes to generate a 256x256 image on an AWS P2.XL instance. This is a fantastic tool! I've been using it to generate several one-off images and I'm excited to expand upon it and contribute in any way I can. Option two gets really long-winded once you want ALL args, and option one is overly simplistic and doesn't allow you to control the params going in well. Neither of these are tested yet as I'm just exploring concepts, what do you think is the best way? is there another way? Raise RuntimeError('Error(s) in loading state_dict for generate.py") Model = load_vqgan_model(args.vqgan_config, args.vqgan_checkpoint).to(device)įile "C:\Users\stiet\Desktop\Work\AIStuff\VQGAN-CLIP\generate.py", line 520, in load_vqgan_modelįile "C:\Users\stiet\anaconda3\envs\vqgan\lib\site-packages\taming\models\vqgan.py", line 48, in init_from_ckptįile "C:\Users\stiet\anaconda3\envs\vqgan\lib\site-packages\torch\nn\modules\module.py", line 1406, in load_state_dict VQLPIPSWithDiscriminator running with hinge loss.įile "C:\Users\stiet\Desktop\Work\AIStuff\VQGAN-CLIP\generate.py", line 546, in Loaded pretrained LPIPS loss from taming/modules/autoencoder/lpips\vgg.pth (vqgan) PS C:\Users\stiet\Desktop\Work\AIStuff\VQGAN-CLIP> python generate.py -p "A painting of an apple in a fruit bowl"
Simpleimage object has no attribute install#
I was able to install everything w/o any issues but when I try to run the example it bails out.
Simpleimage object has no attribute windows 10#
So I'm trying to be brave and set this up on my Windows 10 machine running Conda since my Titan RTX GPU is on that box. se DISPLAY_FREQ, -save_every DISPLAY_FREQ ckpt VQGAN_CHECKPOINT, -vqgan_checkpoint VQGAN_CHECKPOINT conf VQGAN_CONFIG, -vqgan_config VQGAN_CONFIG iw INIT_WEIGHT, -init_weight INIT_WEIGHT ip IMAGE_PROMPTS, -image_prompts IMAGE_PROMPTS i MAX_ITERATIONS, -iterations MAX_ITERATIONS h, -help show this help message and exit
0 kommentar(er)
