Open DirtyHamster opened 1 year ago
what about using the inpainting model as a
?
Similar errors: The order of the RuntimeError: The size of tensor a (4) must match the size of tensor b (9) at non-singleton dimension 1 swaps to RuntimeError: The size of tensor a (9) must match the size of tensor b (4) at non-singleton dimension 1
H:\Users\adamf\AI_Progs\sd-meh-merge\meh>merge_models.py -a H:\Users\adamf\AI_Progs\AI_Models\Stable_Diffusion\sd-v1-5-inpainting.ckpt -b H:\Users\adamf\AI_Progs\AI_Models\test\00-regit-nametolongmaster16_50prune.safetensors -m weighted_sum -p 32 -o H:\Users\adamf\AI_Progs\AI_Models\test\testggg -f safetensors -ba 0.5 -bb 0.5 -pr -rb -rbi 1
before loading models: 0.000
loading: H:\Users\adamf\AI_Progs\AI_Models\Stable_Diffusion\sd-v1-5-inpainting.ckpt
loading: H:\Users\adamf\AI_Progs\AI_Models\test\00-regit-nametolongmaster16_50prune.safetensors
models loaded: 0.000
permuting
0 iteration start: 0.000
weights & bases, before simple merge: 0.000
stage 1: 100%|████████████████████████████████████████████████████████████████████▉| 1130/1131 [02:47<00:00, 6.73it/s]
Traceback (most recent call last):
File "H:\Users\adamf\AI_Progs\sd-meh-merge\meh\merge_models.py", line 151, in
H:\Users\adamf\AI_Progs\sd-meh-merge\meh>merge_models.py -a H:\Users\adamf\AI_Progs\AI_Models\Stable_Diffusion\sd-v1-5-inpainting.ckpt -b H:\Users\adamf\AI_Progs\AI_Models\test\00-regit-nametolongmaster16_50prune.safetensors -m weighted_sum -p 32 -o H:\Users\adamf\AI_Progs\AI_Models\test\testggg -f safetensors -ba 0.5 -bb 0.5 -pr
before loading models: 0.000
loading: H:\Users\adamf\AI_Progs\AI_Models\Stable_Diffusion\sd-v1-5-inpainting.ckpt
loading: H:\Users\adamf\AI_Progs\AI_Models\test\00-regit-nametolongmaster16_50prune.safetensors
models loaded: 0.000
stage 1: 100%|███████████████████████████████████████████████████████████████████▉| 1130/1131 [00:05<00:00, 206.46it/s]
Traceback (most recent call last):
File "H:\Users\adamf\AI_Progs\sd-meh-merge\meh\merge_models.py", line 151, in
0.9.0 should fix this
Will check haven't had a chance to do so.. yet.
Part 1: The normal weighted sum worked as: merge_models.py -a H:\Users\adamf\AI_Progs\AI_Models\Stable_Diffusion\Reliberate-inpainting.safetensors -b H:\Users\adamf\AI_Progs\AI_Models\Stable_Diffusion\wd-ink-fp16.safetensors -m weighted_sum -p 16 -o H:\Users\adamf\AI_Progs\AI_Models\test\inpaintfp16test -f safetensors -ba 0.5 -bb 0.5 -pr
This now looks like it still have to test the file but want to run off the other pix2pix test first. Probably will not get to the file testing tonight though. I'll get through running off the pix2pix test though. Should I try reversing the models to see if it works as model b too?
Part 2: (Still get the re-basin error, If this is possible to fix it would be nice. If not at least the above works.) RB error: merge_models.py -a H:\Users\adamf\AI_Progs\AI_Models\Stable_Diffusion\Reliberate-inpainting.safetensors -b H:\Users\adamf\AI_Progs\AI_Models\Stable_Diffusion\wd-ink-fp16.safetensors -m weighted_sum -p 16 -o H:\Users\adamf\AI_Progs\AI_Models\test\inpaintfp16test -f safetensors -ba 0.5 -bb 0.5 -pr -rb -rbi 50
Starts and Returns:
INFO: Assembling alpha w&b INFO: base_alpha: 0.5 INFO: alpha weights: [0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5] INFO: Loading: H:\Users\adamf\AI_Progs\AI_Models\Stable_Diffusion\Reliberate-inpainting.safetensors INFO: Loading: H:\Users\adamf\AI_Progs\AI_Models\Stable_Diffusion\wd-ink-fp16.safetensors INFO: start merging with weighted_sum method INFO: Init rebasin iterations INFO: Rebasin iteration 0 stage 1: 34%|███████████████████████▋ | 388/1131 [00:02<00:04, 158.17it/s]model.diffusion_model.input_blocks.0.0.weight torch.Size([320, 9, 3, 3]) torch.Size([320, 4, 3, 3]) model.diffusion_model.input_blocks.1.1.proj_in.weight torch.Size([320, 320, 1, 1]) torch.Size([320, 320]) model.diffusion_model.input_blocks.1.1.proj_out.weight torch.Size([320, 320, 1, 1]) torch.Size([320, 320]) model.diffusion_model.input_blocks.1.1.transformer_blocks.0.attn2.to_k.weight torch.Size([320, 768]) torch.Size([320, 1024]) stage 1: 42%|████████████████████████████▋ | 470/1131 [00:03<00:05, 123.41it/s]model.diffusion_model.input_blocks.1.1.transformer_blocks.0.attn2.to_v.weight torch.Size([320, 768]) torch.Size([320, 1024]) model.diffusion_model.input_blocks.2.1.proj_in.weight torch.Size([320, 320, 1, 1]) torch.Size([320, 320]) stage 1: 46%|████████████████████████████████ | 518/1131 [00:05<00:09, 63.75it/s]model.diffusion_model.input_blocks.2.1.proj_out.weight torch.Size([320, 320, 1, 1]) torch.Size([320, 320]) model.diffusion_model.input_blocks.2.1.transformer_blocks.0.attn2.to_k.weight torch.Size([320, 768]) torch.Size([320, 1024]) model.diffusion_model.input_blocks.2.1.transformer_blocks.0.attn2.to_v.weight torch.Size([320, 768]) torch.Size([320, 1024]) stage 1: 48%|█████████████████████████████████▉ | 548/1131 [00:05<00:08, 68.14it/s]model.diffusion_model.input_blocks.4.1.proj_in.weight torch.Size([640, 640, 1, 1]) torch.Size([640, 640]) model.diffusion_model.input_blocks.4.1.proj_out.weight torch.Size([640, 640, 1, 1]) torch.Size([640, 640]) model.diffusion_model.input_blocks.4.1.transformer_blocks.0.attn2.to_k.weight torch.Size([640, 768]) torch.Size([640, 1024]) model.diffusion_model.input_blocks.4.1.transformer_blocks.0.attn2.to_v.weight torch.Size([640, 768]) torch.Size([640, 1024]) stage 1: 52%|████████████████████████████████████▌ | 590/1131 [00:06<00:08, 64.46it/s]model.diffusion_model.input_blocks.5.1.proj_in.weight torch.Size([640, 640, 1, 1]) torch.Size([640, 640]) model.diffusion_model.input_blocks.5.1.proj_out.weight torch.Size([640, 640, 1, 1]) torch.Size([640, 640]) model.diffusion_model.input_blocks.5.1.transformer_blocks.0.attn2.to_k.weight torch.Size([640, 768]) torch.Size([640, 1024]) stage 1: 53%|█████████████████████████████████████▍ | 604/1131 [00:06<00:08, 65.33it/s]model.diffusion_model.input_blocks.5.1.transformer_blocks.0.attn2.to_v.weight torch.Size([640, 768]) torch.Size([640, 1024]) stage 1: 55%|██████████████████████████████████████▋ | 626/1131 [00:07<00:09, 52.49it/s]model.diffusion_model.input_blocks.7.1.proj_in.weight torch.Size([1280, 1280, 1, 1]) torch.Size([1280, 1280]) stage 1: 56%|███████████████████████████████████████▏ | 634/1131 [00:07<00:12, 38.59it/s]model.diffusion_model.input_blocks.7.1.proj_out.weight torch.Size([1280, 1280, 1, 1]) torch.Size([1280, 1280]) stage 1: 57%|███████████████████████████████████████▌ | 640/1131 [00:08<00:14, 33.38it/s]model.diffusion_model.input_blocks.7.1.transformer_blocks.0.attn2.to_k.weight torch.Size([1280, 768]) torch.Size([1280, 1024]) model.diffusion_model.input_blocks.7.1.transformer_blocks.0.attn2.to_v.weight torch.Size([1280, 768]) torch.Size([1280, 1024]) stage 1: 59%|█████████████████████████████████████████▏ | 665/1131 [00:10<00:32, 14.46it/s]model.diffusion_model.input_blocks.8.1.proj_in.weight torch.Size([1280, 1280, 1, 1]) torch.Size([1280, 1280]) model.diffusion_model.input_blocks.8.1.proj_out.weight torch.Size([1280, 1280, 1, 1]) torch.Size([1280, 1280]) stage 1: 60%|█████████████████████████████████████████▊ | 675/1131 [00:10<00:25, 17.71it/s]model.diffusion_model.input_blocks.8.1.transformer_blocks.0.attn2.to_k.weight torch.Size([1280, 768]) torch.Size([1280, 1024]) stage 1: 60%|██████████████████████████████████████████ | 679/1131 [00:11<00:24, 18.77it/s]model.diffusion_model.input_blocks.8.1.transformer_blocks.0.attn2.to_v.weight torch.Size([1280, 768]) torch.Size([1280, 1024]) stage 1: 62%|███████████████████████████████████████████▌ | 703/1131 [00:13<00:40, 10.56it/s]model.diffusion_model.middle_block.1.proj_in.weight torch.Size([1280, 1280, 1, 1]) torch.Size([1280, 1280]) model.diffusion_model.middle_block.1.proj_out.weight torch.Size([1280, 1280, 1, 1]) torch.Size([1280, 1280]) stage 1: 63%|████████████████████████████████████████████▏ | 713/1131 [00:13<00:26, 15.71it/s]model.diffusion_model.middle_block.1.transformer_blocks.0.attn2.to_k.weight torch.Size([1280, 768]) torch.Size([1280, 1024]) stage 1: 63%|████████████████████████████████████████████▎ | 716/1131 [00:13<00:24, 17.11it/s]model.diffusion_model.middle_block.1.transformer_blocks.0.attn2.to_v.weight torch.Size([1280, 768]) torch.Size([1280, 1024]) stage 1: 69%|████████████████████████████████████████████████ | 777/1131 [00:19<00:22, 15.71it/s]model.diffusion_model.output_blocks.10.1.proj_in.weight torch.Size([320, 320, 1, 1]) torch.Size([320, 320]) model.diffusion_model.output_blocks.10.1.proj_out.weight torch.Size([320, 320, 1, 1]) torch.Size([320, 320]) model.diffusion_model.output_blocks.10.1.transformer_blocks.0.attn2.to_k.weight torch.Size([320, 768]) torch.Size([320, 1024]) model.diffusion_model.output_blocks.10.1.transformer_blocks.0.attn2.to_v.weight torch.Size([320, 768]) torch.Size([320, 1024]) stage 1: 72%|██████████████████████████████████████████████████▌ | 817/1131 [00:19<00:06, 51.44it/s]model.diffusion_model.output_blocks.11.1.proj_in.weight torch.Size([320, 320, 1, 1]) torch.Size([320, 320]) model.diffusion_model.output_blocks.11.1.proj_out.weight torch.Size([320, 320, 1, 1]) torch.Size([320, 320]) model.diffusion_model.output_blocks.11.1.transformer_blocks.0.attn2.to_k.weight torch.Size([320, 768]) torch.Size([320, 1024]) model.diffusion_model.output_blocks.11.1.transformer_blocks.0.attn2.to_v.weight torch.Size([320, 768]) torch.Size([320, 1024]) stage 1: 77%|█████████████████████████████████████████████████████▉ | 871/1131 [00:23<00:20, 12.90it/s]model.diffusion_model.output_blocks.3.1.proj_in.weight torch.Size([1280, 1280, 1, 1]) torch.Size([1280, 1280]) model.diffusion_model.output_blocks.3.1.proj_out.weight torch.Size([1280, 1280, 1, 1]) torch.Size([1280, 1280]) stage 1: 78%|██████████████████████████████████████████████████████▍ | 879/1131 [00:23<00:16, 15.48it/s]model.diffusion_model.output_blocks.3.1.transformer_blocks.0.attn2.to_k.weight torch.Size([1280, 768]) torch.Size([1280, 1024]) stage 1: 78%|██████████████████████████████████████████████████████▋ | 883/1131 [00:24<00:15, 15.66it/s]model.diffusion_model.output_blocks.3.1.transformer_blocks.0.attn2.to_v.weight torch.Size([1280, 768]) torch.Size([1280, 1024]) stage 1: 80%|████████████████████████████████████████████████████████ | 905/1131 [00:26<00:23, 9.60it/s]model.diffusion_model.output_blocks.4.1.proj_in.weight torch.Size([1280, 1280, 1, 1]) torch.Size([1280, 1280]) stage 1: 81%|████████████████████████████████████████████████████████▍ | 911/1131 [00:26<00:17, 12.58it/s]model.diffusion_model.output_blocks.4.1.proj_out.weight torch.Size([1280, 1280, 1, 1]) torch.Size([1280, 1280]) stage 1: 81%|████████████████████████████████████████████████████████▊ | 917/1131 [00:27<00:13, 15.49it/s]model.diffusion_model.output_blocks.4.1.transformer_blocks.0.attn2.to_k.weight torch.Size([1280, 768]) torch.Size([1280, 1024]) stage 1: 81%|█████████████████████████████████████████████████████████ | 921/1131 [00:27<00:11, 17.83it/s]model.diffusion_model.output_blocks.4.1.transformer_blocks.0.attn2.to_v.weight torch.Size([1280, 768]) torch.Size([1280, 1024]) stage 1: 83%|██████████████████████████████████████████████████████████▎ | 943/1131 [00:29<00:16, 11.07it/s]model.diffusion_model.output_blocks.5.1.proj_in.weight torch.Size([1280, 1280, 1, 1]) torch.Size([1280, 1280]) stage 1: 84%|██████████████████████████████████████████████████████████▋ | 949/1131 [00:29<00:12, 14.29it/s]model.diffusion_model.output_blocks.5.1.proj_out.weight torch.Size([1280, 1280, 1, 1]) torch.Size([1280, 1280]) stage 1: 84%|███████████████████████████████████████████████████████████ | 955/1131 [00:29<00:10, 17.20it/s]model.diffusion_model.output_blocks.5.1.transformer_blocks.0.attn2.to_k.weight torch.Size([1280, 768]) torch.Size([1280, 1024]) stage 1: 85%|███████████████████████████████████████████████████████████▎ | 959/1131 [00:29<00:08, 19.21it/s]model.diffusion_model.output_blocks.5.1.transformer_blocks.0.attn2.to_v.weight torch.Size([1280, 768]) torch.Size([1280, 1024]) stage 1: 87%|████████████████████████████████████████████████████████████▊ | 983/1131 [00:32<00:11, 13.37it/s]model.diffusion_model.output_blocks.6.1.proj_in.weight torch.Size([640, 640, 1, 1]) torch.Size([640, 640]) model.diffusion_model.output_blocks.6.1.proj_out.weight torch.Size([640, 640, 1, 1]) torch.Size([640, 640]) stage 1: 88%|█████████████████████████████████████████████████████████████▎ | 991/1131 [00:32<00:06, 20.31it/s]model.diffusion_model.output_blocks.6.1.transformer_blocks.0.attn2.to_k.weight torch.Size([640, 768]) torch.Size([640, 1024]) stage 1: 88%|█████████████████████████████████████████████████████████████▊ | 999/1131 [00:32<00:04, 27.40it/s]model.diffusion_model.output_blocks.6.1.transformer_blocks.0.attn2.to_v.weight torch.Size([640, 768]) torch.Size([640, 1024]) stage 1: 91%|██████████████████████████████████████████████████████████████▍ | 1024/1131 [00:32<00:03, 34.29it/s]model.diffusion_model.output_blocks.7.1.proj_in.weight torch.Size([640, 640, 1, 1]) torch.Size([640, 640]) model.diffusion_model.output_blocks.7.1.proj_out.weight torch.Size([640, 640, 1, 1]) torch.Size([640, 640]) stage 1: 91%|███████████████████████████████████████████████████████████████ | 1034/1131 [00:32<00:02, 46.34it/s]model.diffusion_model.output_blocks.7.1.transformer_blocks.0.attn2.to_k.weight torch.Size([640, 768]) torch.Size([640, 1024]) model.diffusion_model.output_blocks.7.1.transformer_blocks.0.attn2.to_v.weight torch.Size([640, 768]) torch.Size([640, 1024]) stage 1: 94%|████████████████████████████████████████████████████████████████▋ | 1061/1131 [00:33<00:01, 46.18it/s]model.diffusion_model.output_blocks.8.1.proj_in.weight torch.Size([640, 640, 1, 1]) torch.Size([640, 640]) model.diffusion_model.output_blocks.8.1.proj_out.weight torch.Size([640, 640, 1, 1]) torch.Size([640, 640]) model.diffusion_model.output_blocks.8.1.transformer_blocks.0.attn2.to_k.weight torch.Size([640, 768]) torch.Size([640, 1024]) stage 1: 95%|█████████████████████████████████████████████████████████████████▍ | 1073/1131 [00:33<00:00, 60.01it/s]model.diffusion_model.output_blocks.8.1.transformer_blocks.0.attn2.to_v.weight torch.Size([640, 768]) torch.Size([640, 1024]) stage 1: 97%|███████████████████████████████████████████████████████████████████ | 1099/1131 [00:34<00:00, 62.18it/s]model.diffusion_model.output_blocks.9.1.proj_in.weight torch.Size([320, 320, 1, 1]) torch.Size([320, 320]) model.diffusion_model.output_blocks.9.1.proj_out.weight torch.Size([320, 320, 1, 1]) torch.Size([320, 320]) model.diffusion_model.output_blocks.9.1.transformer_blocks.0.attn2.to_k.weight torch.Size([320, 768]) torch.Size([320, 1024]) model.diffusion_model.output_blocks.9.1.transformer_blocks.0.attn2.to_v.weight torch.Size([320, 768]) torch.Size([320, 1024]) stage 1: 100%|█████████████████████████████████████████████████████████████████████| 1131/1131 [00:34<00:00, 32.94it/s] stage 2: 100%|██████████████████████████████████████████████████████████████████| 1215/1215 [00:00<00:00, 28256.61it/s]
Traceback (most recent call last):
File "H:\Users\adamf\AI_Progs\sd-meh-merge\meh\merge_models.py", line 181, in
Run 1: H:\Users\adamf\AI_Progs\sd-meh-merge\meh>merge_models.py -a H:\Users\adamf\AI_Progs\AI_Models\test\00-regit-nametolongmaster4_50prune.safetensors -b H:\Users\adamf\AI_Progs\AI_Models\Stable_Diffusion\dreamshaper_7-inpainting.safetensors -m weighted_sum -p 32 -o H:\Users\adamf\AI_Progs\AI_Models\test\inpainttest -f safetensors -ba 0.5 -bb 0.5 -pr -rb -rbi 10
Run 2: without rebasin.
merge_models.py -a H:\Users\adamf\AI_Progs\AI_Models\test\00-regit-nametolongmaster4_50prune.safetensors -b H:\Users\adamf\AI_Progs\AI_Models\Stable_Diffusion\dreamshaper_7-inpainting.safetensors -m weighted_sum -p 32 -o H:\Users\adamf\AI_Progs\AI_Models\test\inpainttest -f safetensors -ba 0.5 -bb 0.5 -pr
Errors:
Run 1: before loading models: 0.000 loading: H:\Users\adamf\AI_Progs\AI_Models\test\00-regit-nametolongmaster4_50prune.safetensors loading: H:\Users\adamf\AI_Progs\AI_Models\Stable_Diffusion\dreamshaper_7-inpainting.safetensors models loaded: 0.000 permuting 0 iteration start: 0.000 weights & bases, before simple merge: 0.000 stage 1: 100%|████████████████████████████████████████████████████████████████████▉| 1130/1131 [01:15<00:00, 14.94it/s] Traceback (most recent call last): File "H:\Users\adamf\AI_Progs\sd-meh-merge\meh\merge_models.py", line 151, in
main()
File "C:\Users\adamf\AppData\Local\Programs\Python\Python310\lib\site-packages\click\core.py", line 1157, in call
return self.main(args, kwargs)
File "C:\Users\adamf\AppData\Local\Programs\Python\Python310\lib\site-packages\click\core.py", line 1078, in main
rv = self.invoke(ctx)
File "C:\Users\adamf\AppData\Local\Programs\Python\Python310\lib\site-packages\click\core.py", line 1434, in invoke
return ctx.invoke(self.callback, ctx.params)
File "C:\Users\adamf\AppData\Local\Programs\Python\Python310\lib\site-packages\click\core.py", line 783, in invoke
return __callback(args, kwargs)
File "H:\Users\adamf\AI_Progs\sd-meh-merge\meh\merge_models.py", line 132, in main
merged = merge_models(
File "H:\Users\adamf\AI_Progs\sd-meh-merge\meh\sd_meh\merge.py", line 146, in merge_models
merged = rebasin_merge(
File "H:\Users\adamf\AI_Progs\sd-meh-merge\meh\sd_meh\merge.py", line 286, in rebasin_merge
thetas["model_a"] = simple_merge(
File "H:\Users\adamf\AI_Progs\sd-meh-merge\meh\sd_meh\merge.py", line 244, in simple_merge
res.result()
File "C:\Users\adamf\AppData\Local\Programs\Python\Python310\lib\concurrent\futures_base.py", line 451, in result
return self.get_result()
File "C:\Users\adamf\AppData\Local\Programs\Python\Python310\lib\concurrent\futures_base.py", line 403, in get_result
raise self._exception
File "C:\Users\adamf\AppData\Local\Programs\Python\Python310\lib\concurrent\futures\thread.py", line 58, in run
result = self.fn(*self.args, *self.kwargs)
File "H:\Users\adamf\AI_Progs\sd-meh-merge\meh\sd_meh\merge.py", line 342, in simple_merge_key
with merge_key_context(key, thetas, args, kwargs) as result:
File "C:\Users\adamf\AppData\Local\Programs\Python\Python310\lib\contextlib.py", line 135, in enter
return next(self.gen)
File "H:\Users\adamf\AI_Progs\sd-meh-merge\meh\sd_meh\merge.py", line 428, in merge_key_context
result = merge_key(args, kwargs)
File "H:\Users\adamf\AI_Progs\sd-meh-merge\meh\sd_meh\merge.py", line 403, in merge_key
merged_key = merge_method(merge_args).to(storage_device)
File "H:\Users\adamf\AI_Progs\sd-meh-merge\meh\sd_meh\merge_methods.py", line 27, in weighted_sum
return (1 - alpha) a + alpha * b
RuntimeError: The size of tensor a (4) must match the size of tensor b (9) at non-singleton dimension 1
Run 2:
before loading models: 0.000 loading: H:\Users\adamf\AI_Progs\AI_Models\test\00-regit-nametolongmaster4_50prune.safetensors loading: H:\Users\adamf\AI_Progs\AI_Models\Stable_Diffusion\dreamshaper_7-inpainting.safetensors models loaded: 0.000 stage 1: 100%|███████████████████████████████████████████████████████████████████▉| 1130/1131 [00:06<00:00, 185.51it/s] Traceback (most recent call last): File "H:\Users\adamf\AI_Progs\sd-meh-merge\meh\merge_models.py", line 151, in
main()
File "C:\Users\adamf\AppData\Local\Programs\Python\Python310\lib\site-packages\click\core.py", line 1157, in call
return self.main(args, kwargs)
File "C:\Users\adamf\AppData\Local\Programs\Python\Python310\lib\site-packages\click\core.py", line 1078, in main
rv = self.invoke(ctx)
File "C:\Users\adamf\AppData\Local\Programs\Python\Python310\lib\site-packages\click\core.py", line 1434, in invoke
return ctx.invoke(self.callback, ctx.params)
File "C:\Users\adamf\AppData\Local\Programs\Python\Python310\lib\site-packages\click\core.py", line 783, in invoke
return __callback(args, kwargs)
File "H:\Users\adamf\AI_Progs\sd-meh-merge\meh\merge_models.py", line 132, in main
merged = merge_models(
File "H:\Users\adamf\AI_Progs\sd-meh-merge\meh\sd_meh\merge.py", line 162, in merge_models
merged = simple_merge(
File "H:\Users\adamf\AI_Progs\sd-meh-merge\meh\sd_meh\merge.py", line 244, in simple_merge
res.result()
File "C:\Users\adamf\AppData\Local\Programs\Python\Python310\lib\concurrent\futures_base.py", line 451, in result
return self.get_result()
File "C:\Users\adamf\AppData\Local\Programs\Python\Python310\lib\concurrent\futures_base.py", line 403, in get_result
raise self._exception
File "C:\Users\adamf\AppData\Local\Programs\Python\Python310\lib\concurrent\futures\thread.py", line 58, in run
result = self.fn(*self.args, *self.kwargs)
File "H:\Users\adamf\AI_Progs\sd-meh-merge\meh\sd_meh\merge.py", line 342, in simple_merge_key
with merge_key_context(key, thetas, args, kwargs) as result:
File "C:\Users\adamf\AppData\Local\Programs\Python\Python310\lib\contextlib.py", line 135, in enter
return next(self.gen)
File "H:\Users\adamf\AI_Progs\sd-meh-merge\meh\sd_meh\merge.py", line 428, in merge_key_context
result = merge_key(args, kwargs)
File "H:\Users\adamf\AI_Progs\sd-meh-merge\meh\sd_meh\merge.py", line 403, in merge_key
merged_key = merge_method(merge_args).to(storage_device)
File "H:\Users\adamf\AI_Progs\sd-meh-merge\meh\sd_meh\merge_methods.py", line 27, in weighted_sum
return (1 - alpha) a + alpha * b
RuntimeError: The size of tensor a (4) must match the size of tensor b (9) at non-singleton dimension 1