assert c_adm is not None AssertionError

[aliendaniel]

/ldm/models/diffusion/ddpm.py", line 1346, in forward assert c_adm is not None AssertionError

[aliendaniel]

Creating invisible watermark encoder (see https://github.com/ShieldMnt/invisible-watermark)... Sampling: 0%| | 0/3 [00:00<?, ?it/sData shape for DDIM sampling is (3, 4, 96, 96), eta 0.0 | 0/1 [00:00<?, ?it/s] Running DDIM Sampling with 50 timesteps DDIM Sampler: 0%| | 0/50 [00:00<?, ?it/s] data: 0%| | 0/1 [12:34<?, ?it/s] Sampling: 0%| | 0/3 [12:34<?, ?it/s] Traceback (most recent call last): File "txt2img.py", line 388, in main(opt) File "txt2img.py", line 347, in main samples, _ = sampler.sample(S=opt.steps, File "/opt/anaconda3/lib/python3.8/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context return func(*args, **kwargs) File "/Users/xuanwu/Desktop/StableDiffusion/stablediffusion-main/ldm/models/diffusion/ddim.py", line 104, in sample samples, intermediates = self.ddim_sampling(conditioning, size, File "/opt/anaconda3/lib/python3.8/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context return func(*args, **kwargs) File "/Users/xuanwu/Desktop/StableDiffusion/stablediffusion-main/ldm/models/diffusion/ddim.py", line 164, in ddim_sampling outs = self.p_sample_ddim(img, cond, ts, index=index, use_original_steps=ddim_use_original_steps, File "/opt/anaconda3/lib/python3.8/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context return func(*args, **kwargs) File "/Users/xuanwu/Desktop/StableDiffusion/stablediffusion-main/ldm/models/diffusion/ddim.py", line 212, in p_sample_ddim model_uncond, model_t = self.model.apply_model(x_in, t_in, c_in).chunk(2) File "/Users/xuanwu/Desktop/StableDiffusion/stablediffusion-main/ldm/models/diffusion/ddpm.py", line 858, in apply_model x_recon = self.model(x_noisy, t, **cond) File "/opt/anaconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl return forward_call(*input, **kwargs) File "/Users/xuanwu/Desktop/StableDiffusion/stablediffusion-main/ldm/models/diffusion/ddpm.py", line 1346, in forward assert c_adm is not None AssertionError

[Jayyyyyyyyyyyy]

same question

[gitgotcha77]

Happens to me too. Windows 11, WSL2, Python 3.9.16. My package list:

albumentations                 1.3.0         pyhd8ed1ab_0                 conda-forge
gradio                         3.23.0        pyhd8ed1ab_0                 conda-forge
kornia                         0.6.11        pyhd8ed1ab_0                 conda-forge
omegaconf                      2.3.0         pyhd8ed1ab_0                 conda-forge
open-clip-torch                2.7.0         pyhd8ed1ab_0                 conda-forge
opencv                         4.7.0         py39hf3d152e_1               conda-forge
pytorch                        1.13.1        py3.9_cuda11.7_cudnn8.5.0_0  pytorch
pytorch-cuda                   11.7          h778d358_3                   pytorch
pytorch-lightning              1.4.9         pyhd8ed1ab_0                 conda-forge
pytorch-mutex                  1.0           cuda                         pytorch
sentencepiece                  0.1.96        py39hf939315_1               conda-forge
torchaudio                     0.13.1        py39_cu117                   pytorch
torchdata                      0.5.1         py39hebc40ba_1               conda-forge
torchmetrics                   0.7.3         pyhd8ed1ab_0                 conda-forge
torchtext                      0.6.0         py_1                         pytorch
torchvision                    0.14.1        py39_cu117                   pytorch
tqdm                           4.65.0        pyhd8ed1ab_1                 conda-forge
transformers                   4.19.4        pyhd8ed1ab_0                 conda-forge
webdataset                     0.2.48        pyhd8ed1ab_0                 conda-forge
xformers                       0.0.16        py39h4b4f3f3_2               conda-forge

[fairleehu]

i have the same question,do you solve it?

[zzxgdh]

it doesn't work when using v2-1-stable-unclip-l-inference.yaml, but v2-inference-v.yaml is finished.ckpt is --ckpt models/v2-1_768-ema-pruned.ckpt

[Morinage]

it doesn't work when using v2-1-stable-unclip-l-inference.yaml, but v2-inference-v.yaml is finished.ckpt is --ckpt models/v2-1_768-ema-pruned.ckpt

thankyou！