Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

ValueError: too many values to unpack (expected 3) #27

Open
nitinmukesh opened this issue Nov 7, 2024 · 0 comments
Open

ValueError: too many values to unpack (expected 3) #27

nitinmukesh opened this issue Nov 7, 2024 · 0 comments

Comments

@nitinmukesh
Copy link

C:\ai\FancyVideo\FV_venv\Lib\site-packages\diffusers\schedulers\scheduling_ddim.py:142: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
  self.betas = torch.tensor(trained_betas, dtype=torch.float32)
load scheduler done

load text_encoder done

>>VAE<< resources/models/stable-diffusion-v1-5
load vae done

unet_additional_kwargs =  {'use_motion_module': True, 'motion_module_resolutions': [1, 2, 4, 8], 'unet_use_cross_frame_attention': False, 'unet_use_temporal_attention': False, 'motion_module_type': 'Vanilla', 'motion_module_kwargs': {'num_attention_heads': 8, 'num_transformer_block': 1, 'attention_block_types': ['Temporal_Self', 'Temporal_Self'], 'temporal_position_encoding': True, 'temporal_position_encoding_max_len': 32, 'temporal_attention_dim_div': 1, 'zero_initialize': True}, 'use_inflated_groupnorm': True, 'motion_module_mid_block': True, 'motion_module_decoder_only': False, 'emu_mask': True, 'in_channels': 9, 'use_fps_embedding': True, 'use_motion_embedding': True}
Unet init from resources/models/stable-diffusion-v1-5\unet\diffusion_pytorch_model.bin done!
### missing keys: 594;
### unexpected keys: 0;
### Temporal Module Parameters: 453.20928 M
### Unet All Module Parameters: 1313.566404 M
load unet done

load base model from resources/models/sd_v1-5_base_models/realisticVisionV60B1_v51VAE.safetensors...
unet load base model done
missing keys num 594 ; unexpected keys num 0
text_encoder load base model done
missing keys num 0 ; unexpected keys num 0
vae load base model done
missing keys num 0 ; unexpected keys num 0
load base model done

res_adapter_type =  res_adapter_v2
lora_weights_path =  resources/models/res-adapter/resadapter_v2_sd1.5/pytorch_lora_weights.safetensors
lora_norm_path =  resources/models/res-adapter/resadapter_v2_sd1.5/diffusion_pytorch_model.safetensors
load lora weights missing keys num 1278 ; unexpect keys num 6
load norm weights missing keys num 1202 ; unexpect keys num 0
load res_adapter done

load unet missing keys num =  697
load unet unexpected keys num =  0
text_to_video_unet load motion module from resources/models/fancyvideo_ckpts/vae_3d_61_frames/mp_rank_00_model_states.pt
text_to_video_unet init done

load text_to_video_pipeline done

Init fancyvideo infer pipeline done!

infer_mode =  i2v
processing 1/1
prompt =  Teddy bear walking down 5th Avenue, front view, beautiful sunset, close up, high definition, 4k.
dst_path =  resources/demos/samples/i2v/realisticVisionV60B1_v51VAE/512x512/example_0.mp4
positive prompt =  Teddy bear walking down 5th Avenue, front view, beautiful sunset, close up, high definition, 4k.,Best quality, masterpiece, ultra high res, photorealistic, Ultra realistic illustration, hyperrealistic, 8k
negative prompt =  (low quality:1.3), (worst quality:1.3),poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face,Facial blurring,a large crowd, many people,advertising, information, news, watermark, text, username, signature,out of frame, low res, error, cropped, worst quality, low quality, artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck, nsfw, breast, naked, eroticism
Generate reference_image ...
Generate reference_image done!
Generate video ...
100%|█████████████████████████████████████████████████████████████████████████████████| 50/50 [01:53<00:00,  2.26s/it]
>>Post processing starting<<
Generate video done!
Traceback (most recent call last):
  File "C:\ai\FancyVideo\scripts\demo.py", line 86, in <module>
    main(args)
  File "C:\ai\FancyVideo\FV_venv\Lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "C:\ai\FancyVideo\scripts\demo.py", line 67, in main
    reference_image, video, prompt = infer_pipeline.t2v_process_one_prompt(prompt=prompt, reference_image_path=reference_image_path, seed=seed, video_length=video_length, resolution=resolution, use_noise_scheduler_snr=use_noise_scheduler_snr, fps=cond_fps, motion_score=cond_motion_score,)
    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: too many values to unpack (expected 3)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant