Video generation is very slow on my Windows 11, WSL Ubuntu 24.04, RTX 4060 Ti (16GB)
You wrote "It can generate a 5-second 480P video on an RTX 4090 in about 4 minutes (without optimization techniques like quantization). Its performance is even comparable to some closed-source models."
Ok, I have a RTX 4060 Ti (16GB) only, but for me it takes 4,5 hours instead of 4 minutes (I tested it twice). Any known reason for that?
Windows 11, WSL: Ubuntu 24.04
python generate.py --task t2v-1.3B --size 832480 --ckpt_dir ./Wan2.1-T2V-1.3B --sample_shift 8 --sample_guide_scale 6 --prompt "Two anthropomorphic cats in comfy boxing gear and bright gloves fight intensely on a spotlighted stage."
[2025-04-21 17:44:15,009] INFO: offload_model is not specified, set to True.
[2025-04-21 17:44:15,010] INFO: Generation job args: Namespace(task='t2v-1.3B', size='832480', frame_num=81, ckpt_dir='./Wan2.1-T2V-1.3B', offload_model=True, ulysses_size=1, ring_size=1, t5_fsdp=False, t5_cpu=False, dit_fsdp=False, save_file=None, prompt='Two anthropomorphic cats in comfy boxing gear and bright gloves fight intensely on a spotlighted stage.', use_prompt_extend=False, prompt_extend_method='local_qwen', prompt_extend_model=None, prompt_extend_target_lang='zh', base_seed=7970858068020314444, image=None, first_frame=None, last_frame=None, sample_solver='unipc', sample_steps=50, sample_shift=8.0, sample_guide_scale=6.0)
[2025-04-21 17:44:15,010] INFO: Generation model config: {'name': 'Config: Wan T2V 1.3B', 't5_model': 'umt5_xxl', 't5_dtype': torch.bfloat16, 'text_len': 512, 'param_dtype': torch.bfloat16, 'num_train_timesteps': 1000, 'sample_fps': 16, 'sample_neg_prompt': '色调艳丽，过曝，静态，细节模糊不清，字幕，风格，作品，画作，画面，静止，整体发灰，最差质量，低质量，JPEG压缩残留，丑陋的，残缺的，多余的手指，画得不好的手部，画得不好的脸部，畸形的，毁容的，形态畸形的肢体，手指融合，静止不动的画面，杂乱的背景，三条腿，背景人很多，倒着走', 't5_checkpoint': 'models_t5_umt5-xxl-enc-bf16.pth', 't5_tokenizer': 'google/umt5-xxl', 'vae_checkpoint': 'Wan2.1_VAE.pth', 'vae_stride': (4, 8, 8), 'patch_size': (1, 2, 2), 'dim': 1536, 'ffn_dim': 8960, 'freq_dim': 256, 'num_heads': 12, 'num_layers': 30, 'window_size': (-1, -1), 'qk_norm': True, 'cross_attn_norm': True, 'eps': 1e-06}
[2025-04-21 17:44:15,010] INFO: Input prompt: Two anthropomorphic cats in comfy boxing gear and bright gloves fight intensely on a spotlighted stage.
[2025-04-21 17:44:15,010] INFO: Creating WanT2V pipeline.
[2025-04-21 17:46:53,460] INFO: loading ./Wan2.1-T2V-1.3B/models_t5_umt5-xxl-enc-bf16.pth
[2025-04-21 17:49:09,329] INFO: loading ./Wan2.1-T2V-1.3B/Wan2.1_VAE.pth
[2025-04-21 17:49:17,266] INFO: Creating WanModel from ./Wan2.1-T2V-1.3B
[2025-04-21 17:50:29,129] INFO: Generating video ...
100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████| 50/50 [4:27:12<00:00, 320.65s/it]
[2025-04-21 22:19:24,331] INFO: Saving generated video to t2v-1.3B_832*480_1_1_Two_anthropomorphic_cats_in_comfy_boxing_gear_and__20250421_221924.mp4
[2025-04-21 22:19:26,610] INFO: Finished.