De-Anime-er Reviews

For some reason the lycoris does not work. ''got prompt model weight dtype torch.bfloat16, manual cast: torch.float32 model_type EPS Using pytorch attention in VAE Using pytorch attention in VAE VAE load device: cuda:0, offload device: cpu, dtype: torch.float32 Requested to load SD1ClipModel loaded completely 9.5367431640625e+25 235.84423828125 True CLIP/text encoder model load device: cpu, offload device: cpu, current: cpu, dtype: torch.float16 [load_lora] Detected ai-toolkit model (OSTRIS). Enabling ostris_fallback mode. Starting load_lora with 2719 layers to process Failed to load LyCORIS /home/silananda/comfy/ComfyUI/models/loras/de-anime-er_v10.safetensors: shape '[320, 2880, 3, 3]' is invalid for input of size 921600 Traceback (most recent call last): File "/home/silananda/comfy/ComfyUI/custom_nodes/comfyui-lycoris/node/lycoris_loader.py", line 120, in load_lycoris loaded = load_lora(lora_data, key_map, lycoris_type) File "/home/silananda/comfy/ComfyUI/custom_nodes/comfyui-lycoris/module/load_lora.py", line 275, in load_lora diff_tensor = diff_tensor.reshape(out_ch, in_ch, kernel_size, kernel_size) RuntimeError: shape '[320, 2880, 3, 3]' is invalid for input of size 921600 Requested to load SD1ClipModel Requested to load BaseModel loaded partially 749.86201171875 749.8614501953125 0 100%|███████████████████████████████████████████| 20/20 [08:01<00:00, 24.05s/it] --- VAE Decode Switcher --- Selected Decoder: tiled Executing Tiled VAE Decode. Requested to load AutoencoderKL 0 models unloaded. loaded partially 128.0 127.99989318847656 0 Tiled decoding successful. Prompt executed in 561.00 seconds''