diffusers_stablediff_conversion

diffusers_stablediff_conversion copied to clipboard

``` loading diff model from 'D:\\_SD\\_to convert\\classic-anim-diffusion' Cannot initialize model with low cpu memory usage because `accelerate` was not found in the environment. Defaulting to `low_cpu_mem_usage=False`. It is strongly recommended...

Corshi


ZeroCool22

Loading model from models/ldm/stable-diffusion-v1/model.ckpt Traceback (most recent call last): File ".\optimizedSD\txt2img_gradio.py", line 46, in sd = load_model_from_config(f"{ckpt}") File ".\optimizedSD\txt2img_gradio.py", line 38, in load_model_from_config pl_sd = torch.load(ckpt, map_location="cpu") File "C:\Users\ferna\AppData\Roaming\Python\Python38\site-packages\torch\serialization.py", line...

foxxfiles

Fix the error when it converts safetensors

1

Sort output_block_list before checking it in unet_state_dict Fixes: ```text Missing key(s) in state_dict: "up_blocks.0.upsamplers.0.conv.weight", "up_blocks.0.upsamplers.0.conv.bias", "up_blocks.1.upsamplers.0.conv.weight", "up_blocks.1.upsamplers.0.conv.bias", "up_blocks.2.upsamplers.0.conv.weight", "up_blocks.2.upsamplers.0.conv.bias" ```

rodjjo