no CLIP/text encoder weights in checkpoint

#13
by likuangyu - opened

Hello, when I use ComfyUI to run the stable diffusion-3.5-large turbo model, it prompts me "no CLIP/text encoder weights in checkpoint, the text encoder model will not be loaded". How can I solve this problem? I hope to get help. Thank you

i have the same question . i download the modles file and put these 3 files into the /model/Clip and /model/Clipversion folder . but confyui workflow didnt find them and gave the samew Error meaasge.

I have the same problem as above. Please help.

i have the same question +1

same here

I am having the exact same problem here. My GPU is RTX5070. The ComfyUI installed is "ComfyUI_windows_portable_nvidia_or_cpu_nightly_pytorch". Tried using both 3.5 large and 3.5 large turbo, but the problem is basically the same. "no CLIP/text encoder weights in checkpoint, the text encoder model will not be loaded.
CLIP/text encoder model load device: cuda:0, offload device: cpu, current: cpu, dtype: torch.float16
clip missing: ['text_projection.weight']
Requested to load SD3ClipModel_
loaded completely 9511.8 6102.49609375 True
Requested to load SD3
loaded partially 9451.674980926513 9447.805786132812 0"
CAN ANYBODY HELP? THANKS IN ADVANCE!

Your need to confirm your account before you can post a new comment.

Sign up or log in to comment