mirror of
https://github.com/AcademiaSD/sd-forge-fluxtools-v2.git
synced 2026-11-04 23:27:24 +00:00
[GH-ISSUE #3] Some kind of error #1
Loading…
Add table
Add a link
Reference in a new issue
No description provided.
Delete branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Originally created by @Rolf-100R on GitHub (Apr 12, 2025).
Original GitHub issue: https://github.com/AcademiaSD/sd-forge-fluxtools-v2/issues/3
It didn't work for me:
in the terminal the entry
RuntimeError: mat1 and mat2 shapes cannot be multiplied (1024x128 and 64x3072)
mat1 and mat2 shapes cannot be multiplied (1024x128 and 64x3072)
Can you tell me what this means?
@AcademiaSD commented on GitHub (Apr 13, 2025):
When this error appears, it means that you have not selected the corresponding checkpoint.
@Rolf-100R commented on GitHub (Apr 14, 2025):
Thank you so much for your reply! But... retirement age and humanitarian education make me terribly stupid - I didn't understand anything from the answer. What does “appropriate reference point” mean in this case? What are we talking about? In Checkpoint I have flux1-dev-bnb-nf4-v2.safetensors selected. If I select flux1-Depth-Dev_FP8.safetensors, it says AssertionError: You do not have CLIP state dict!
@AcademiaSD commented on GitHub (Apr 14, 2025):
Watch this explanatory video https://www.youtube.com/watch?v=MHYSFBkF36s
@Rolf-100R commented on GitHub (Apr 14, 2025):
I have now installed the new version of stable-diffusion-webui-forge on a new disk
I didn't update the old version because one of the updates removed the Sampling flux realistic from Sampling flux
On the new version, I went through all the steps in your video. It doesn't work.
The VAE / Text Encoder tab does not open, although text_encoders_FP8 was extracted to the diffusers folder.
Result: AssertionError: You do not have CLIP state dict!
File "G:\Forge\webui\backend\loader.py", line 62, in load_huggingface_component
assert isinstance(state_dict, dict) and len(state_dict) > 16, 'You do not have CLIP state dict!'
AssertionError: You do not have CLIP state dict!
@Rolf-100R commented on GitHub (Apr 15, 2025):
Thank you very much for your work! I was not very attentive, but I figured out my problem.
I did not have
ae.safetensors
clip_l.safetensors
t5xxl_fp8_e4m3fn.safetensors
That's why nothing worked. I downloaded the missing models and everything worked.
Thanks again!