intel / intel/llm-scaler

LTX-2.3 can't run with llm-scaler-omni:0.1.0-b6

Open
#358 1 comment 0 reactions 1 assignee Claimed by @xiangyuT View on GitHub
Dominant language
C++
Stars
529
Forks
80
Avg merge
9h 7m
Merged PRs (30d)
38

Description

LTX-2.3 already released https://huggingface.co/Lightricks/LTX-2.3.
Load model will report below error:
```
CheckpointLoaderSimple
Error(s) in loading state_dict for LTXAVModel:
size mismatch for adaln_single.linear.bias: copying a param with shape torch.Size([36864]) from checkpoint, the shape in current model is torch.Size([24576]).
size mismatch for audio_adaln_single.linear.bias: copying a param with shape torch.Size([18432]) from checkpoint, the shape in current model is torch.Size([12288]).
size mismatch for transformer_blocks.0.scale_shift_table: copying a param with shape torch.Size([9, 4096]) from checkpoint, the shape in current model is torch.Size([6, 4096]).
```
Please refer to below workflow.
[LTX2.3-生视频.json](https://github.com/user-attachments/files/26774732/LTX2.3-.json)

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.