add WAN2.1-I2V model modules #400
Open
+4,151
−0
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
xiao-yu-chen
requested review from
liutongxuan,
xiao-yu-chen,
yq33victor and
z-jun03
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
The umt5_encoder.h and clip_vision_model.h modules have been registered as VLM models and tested, but issues were encountered during testing:
umt5_encoder.h error: engine.h:47 kv_cache_manager_ is not BlockManagerPool type!
clip_vision_model.h error: utils.cpp:32 Check failed: weight.sizes() == tensor.sizes() ([0, 1280] vs. [1280, 1280]) weight size mismatch for vision_model.encoder.layers.0.self_attn.q_proj.weight
The other three modules (autoencoder_kl_wan.h, dit_wan.h, and unipc_multistep_scheduler.h) have not been tested yet. Additionally, the overall pipeline for the WAN model has not been implemented.