[Text Pipeline] Implement Embedding Connector#338
Open
syhuang22 wants to merge 2 commits intoAI-Hypercomputer:mainfrom
Open
[Text Pipeline] Implement Embedding Connector#338syhuang22 wants to merge 2 commits intoAI-Hypercomputer:mainfrom
syhuang22 wants to merge 2 commits intoAI-Hypercomputer:mainfrom
Conversation
|
Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA). View this failed invocation of the CLA check for more information. For the most up to date status, view the checks section at the bottom of the pull request. |
syhuang22
force-pushed
the
feat/ltx2-embedding-connector
branch
from
e656273 to
099551b
Compare
Signed-off-by: James Huang <syhuang1201@gmail.com>
syhuang22
force-pushed
the
feat/ltx2-embedding-connector
branch
from
099551b to
7747a33
Compare
prishajain1
reviewed
Feb 26, 2026
| rngs=rngs, | ||
| ) | ||
| self.ff = NNXSimpleFeedForward(rngs=rngs, dim=dim, dim_out=dim) | ||
| self.norm1 = nnx.RMSNorm(dim, epsilon=1e-6, dtype=jnp.float32, param_dtype=jnp.float32, use_scale=True, rngs=rngs) |
Collaborator
There was a problem hiding this comment.
Diffusers uses elementwise_affine = False
https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/ltx2/connectors.py#L112
We should set use_scale = False
prishajain1
reviewed
Feb 26, 2026
| ) | ||
| self.ff = NNXSimpleFeedForward(rngs=rngs, dim=dim, dim_out=dim) | ||
| self.norm1 = nnx.RMSNorm(dim, epsilon=1e-6, dtype=jnp.float32, param_dtype=jnp.float32, use_scale=True, rngs=rngs) | ||
| self.norm2 = nnx.RMSNorm(dim, epsilon=1e-6, dtype=jnp.float32, param_dtype=jnp.float32, use_scale=True, rngs=rngs) |
prishajain1
reviewed
Feb 26, 2026
| ) | ||
|
|
||
| self.final_norm = nnx.RMSNorm( | ||
| self.dim, epsilon=1e-6, dtype=jnp.float32, param_dtype=jnp.float32, use_scale=True, rngs=rngs |
Collaborator
There was a problem hiding this comment.
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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.
This module acts as the crucial bridge in the LTX-2 text pipeline, responsible for processing and aligning the text embeddings (after feature extraction) before they are fed into the main diffusion model.