Open
Conversation
csgoogle
force-pushed
the
sagarchapara/wananimate-pipeline
branch
from
67233e9 to
e281524
Compare
csgoogle
force-pushed
the
sagarchapara/wananimate-pipeline
branch
from
e281524 to
349d080
Compare
csgoogle
commented
Apr 13, 2026
| sigmas = 1.0 - alphas | ||
| sigmas = jnp.flip(self.config.flow_shift * sigmas / (1 + (self.config.flow_shift - 1) * sigmas))[:-1].copy() | ||
| timesteps = (sigmas * self.config.num_train_timesteps).copy().astype(jnp.int64) | ||
| sigmas = jnp.linspace(1.0, 1.0 / self.config.num_train_timesteps, num_inference_steps + 1)[:-1] |
Collaborator
Author
There was a problem hiding this comment.
converging it with hf implementation, lmk if I need to revert it
Perseus14
reviewed
Apr 13, 2026
| sigmas = self.config.flow_shift * sigmas / (1 + (self.config.flow_shift - 1) * sigmas) | ||
| eps = 1e-6 | ||
| sigmas = sigmas.at[0].set(jnp.where(jnp.abs(sigmas[0] - 1.0) < eps, sigmas[0] - eps, sigmas[0])) | ||
| timesteps = (sigmas * self.config.num_train_timesteps).copy().astype(jnp.int32) |
Collaborator
There was a problem hiding this comment.
Why move from jnp.int64 to jnp.int32?
Collaborator
Author
There was a problem hiding this comment.
timestamps are sufficient to be in int32, so casted to int32 only
Perseus14
reviewed
Apr 13, 2026
Collaborator
There was a problem hiding this comment.
Could we move the assets to a public GCS path or use an existing hf dataset link?
Perseus14
reviewed
Apr 18, 2026
Comment on lines
+960
to
+993
| noise_pred = animate_transformer_forward_pass( | ||
| graphdef, | ||
| state, | ||
| rest_of_state, | ||
| seg_latents, | ||
| reference_latents, | ||
| pose_latents, | ||
| face_seg, | ||
| timestep, | ||
| prompt_embeds, | ||
| image_embeds, | ||
| motion_encode_batch_size=motion_encode_batch_size, | ||
| ) | ||
|
|
||
| if do_classifier_free_guidance: | ||
| # Blank face pixels (all -1) for the unconditional pass. | ||
| face_seg_uncond = face_seg * 0 - 1 | ||
| noise_uncond = animate_transformer_forward_pass( | ||
| graphdef, | ||
| state, | ||
| rest_of_state, | ||
| seg_latents, | ||
| reference_latents, | ||
| pose_latents, | ||
| face_seg_uncond, | ||
| timestep, | ||
| negative_prompt_embeds, | ||
| image_embeds, | ||
| motion_encode_batch_size=motion_encode_batch_size, | ||
| ) | ||
| noise_pred = noise_uncond + guidance_scale * (noise_pred - noise_uncond) | ||
|
|
||
| noise_pred = noise_pred.astype(seg_latents.dtype) | ||
| seg_latents, scheduler_state = self.scheduler.step(scheduler_state, noise_pred, t, seg_latents, return_dict=False) |
Collaborator
| sigmas = 1.0 - alphas | ||
| sigmas = jnp.flip(self.config.flow_shift * sigmas / (1 + (self.config.flow_shift - 1) * sigmas))[:-1].copy() | ||
| timesteps = (sigmas * self.config.num_train_timesteps).copy().astype(jnp.int64) | ||
| sigmas = jnp.linspace(1.0, 1.0 / self.config.num_train_timesteps, num_inference_steps + 1)[:-1] |
| f"{_frame_summary('mask', mask_video)}" | ||
| ) | ||
|
|
||
| animate_settings = _get_animate_inference_settings(config) |
Collaborator
There was a problem hiding this comment.
Could you also add lora support?
Collaborator
There was a problem hiding this comment.
I wonder if there is a need for a separate generate script? Can we add this to existing generate_wan.py file?
Collaborator
|
Please resolve conflicts and enable support for diagnostics and profiling as in this PR |
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.
Wan Animate Pipeline
This CL publishes add the Wan Animate pipepline.
Links
Performance
Configuration