Add transfer support to the Cosmos3 modular pipeline

[yzhautouskay]

What does this PR do?

Adds the transfer (structure-controlled) path to the Cosmos3 Modular pipeline (Cosmos3OmniModularPipeline / Cosmos3OmniBlocks), letting users condition video generation on one or more control videos (segmentation, depth, edge/canny, blur, world-scenario map) in addition to the text prompt. This mirrors the transfer path in the task-based Cosmos3OmniPipeline and is element-wise consistent with it

What this adds

• A transfer workflow for the modular pipeline, triggered automatically when control_videos is passed -- no new pipeline class, it coexists with the existing modular modes (text2image, text2video, image2video, video2video, action, sound).
• Transfer is implemented as first-class modular blocks (matching how the existing modalities are built), not a monolithic step:
  • text: Cosmos3TransferTextStep
  • before-denoise: Cosmos3TransferSetupStep, Cosmos3TransferPrepareLatentsStep, Cosmos3TransferPackSequenceStep, Cosmos3TransferSetTimestepsStep
  • denoise: per-chunk loop blocks (Cosmos3TransferChunkVaeEncoderStep -> prepare -> denoise -> scheduler), with the denoiser consuming the packed static contexts through the shared denoiser_input_fields mechanism
  • decode: Cosmos3TransferDecodeChunkStep, Cosmos3TransferStitchStep
  • composed/wired in modular_blocks_cosmos3.py via the Auto* blocks (selected on control_videos), with "transfer" added to available_workflows.

How it works

The pipeline accepts a control_videos mapping ({hint: video}); each control clip is VAE-encoded and injected as an additional clean conditioning item before the noisy target during denoising, so generated frames follow the control's spatial structure while the prompt drives appearance. A separate control_guidance (and optional control_guidance_interval) scales how strongly the structural signal is enforced, independently of the text guidance_scale, via a nested control/text CFG blend. It runs in V2V mode with num_conditional_frames priming frames, generating long clips autoregressively in chunks of num_video_frames_per_chunk and stitching them into a temporally coherent multi-second clip

Supported hints

edge, blur, depth, seg, wsm

Notes for reviewers

This PR is stacked on the Cosmos3 modular pipeline PR 14110 the diff here is transfer-only relative to that branch. It will be rebased onto main once the modular PR merges.

Before submitting

• Did you use an AI agent (Claude Code, Codex, Cursor, etc.) to help with this PR? If so:
  • Did you read the Coding with AI agents guide?
  • Did you self-review the diff against .ai/review-rules.md?
• Did you read the contributor guideline?
• Did you read our philosophy doc? (important for complex PRs)
• Was this discussed/approved via a GitHub issue or the forum? Please add a link to it if that's the case.
• Did you make sure to update the documentation with your changes? Here are the
  documentation guidelines, and
  here are tips on formatting docstrings.
• Did you write any new necessary tests?
• Are you the author (or part of the team) of the model/pipeline (only applicable for model/pipeline related PRs)?

Who can review?

Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.