* add guidance rescale
* update docs
* support adaptive instance norm filter
* fix custom timesteps support
* add custom timestep example to docs
* add a note about best generation settings being available only in the original repository
* use original org hub ids instead of personal
* make fix-copies
---------
Co-authored-by: Linoy Tsaban <57615435+linoytsaban@users.noreply.github.com>
* begin transformer conversion
* refactor
* refactor
* refactor
* refactor
* refactor
* refactor
* update
* add conversion script
* add pipeline
* make fix-copies
* remove einops
* update docs
* gradient checkpointing
* add transformer test
* update
* debug
* remove prints
* match sigmas
* add vae pt. 1
* finish CV* vae
* update
* update
* update
* update
* update
* update
* make fix-copies
* update
* make fix-copies
* fix
* update
* update
* make fix-copies
* update
* update tests
* handle device and dtype for safety checker; required in latest diffusers
* remove enable_gqa and use repeat_interleave instead
* enforce safety checker; use dummy checker in fast tests
* add review suggestion for ONNX export
Co-Authored-By: Asfiya Baig <asfiyab@nvidia.com>
* fix safety_checker issues when not passed explicitly
We could either do what's done in this commit, or update the Cosmos examples to explicitly pass the safety checker
* use cosmos guardrail package
* auto format docs
* update conversion script to support 14B models
* update name CosmosPipeline -> CosmosTextToWorldPipeline
* update docs
* fix docs
* fix group offload test failing for vae
---------
Co-authored-by: Asfiya Baig <asfiyab@nvidia.com>
* Refactor `LTXConditionPipeline` to add text-only conditioning
* style
* up
* Refactor `LTXConditionPipeline` to streamline condition handling and improve clarity
* Improve condition checks
* Simplify latents handling based on conditioning type
* Refactor rope_interpolation_scale preparation for clarity and efficiency
* Update LTXConditionPipeline docstring to clarify supported input types
* Add LTX Video 0.9.5 model to documentation
* Clarify documentation to indicate support for text-only conditioning without passing `conditions`
* refactor: comment out unused parameters in LTXConditionPipeline
* fix: restore previously commented parameters in LTXConditionPipeline
* fix: remove unused parameters from LTXConditionPipeline
* refactor: remove unnecessary lines in LTXConditionPipeline
* minor documentation fixes of the depth and normals pipelines
* update license headers
* update model checkpoints in examples
fix missing prediction_type in register_to_config in the normals pipeline
* add initial marigold intrinsics pipeline
update comments about num_inference_steps and ensemble_size
minor fixes in comments of marigold normals and depth pipelines
* update uncertainty visualization to work with intrinsics
* integrate iid
---------
Co-authored-by: YiYi Xu <yixu310@gmail.com>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
* init
* encode with glm
* draft schedule
* feat(scheduler): Add CogView scheduler implementation
* feat(embeddings): add CogView 2D rotary positional embedding
* 1
* Update pipeline_cogview4.py
* fix the timestep init and sigma
* update latent
* draft patch(not work)
* fix
* [WIP][cogview4]: implement initial CogView4 pipeline
Implement the basic CogView4 pipeline structure with the following changes:
- Add CogView4 pipeline implementation
- Implement DDIM scheduler for CogView4
- Add CogView3Plus transformer architecture
- Update embedding models
Current limitations:
- CFG implementation uses padding for sequence length alignment
- Need to verify transformer inference alignment with Megatron
TODO:
- Consider separate forward passes for condition/uncondition
instead of padding approach
* [WIP][cogview4][refactor]: Split condition/uncondition forward pass in CogView4 pipeline
Split the forward pass for conditional and unconditional predictions in the CogView4 pipeline to match the original implementation. The noise prediction is now done separately for each case before combining them for guidance. However, the results still need improvement.
This is a work in progress as the generated images are not yet matching expected quality.
* use with -2 hidden state
* remove text_projector
* 1
* [WIP] Add tensor-reload to align input from transformer block
* [WIP] for older glm
* use with cogview4 transformers forward twice of u and uc
* Update convert_cogview4_to_diffusers.py
* remove this
* use main example
* change back
* reset
* setback
* back
* back 4
* Fix qkv conversion logic for CogView4 to Diffusers format
* back5
* revert to sat to cogview4 version
* update a new convert from megatron
* [WIP][cogview4]: implement CogView4 attention processor
Add CogView4AttnProcessor class for implementing scaled dot-product attention
with rotary embeddings for the CogVideoX model. This processor concatenates
encoder and hidden states, applies QKV projections and RoPE, but does not
include spatial normalization.
TODO:
- Fix incorrect QKV projection weights
- Resolve ~25% error in RoPE implementation compared to Megatron
* [cogview4] implement CogView4 transformer block
Implement CogView4 transformer block following the Megatron architecture:
- Add multi-modulate and multi-gate mechanisms for adaptive layer normalization
- Implement dual-stream attention with encoder-decoder structure
- Add feed-forward network with GELU activation
- Support rotary position embeddings for image tokens
The implementation follows the original CogView4 architecture while adapting
it to work within the diffusers framework.
* with new attn
* [bugfix] fix dimension mismatch in CogView4 attention
* [cogview4][WIP]: update final normalization in CogView4 transformer
Refactored the final normalization layer in CogView4 transformer to use separate layernorm and AdaLN operations instead of combined AdaLayerNormContinuous. This matches the original implementation but needs validation.
Needs verification against reference implementation.
* 1
* put back
* Update transformer_cogview4.py
* change time_shift
* Update pipeline_cogview4.py
* change timesteps
* fix
* change text_encoder_id
* [cogview4][rope] align RoPE implementation with Megatron
- Implement apply_rope method in attention processor to match Megatron's implementation
- Update position embeddings to ensure compatibility with Megatron-style rotary embeddings
- Ensure consistent rotary position encoding across attention layers
This change improves compatibility with Megatron-based models and provides
better alignment with the original implementation's positional encoding approach.
* [cogview4][bugfix] apply silu activation to time embeddings in CogView4
Applied silu activation to time embeddings before splitting into conditional
and unconditional parts in CogView4Transformer2DModel. This matches the
original implementation and helps ensure correct time conditioning behavior.
* [cogview4][chore] clean up pipeline code
- Remove commented out code and debug statements
- Remove unused retrieve_timesteps function
- Clean up code formatting and documentation
This commit focuses on code cleanup in the CogView4 pipeline implementation, removing unnecessary commented code and improving readability without changing functionality.
* [cogview4][scheduler] Implement CogView4 scheduler and pipeline
* now It work
* add timestep
* batch
* change convert scipt
* refactor pt. 1; make style
* refactor pt. 2
* refactor pt. 3
* add tests
* make fix-copies
* update toctree.yml
* use flow match scheduler instead of custom
* remove scheduling_cogview.py
* add tiktoken to test dependencies
* Update src/diffusers/models/embeddings.py
Co-authored-by: YiYi Xu <yixu310@gmail.com>
* apply suggestions from review
* use diffusers apply_rotary_emb
* update flow match scheduler to accept timesteps
* fix comment
* apply review sugestions
* Update src/diffusers/schedulers/scheduling_flow_match_euler_discrete.py
Co-authored-by: YiYi Xu <yixu310@gmail.com>
---------
Co-authored-by: 三洋三洋 <1258009915@qq.com>
Co-authored-by: OleehyO <leehy0357@gmail.com>
Co-authored-by: Aryan <aryan@huggingface.co>
Co-authored-by: YiYi Xu <yixu310@gmail.com>
* Add IP-Adapter example to Flux docs
* Apply suggestions from code review
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
* Update hunyuan_video.md to rectify the checkpoint id
* bfloat16
* more fixes
* don't update the checkpoint ids.
* update
* t -> T
* Apply suggestions from code review
* fix
---------
Co-authored-by: YiYi Xu <yixu310@gmail.com>
Fix argument name in 8bit quantized example
Found a tiny mistake in the documentation where the text encoder model was passed to the wrong argument in the FluxPipeline.from_pretrained function.
