-
Notifications
You must be signed in to change notification settings - Fork 5.9k
Raise warning and round down if Wan num_frames is not 4k + 1 #11167
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Pull Request Overview
This pull request ensures that the number of frames passed to the WAN pipelines follows the required format (4 * k + 1).
- In src/diffusers/pipelines/wan/pipeline_wan_i2v.py, the num_frames parameter is added to the function signature and validated.
- In src/diffusers/pipelines/wan/pipeline_wan.py, similar changes are applied to enforce the frame constraint.
Reviewed Changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated 1 comment.
File | Description |
---|---|
src/diffusers/pipelines/wan/pipeline_wan_i2v.py | Added num_frames parameter and validation logic to enforce 4*k+1. |
src/diffusers/pipelines/wan/pipeline_wan.py | Updated function signatures and added the same num_frames check to ensure consistency. |
Comments suppressed due to low confidence (1)
src/diffusers/pipelines/wan/pipeline_wan_i2v.py:331
- Consider adding a check that num_frames is greater than or equal to 1 to ensure the validation accurately reflects a 4*k + 1 form where k >= 0.
if num_frames % 4 != 1:
@@ -265,12 +265,15 @@ def check_inputs( | |||
negative_prompt, | |||
height, | |||
width, | |||
num_frames, | |||
prompt_embeds=None, | |||
negative_prompt_embeds=None, | |||
callback_on_step_end_tensor_inputs=None, | |||
): | |||
if height % 16 != 0 or width % 16 != 0: | |||
raise ValueError(f"`height` and `width` have to be divisible by 16 but are {height} and {width}.") |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Consider enforcing that num_frames is at least 1 before applying the modulo check to handle negative values appropriately.
raise ValueError(f"`height` and `width` have to be divisible by 16 but are {height} and {width}.") | |
raise ValueError(f"`height` and `width` have to be divisible by 16 but are {height} and {width}.") | |
if num_frames < 1: | |
raise ValueError("`num_frames` must be at least 1") |
Copilot is powered by AI, so mistakes are possible. Review output carefully before use.
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
@DN6 I've updated the PR to round down and raise a warning if num_frames is not of the form 4 * k + 1 instead of raising an error as discussed |
* Raise warning and round down if Wan num_frames is not 4k + 1 (huggingface#11167) * update * raise warning and round to nearest multiple of scale factor * [Docs] Fix environment variables in `installation.md` (huggingface#11179) * Add `latents_mean` and `latents_std` to `SDXLLongPromptWeightingPipeline` (huggingface#11034) * Bug fix in LTXImageToVideoPipeline.prepare_latents() when latents is already set (huggingface#10918) * Bug fix in ltx * Assume packed latents. --------- Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com> Co-authored-by: YiYi Xu <yixu310@gmail.com> * [tests] no hard-coded cuda (huggingface#11186) no cuda only * [WIP] Add Wan Video2Video (huggingface#11053) * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * map BACKEND_RESET_MAX_MEMORY_ALLOCATED to reset_peak_memory_stats on XPU (huggingface#11191) Signed-off-by: YAO Matrix <matrix.yao@intel.com> * fix autocast (huggingface#11190) Signed-off-by: jiqing-feng <jiqing.feng@intel.com> * fix: for checking mandatory and optional pipeline components (huggingface#11189) fix: optional componentes verification on load * remove unnecessary call to `F.pad` (huggingface#10620) * rewrite memory count without implicitly using dimensions by @ic-synth * replace F.pad by built-in padding in Conv3D * in-place sums to reduce memory allocations * fixed trailing whitespace * file reformatted * in-place sums * simpler in-place expressions * removed in-place sum, may affect backward propagation logic * removed in-place sum, may affect backward propagation logic * removed in-place sum, may affect backward propagation logic * reverted change * allow models to run with a user-provided dtype map instead of a single dtype (huggingface#10301) * allow models to run with a user-provided dtype map instead of a single dtype * make style * Add warning, change `_` to `default` * make style * add test * handle shared tensors * remove warning --------- Co-authored-by: Sayak Paul <spsayakpaul@gmail.com> * [tests] HunyuanDiTControlNetPipeline inference precision issue on XPU (huggingface#11197) * add xpu part * fix more cases * remove some cases * no canny * format fix * Revert `save_model` in ModelMixin save_pretrained and use safe_serialization=False in test (huggingface#11196) * [docs] `torch_dtype` map (huggingface#11194) * Fix enable_sequential_cpu_offload in CogView4Pipeline (huggingface#11195) * Fix enable_sequential_cpu_offload in CogView4Pipeline * make fix-copies * SchedulerMixin from_pretrained and ConfigMixin Self type annotation (huggingface#11192) * Update import_utils.py (huggingface#10329) added onnxruntime-vitisai for custom build onnxruntime pkg * Add CacheMixin to Wan and LTX Transformers (huggingface#11187) * update * update * update * feat: [Community Pipeline] - FaithDiff Stable Diffusion XL Pipeline (huggingface#11188) * feat: [Community Pipeline] - FaithDiff Stable Diffusion XL Pipeline for Image SR. * added pipeline * [Model Card] standardize advanced diffusion training sdxl lora (huggingface#7615) * model card gen code * push modelcard creation * remove optional from params * add import * add use_dora check * correct lora var use in tags * make style && make quality --------- Co-authored-by: Aryan <aryan@huggingface.co> Co-authored-by: Sayak Paul <spsayakpaul@gmail.com> * Change KolorsPipeline LoRA Loader to StableDiffusion (huggingface#11198) Change LoRA Loader to StableDiffusion Replace the SDXL LoRA Loader Mixin inheritance with the StableDiffusion one * Update Style Bot workflow (huggingface#11202) update style bot workflow --------- Signed-off-by: YAO Matrix <matrix.yao@intel.com> Signed-off-by: jiqing-feng <jiqing.feng@intel.com> Co-authored-by: Aryan <aryan@huggingface.co> Co-authored-by: Mark <remarkablemark@users.noreply.github.com> Co-authored-by: hlky <hlky@hlky.ac> Co-authored-by: kakukakujirori <63725741+kakukakujirori@users.noreply.github.com> Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com> Co-authored-by: YiYi Xu <yixu310@gmail.com> Co-authored-by: Fanli Lin <fanli.lin@intel.com> Co-authored-by: Yao Matrix <matrix.yao@intel.com> Co-authored-by: jiqing-feng <jiqing.feng@intel.com> Co-authored-by: Eliseu Silva <elismasilva@gmail.com> Co-authored-by: Bruno Magalhaes <bruno.magalhaes@synthesia.io> Co-authored-by: Sayak Paul <spsayakpaul@gmail.com> Co-authored-by: lakshay sharma <31830611+Lakshaysharma048@users.noreply.github.com> Co-authored-by: Abhipsha Das <ad6489@nyu.edu> Co-authored-by: Basile Lewandowski <basile.lewan@gmail.com> Co-authored-by: célina <hanouticelina@gmail.com>
Fixes #11163.
Raises a warning if the number of frames to be generated is not a multiple of 4K + 1. The reason for it being that way is because the VAE applies a 4x temporal downscaling/upscaling and the latents are created respecting that.
It is mentioned in the docs.