modelscope / modelscope/DiffSynth-Studio
Inquiry About Wan-I2V Training/Inference Performance on A6000 GPUs
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 13.1k
- Forks
- 1.3k
- Avg merge
- 13h 12m
- Merged PRs (30d)
- 45
Description
Hi @Artiprocher,
I'd like to consult about the training and inference speeds of Wan-I2V-14B-480P. My setup consists of 4×A6000 (49GB GPUs). After installing Diffsynth-Studio, I ran the example code test and observed the following performance:
wan-1.3B-T2V: ~5 minutes per video generation
wan-14B-I2V-480P:
~50 minutes for 81 frames (bfloat16, 50 iterations)
~37 minutes for 21 frames
My questions:
-
Baseline Validation: Are these inference times normal?
-
Inference Acceleration: Is multi-GPU parallelization supported for inference? (I couldn't find related documentation)
-
Training Acceleration: The current 50min/it training speed is impractical. Are there optimization strategies?
Thank you for your help!
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Begin with the Wan-I2V-14B-480P example code and reproduce the reported timings on 4×A6000 GPUs using 81 and 21 frames. Compare the results with the wan-1.3B-T2V example, then determine whether multi-GPU inference or training acceleration is supported. Done means providing validated baseline timings and documented optimization or parallelization guidance.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning, performance
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100