lllyasviel / lllyasviel/FramePack
Video generation might be failing due to RAM limits?
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 17.3k
- Forks
- 1.7k
- PR merge metrics
- No merged PRs in 30d
Description
Hi, I'm trying to generate a 5 seconds video, but the process seems to be using almost 100% of my RAM (I have 16GB), and I'm wondering if that's the reason the video isn't generating properly.
At the end of the logs, I see this:
Unloaded SiglipVisionModel as complete.
Moving DynamicSwap_HunyuanVideoTransformer3DModelPacked to cuda:0 with preserved memory: 6 GB
100%|██████████████████████████████████████████████████████████████████████████████████| 25/25 [14:11<00:00, 34.06s/it]
Offloading DynamicSwap_HunyuanVideoTransformer3DModelPacked from cuda:0 to preserve memory: 8 GB
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
No files or tests are named. Start by reproducing a 5-second video generation with 16 GB RAM while monitoring memory, then compare the final log lines around SiglipVisionModel and DynamicSwap_HunyuanVideoTransformer3DModelPacked. Done means determining whether the RAM usage causes the generation failure and documenting a confirmed cause or reproducible result.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100