lllyasviel / lllyasviel/stable-diffusion-webui-forge
Estimation of memory requirement.
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 13k
- Forks
- 1.7k
- PR merge metrics
- No merged PRs in 30d
Description
What is this magic number (16384)? Why is it the same for all models? Why is input_shape[1] (VAE depth for Flux = 16) not taken into account?
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
Read backend/modules/k_model.py lines 48-59 and trace how the memory estimate is used for different models. Compare the fixed 16384 value with the model input shape, including the Flux VAE depth mentioned in the issue. Done means the estimation rationale is established and the implementation accounts for the relevant model differences, with tests or validation covering the result.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- backend, machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100