bytedance / bytedance/IRASim

fine-tuning details with Open-Sora initialization

Open
#12 1 comment 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
164
Forks
17
PR merge metrics
No merged PRs in 30d

Description

Dear Author,
First of all, I would like to express my sincere appreciation for your impressive work on IRASim.
To help me better understand the implementation and hardware requirements, could you please provide more details on the following points?
1.Which specific version of Open-Sora (v1.0, v1.1, or v1.2) was used as the base for the pre-trained weights?
2.what was the specific hardware setup? Specifically, how many GPUs were used, and what were the GPU versions?
3.how do you solve "Latent channel count mismatch" between opensora and sdxl-vae?Or you just use whole opensora framework including vae?
thanks

Contributor guide

No contributing guide indexed for this repository

Research direction

No files, tests, or entry points are named. Start by locating the fine-tuning and Open-Sora/SDXL-VAE initialization documentation or configuration in the repository; document the Open-Sora version, GPU count and models, and latent-channel handling. Done means all three questions in the issue are answered.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Documentation
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.