Conversation
quick_start.sh 的纯文本未注释:原脚本中有一行: RGB video interpolation 它不是注释,shell 会把它当命令执行。 解决方法: 已将相关说明文字修为注释。 原脚本写的是: ./CogVideo-X 但实际更合理的目录命名应为: ./CogVideoX-ft 否则 diffusers 会将 ./CogVideo-X 当作非法 Hugging Face repo id 处理。 解决方法: 已修正 quick_start.sh 中的默认路径。
原代码中硬编码: /home/lff/bigdata1/cjw/model_cache 这显然是作者本地机器路径,导致在当前机器上调用 StableNormal 时失败。 解决方法: 已将 get_normal.py 改为使用当前用户目录下的本地缓存: ~/.cache/langscenex_models 这让代码变为可移植状态。
…line, and tooling Code changes: - Remove hardcoded paths, use project-relative and ~/.cache paths - Replace pytorch3d dependency with local quad2rotation - Decouple dust3r imports by inlining to_numpy/_resize_pil_image - Add --prompt parameter to video_inference.py with lab-scene default - Fix auto-mask-align crash when masks list is empty - Support selected_idxs in preprocessor for external index control - Refactor CUDA extension setup.py for env-var include/nvcc flags - Add #include <cfloat> for newer CUDA compatibility New tooling: - high_quality_inference.sh: full 6-step inference pipeline - langscenex_env.sh: auto-configure LD_LIBRARY_PATH for CUDA - export_rgb_plys.py / view_ply.py: point cloud export & visualization - scripts/: inference result analysis and comparison - tests/: unit test for video_inference prompt Documentation: - inference.md: verified inference chain technical doc - BLACKWELL_MIGRATION.md: Blackwell GPU migration guide - Deployment notes .gitignore: add model weights, runs, build artifacts, personal data, sessions Co-Authored-By: Claude <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
quick_start.sh 的纯文本未注释
原脚本中有一行:
RGB video interpolation
它不是注释,shell 会把它当命令执行。
解决方法:
已将相关说明文字修为注释。
quick_start.sh 中 CogVideo 目录名不正确
原脚本写的是:
./CogVideo-X
但实际更合理的目录命名应为:
./CogVideoX-ft
否则 diffusers 会将 ./CogVideo-X 当作非法 Hugging Face repo id 处理。
解决方法:
已修正 quick_start.sh 中的默认路径。
get_normal.py 使用作者机器上的绝对缓存路径
原代码中硬编码:
/home/lff/bigdata1/cjw/model_cache
这显然是作者本地机器路径,导致在当前机器上调用 StableNormal 时失败。
解决方法:
已将 get_normal.py 改为使用当前用户目录下的本地缓存:
~/.cache/langscenex_models
这让代码变为可移植状态。