VictorMylle/Kohya-ss-sd-scripts
1
0
Fork 1
mirror of https://github.com/kohya-ss/sd-scripts.git synced 2026-04-06 13:47:06 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs: enhance text encoder CPU usage instructions for HunyuanImage-2.1 training

Browse Source
This commit is contained in:
kohya-ss
2025-09-28 18:21:25 +09:00
parent 67d0621313
commit a0c26a0efa
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/hunyuan_image_train_network.md
View File

@@ -190,7 +190,7 @@ The script adds HunyuanImage-2.1 specific arguments. For common arguments (like
* `--fp8_vl`
- Use FP8 for the VLM (Qwen2.5-VL) text encoder.
* `--text_encoder_cpu`
- Runs the text encoders on CPU to reduce VRAM usage. This is useful when VRAM is insufficient (less than 12GB). Encoding one text may take a few minutes (depending on CPU). It is highly recommended to use this option with `--cache_text_encoder_outputs_to_disk` to avoid repeated encoding every time training starts.
- Runs the text encoders on CPU to reduce VRAM usage. This is useful when VRAM is insufficient (less than 12GB). Encoding one text may take a few minutes (depending on CPU). It is highly recommended to use this option with `--cache_text_encoder_outputs_to_disk` to avoid repeated encoding every time training starts. **In addition, increasing `--num_cpu_threads_per_process` in the `accelerate launch` command, like `--num_cpu_threads_per_process=8` or `16`, can speed up encoding in some environments.**
* `--blocks_to_swap=<integer>` **[Experimental Feature]**
- Setting to reduce VRAM usage by swapping parts of the model (Transformer blocks) between CPU and GPU. Specify the number of blocks to swap as an integer (e.g., `18`). Larger values reduce VRAM usage but decrease training speed. Adjust according to your GPU's VRAM capacity. Can be used with `gradient_checkpointing`.
* `--cache_text_encoder_outputs`