theluyuan/DiffSynth-Studio
1
0
Fork 0
mirror of https://github.com/modelscope/DiffSynth-Studio.git synced 2026-03-23 17:38:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

redirect relative

Browse Source
This commit is contained in:
mi804
2026-02-10 18:00:19 +08:00
parent b5acef9e74
commit 07f8f485ed
58 changed files with 265 additions and 265 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
docs/en/QA.md
View File

@@ -29,7 +29,7 @@ Therefore, native FP8 precision training technology is extremely immature. We wi
## How to dynamically load LoRA models during inference?
We support two loading methods for LoRA models. See [LoRA Loading](/docs/en/Pipeline_Usage/Model_Inference.md#loading-lora) for details:
We support two loading methods for LoRA models. See [LoRA Loading](./Pipeline_Usage/Model_Inference.md#loading-lora) for details:
* Cold Loading: When [VRAM Management](/docs/en/Pipeline_Usage/VRAM_management.md) is not enabled for the base model, LoRA will be fused into the base model weights. In this case, inference speed remains unchanged, and LoRA cannot be unloaded after loading.
* Hot Loading: When [VRAM Management](/docs/en/Pipeline_Usage/VRAM_management.md) is enabled for the base model, LoRA will not be fused into the base model weights. In this case, inference speed will slow down, and LoRA can be unloaded after loading via `pipe.clear_lora()`.
* Cold Loading: When [VRAM Management](./Pipeline_Usage/VRAM_management.md) is not enabled for the base model, LoRA will be fused into the base model weights. In this case, inference speed remains unchanged, and LoRA cannot be unloaded after loading.
* Hot Loading: When [VRAM Management](./Pipeline_Usage/VRAM_management.md) is enabled for the base model, LoRA will not be fused into the base model weights. In this case, inference speed will slow down, and LoRA can be unloaded after loading via `pipe.clear_lora()`.