Automated PR - 2026-01-13

packages/ltx-trainer/docs/configuration-reference.md

@@ -24,7 +24,8 @@ sub-configurations:
 
 Check out our example configurations in the `configs` directory:
 
-- 📄 [Audio-Video LoRA Training](../configs/ltx2_av_lora.yaml) - Joint audio-video to generation training
+- 📄 [Audio-Video LoRA Training](../configs/ltx2_av_lora.yaml) - Joint audio-video generation training
+- 📄 [Audio-Video LoRA Training (Low VRAM)](../configs/ltx2_av_lora_low_vram.yaml) - Memory-optimized config for 32GB GPUs (uses 8-bit optimizer, INT8 quantization, and reduced LoRA rank)
 - 📄 [IC-LoRA Training](../configs/ltx2_v2v_ic_lora.yaml) - Video-to-video transformation training
 
 ## ⚙️ Configuration Sections

packages/ltx-trainer/docs/quick-start.md

@@ -11,8 +11,9 @@ Before you begin, ensure you have:
 2. **Gemma Text Encoder** - A local directory containing the Gemma model (required for LTX-2).
    Download from: [HuggingFace Hub](https://huggingface.co/google/gemma-3-12b-it-qat-q4_0-unquantized/)
 3. **Linux with CUDA** - The trainer requires `triton` which is Linux-only
-4. **GPU with sufficient VRAM** - 80GB recommended. Lower VRAM may work with gradient checkpointing and lower
-   resolutions
+4. **GPU with sufficient VRAM** - 80GB recommended for the standard config. For GPUs with 32GB VRAM (e.g., RTX 5090),
+   use the [low VRAM config](../configs/ltx2_av_lora_low_vram.yaml) which enables INT8 quantization and other
+   memory optimizations
 
 ## ⚡ Installation
 
@@ -63,6 +64,7 @@ See [Dataset Preparation](dataset-preparation.md) for detailed instructions.
 Create or modify a configuration YAML file. Start with one of the example configs:
 
 - [`configs/ltx2_av_lora.yaml`](../configs/ltx2_av_lora.yaml) - Audio-video LoRA training
+- [`configs/ltx2_av_lora_low_vram.yaml`](../configs/ltx2_av_lora_low_vram.yaml) - Audio-video LoRA training (optimized for 32GB VRAM)
 - [`configs/ltx2_v2v_ic_lora.yaml`](../configs/ltx2_v2v_ic_lora.yaml) - IC-LoRA video-to-video
 
 Key settings to update:

packages/ltx-trainer/docs/troubleshooting.md

@@ -6,6 +6,11 @@ This guide covers common issues and solutions when training with the LTX-2 train
 
 Memory management is crucial for successful training with LTX-2.
 
+> [!TIP]
+> For GPUs with 32GB VRAM, use the pre-configured low VRAM config:
+> [`configs/ltx2_av_lora_low_vram.yaml`](../configs/ltx2_av_lora_low_vram.yaml)
+> which combines 8-bit optimizer, INT8 quantization, and reduced LoRA rank.
+
 ### Memory Optimization Techniques
 
 #### 1. Enable Gradient Checkpointing