ComfyUI Node
VRGDG LTX LoRA Train Chunk
Runs one LTX-2 LoRA training chunk using musubi-tuner, optionally caches if needed, and can export the latest Comfy-compatible LoRA for downstream preview generation.
VRGDG LTX LoRA Train Chunk
- model
- model
- latest_state_path
- log_path
- video_filename_prefix
- output_name
- completed_steps
- total_target_steps
◄dataset_images_dir►
◄workspace_dir►
◄run_nameLTXChunkRun►
◄output_nameLTXChunkRun►
◄resolution_width1920►
◄resolution_height1080►
◄steps_per_run250►
◄total_target_steps3000►
◄network_dim64►
◄network_alpha32►
◄blocks_to_swap4►
◄clear_memory_before_gemmatrue►
◄learning_rate_preset7e-5►
◄learning_rate0.0001►
◄num_repeats1►
◄cache_strategyauto►
◄copy_latest_to_comfy_lorastrue►
◄keep_only_comfy_lorafalse►
◄strength_model1.00►
◄create_captionsfalse►
◄caption_text►
◄add_trigger_wordfalse►
◄trigger_text►
◄musubi_rootA:/MUSUBI/musubi-tuner-ltx2►
◄ltx2_checkpointA:/MUSUBI/models/ltx2/ltx-2.3-22b-dev.safetensors►
◄gemma_rootA:/MUSUBI/models/gemma3►
◄gemma_recovery_modefalse►
◄gemma_load_in_4bitfalse►
CategoryVRGDG/Training
Inputs (29)
| Name | Type | Default | Description |
|---|---|---|---|
| model | MODEL | Base model to return downstream with the latest trained LoRA optionally applied. | |
| dataset_images_dir | STRING | Folder containing your training images, or a parent folder that will be organized into an images subfolder. | |
| workspace_dir | STRING | Working folder for cache, logs, config files, checkpoints, and training state. | |
| run_name | STRING | LTXChunkRun | Name prefix used for the log file. |
| output_name | STRING | LTXChunkRun | Name prefix used for saved LoRA files and state folders. |
| resolution_width | INT | 192064–8192 | Training bucket width written to the musubi dataset config. Examples: 960 for lighter tests, 1280 for medium runs, 1920 for full HD style training. |
| resolution_height | INT | 108064–8192 | Training bucket height written to the musubi dataset config. Examples: 540 for lighter tests, 720 for medium runs, 1080 for full HD style training. |
| steps_per_run | INT | 2501–100000 | How many steps to train per run, and also when to save the LoRA/state at the end of that run. Examples: 50 for quick tests, 250 for normal preview cadence, 500 for longer chunks. |
| total_target_steps | INT | 30001–1000000 | Training stops once the latest saved step reaches this total. Examples: 1000 for a short experiment, 3000 for a normal run, 6000+ for longer training. |
| network_dim | INT | 641–2048 | LoRA rank. Higher values increase capacity and VRAM usage. Examples: 16 for very small tests, 32 for lighter runs, 64 as a common default, 128 for larger higher-capacity LoRAs. |
| network_alpha | INT | 321–2048 | LoRA alpha scaling value. A common pairing is alpha at half the rank. Examples: rank 16 -> alpha 8, rank 32 -> alpha 16, rank 64 -> alpha 32. |
| blocks_to_swap | INT | 40–64 | Higher values reduce VRAM usage but usually slow training. Use 0 to disable block swapping. Examples: 0 for max speed if VRAM is sufficient, 4 as a balanced default, 8 to 12 for lower VRAM cards. |
| clear_memory_before_gemma | BOOLEAN | true | Tries to unload ComfyUI models and clear VRAM/RAM before Gemma text encoder caching. Keep enabled if stage 2 tends to stall. |
| learning_rate_preset | COMBO | 7e-5 | Quick preset for the training learning rate. Examples: 1e-4 for aggressive training, 7e-5 as a common default, 5e-5 or 3e-5 for gentler training. Choose Custom to use the float input below. |
| learning_rate | FLOAT | 0.00011e-8–1 | Custom learning rate used only when the preset is set to Custom. Examples: 0.0001 = 1e-4, 0.00007 = 7e-5, 0.00005 = 5e-5, 0.00003 = 3e-5. |
| num_repeats | INT | 11–1000 | How many times each image-caption pair is repeated in the dataset. Examples: 1 for normal use, 2 to 4 if the dataset is very small, higher only when you intentionally want more repeats. |
| cache_strategy | COMBO | auto | Auto builds cache only when needed, Force always rebuilds it, Skip goes straight to training. |
| copy_latest_to_comfy_loras | BOOLEAN | true | Copies the latest Comfy-compatible LoRA into the ComfyUI loras folder after training. |
| keep_only_comfy_lora | BOOLEAN | false | If enabled, deletes the standard .safetensors LoRA files after a matching .comfy.safetensors file exists. Resume state folders are kept. |
| strength_model | FLOAT | 1.00-100–100 | Strength used if the node applies the latest LoRA back onto the output model. Examples: 1.0 for normal preview, 0.7 for a lighter effect, 0.0 to effectively disable applying the LoRA to the returned model. |
| create_captions | BOOLEAN | false | If enabled, missing caption txt files are created automatically using the caption text input. |
| caption_text | STRING | Base caption text used when create_captions is enabled and an image has no caption file. Example: woman portrait, cinematic close-up, soft natural light. | |
| add_trigger_word | BOOLEAN | false | If enabled, the trigger text is prepended to each caption. |
| trigger_text | STRING | Trigger word or phrase to prepend to captions when add_trigger_word is enabled. Examples: miranda, my_character, retro-future heroine. | |
| musubi_root | STRING | A:/MUSUBI/musubi-tuner-ltx2 | Root folder of your musubi-tuner-ltx2 install. |
| ltx2_checkpoint | STRING | A:/MUSUBI/models/ltx2/ltx-2.3-22b-dev.safetensors | Path to the base LTX-2 checkpoint used for caching and training. |
| gemma_root | STRING | A:/MUSUBI/models/gemma3 | Folder containing the Gemma model files used for text encoder caching. |
| gemma_recovery_mode | BOOLEAN | false | Experimental. If enabled, the node will keep the normal Gemma cache path first, then try alternate cache settings if that stage fails. |
| gemma_load_in_4bit | BOOLEAN | false | Loads Gemma in 4-bit mode during text encoder caching. This lowers VRAM more than 8-bit, but can be slower or less stable. |
Outputs (7)
| Name | Type | Description |
|---|---|---|
| model | MODEL | — |
| latest_state_path | STRING | — |
| log_path | STRING | — |
| video_filename_prefix | STRING | — |
| output_name | STRING | — |
| completed_steps | INT | — |
| total_target_steps | INT | — |