ComfyUI Node
VRGDG LTX Speed Character Lora Training
Runs the LTX trainer with a fast character-LoRA preset using dynamic IMAGE and caption inputs.
VRGDG LTX Speed Character Lora Training
- model
- image1
- image2
- image3
- image4
- image5
- image6
- image7
- image8
- image9
- image10
- image11
- image12
- image13
- image14
- image15
- image16
- image17
- image18
- image19
- image20
- model
- latest_state_path
- log_path
- video_filename_prefix
- output_name
- completed_steps
- total_target_steps
◄workspace_dirA:/MUSUBI/Training/SpeedCharacterLoraTraining►
◄run_nameSpeedCharacterLoraTrainingRun►
◄output_nameSpeedCharacterLoraTraining►
◄image_count4►
◄resolution_width1256►
◄resolution_height1256►
◄blocks_to_swap0►
◄clear_memory_before_gemmatrue►
◄cache_strategyauto►
◄strength_model1.00►
◄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►
◄caption_1►
◄caption_2►
◄caption_3►
◄caption_4►
◄caption_5►
◄caption_6►
◄caption_7►
◄caption_8►
◄caption_9►
◄caption_10►
◄caption_11►
◄caption_12►
◄caption_13►
◄caption_14►
◄caption_15►
◄caption_16►
◄caption_17►
◄caption_18►
◄caption_19►
◄caption_20►
CategoryVRGDG/Training
Inputs (56)
| Name | Type | Default | Description |
|---|---|---|---|
| model | MODEL | — | |
| workspace_dir | STRING | A:/MUSUBI/Training/SpeedCharacterLoraTraining | Workspace folder for cache, output, logs, config, and the managed dynamic dataset. |
| run_name | STRING | SpeedCharacterLoraTrainingRun | Run name used for logs. |
| output_name | STRING | SpeedCharacterLoraTraining | LoRA output name used for checkpoints and downstream preview naming. |
| image_count | INT | 41–20 | How many dynamic image inputs and caption fields to show. |
| resolution_width | INT | 125664–4096 | Training bucket width. Pick the resolution preset you want to train at. |
| resolution_height | INT | 125664–4096 | Training bucket height. Pick the resolution preset you want to train at. |
| blocks_to_swap | INT | 00–64 | How many transformer blocks to swap to CPU. 0 is fastest if VRAM allows it. |
| clear_memory_before_gemma | BOOLEAN | true | Clears Comfy and CUDA memory before the Gemma cache stage. |
| cache_strategy | COMBO | auto | Cache behavior. auto reuses cache when present, force rebuilds, skip bypasses cache creation. |
| strength_model | FLOAT | 1.00-100–100 | Strength used when applying the newest trained LoRA back onto the returned MODEL. |
| musubi_root | STRING | A:/MUSUBI/musubi-tuner-ltx2 | Root folder of your musubi install. |
| ltx2_checkpoint | STRING | A:/MUSUBI/models/ltx2/ltx-2.3-22b-dev.safetensors | Path to the LTX-2.3 DiT checkpoint. |
| gemma_root | STRING | A:/MUSUBI/models/gemma3 | Path to the Gemma model root used by this preset. |
| gemma_recovery_mode | BOOLEAN | false | Experimental. If enabled, the node will try alternate Gemma cache settings after the normal path 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. |
| image1opt | IMAGE | — | |
| image2opt | IMAGE | — | |
| image3opt | IMAGE | — | |
| image4opt | IMAGE | — | |
| image5opt | IMAGE | — | |
| image6opt | IMAGE | — | |
| image7opt | IMAGE | — | |
| image8opt | IMAGE | — | |
| image9opt | IMAGE | — | |
| image10opt | IMAGE | — | |
| image11opt | IMAGE | — | |
| image12opt | IMAGE | — | |
| image13opt | IMAGE | — | |
| image14opt | IMAGE | — | |
| image15opt | IMAGE | — | |
| image16opt | IMAGE | — | |
| image17opt | IMAGE | — | |
| image18opt | IMAGE | — | |
| image19opt | IMAGE | — | |
| image20opt | IMAGE | — | |
| caption_1opt | STRING | — | |
| caption_2opt | STRING | — | |
| caption_3opt | STRING | — | |
| caption_4opt | STRING | — | |
| caption_5opt | STRING | — | |
| caption_6opt | STRING | — | |
| caption_7opt | STRING | — | |
| caption_8opt | STRING | — | |
| caption_9opt | STRING | — | |
| caption_10opt | STRING | — | |
| caption_11opt | STRING | — | |
| caption_12opt | STRING | — | |
| caption_13opt | STRING | — | |
| caption_14opt | STRING | — | |
| caption_15opt | STRING | — | |
| caption_16opt | STRING | — | |
| caption_17opt | STRING | — | |
| caption_18opt | STRING | — | |
| caption_19opt | STRING | — | |
| caption_20opt | STRING | — |
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 | — |