import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("matanby/ltxv-13b-slime", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]ltxv-13b-slime
This is a fine-tuned version of LTXV_13B_097_DEV trained on custom data.
Model Details
- Base Model:
LTXV_13B_097_DEV - Training Type: LoRA fine-tuning
- Training Steps: 5
- Learning Rate: 0.0002
- Batch Size: 1
Sample Outputs
 PromptSLIME green pouring from above on a man's head |
 PromptSLIME green pouring from above on a woman's head |
Usage
This model is designed to be used with the LTXV (Lightricks Text-to-Video) pipeline.
🔌 Using Trained LoRAs in ComfyUI
In order to use the trained lora in comfy:
- Copy your comfyui trained LoRA weights (
comfyui..safetensorsfile) to themodels/lorasfolder in your ComfyUI installation. - In your ComfyUI workflow:
- Add the "LTXV LoRA Selector" node to choose your LoRA file
- Connect it to the "LTXV LoRA Loader" node to apply the LoRA to your generation
You can find reference Text-to-Video (T2V) and Image-to-Video (I2V) workflows in the official LTXV ComfyUI repository.
Example Prompts
Example prompts used during validation:
SLIME green pouring from above on a man's headSLIME green pouring from above on a woman's head
This model inherits the license of the base model (LTXV_13B_097_DEV).
Acknowledgments
- Base model by Lightricks
- Training infrastructure: LTX-Video-Trainer
- Downloads last month
- 12