No official torrent yet — requesting it tells the flock what to host next. You cannot seed a catalog-only page.
Cataloged from lightx2v/Hy1.5-Quantized-Models
All models by lightx2v →
🤗 HuggingFace | GitHub | License
This repository contains quantized models for HunyuanVideo-1.5 optimized for use with LightX2V. These quantized models significantly reduce memory usage while maintaining high-quality video generation performance.
hy15_720p_i2v_fp8_e4m3_lightx2v.safetensors - 720p Image-to-Video quantized DIT modelhy15_720p_t2v_fp8_e4m3_lightx2v.safetensors - 720p Text-to-Video quantized DIT modelhy15_qwen25vl_llm_encoder_fp8_e4m3_lightx2v.safetensors - Quantized text encoder (Qwen2.5-VL LLM Encoder)First, install LightX2V:
Or build from source:
Download the quantized models from this repository:
These models use FP8-E4M3 quantization with the SGL (SGLang) kernel scheme (fp8-sgl). This quantization format provides:
To use these quantized models, you need to install the SGL kernel:
Alternatively, you can use VLLM kernels:
For more details on quantization schemes, please refer to the LightX2V Quantization Documentation.
Using quantized models provides:
enable_quantize()) must be called before create_generator(), otherwise they will not take effect.sage_attn2) as the attention mode.If you use these quantized models in your research, please cite:
This model is released under the Apache 2.0 License, same as the original HunyuanVideo-1.5 model.
pip install -v git+https://github.com/ModelTC/LightX2V.gitgit clone https://github.com/ModelTC/LightX2V.gitcd LightX2Vpip install -v -e .# Using git-lfsgit lfs installgit clone https://huggingface.co/lightx2v/Hy1.5-Quantized-Models
# Or download individual files using huggingface-hubpip install huggingface-hubpython -c "from huggingface_hub import hf_hub_download; hf_hub_download(repo_id='lightx2v/Hy1.5-Quantized-Models', filename='hy15_720p_i2v_fp8_e4m3_lightx2v.safetensors', local_dir='./models')"from lightx2v import LightX2VPipeline
# Initialize pipelinepipe = LightX2VPipeline( model_path="/path/to/hunyuanvideo-1.5/", # Original model path model_cls="hunyuan_video_1.5", transformer_model_name="720p_t2v", task="t2v",)
# Enable quantizationpipe.enable_quantize( quant_scheme='fp8-sgl', dit_quantized=True, dit_quantized_ckpt="/path/to/hy15_720p_t2v_fp8_e4m3_lightx2v.safetensors", text_encoder_quantized=True, text_encoder_quantized_ckpt="/path/to/hy15_qwen25vl_llm_encoder_fp8_e4m3_lightx2v.safetensors", image_encoder_quantized=False,)
# Optional: Enable offloading for lower VRAM usagepipe.enable_offload( cpu_offload=True, offload_granularity="block", # For HunyuanVideo-1.5, only "block" is supported text_encoder_offload=True, image_encoder_offload=False, vae_offload=False,)
# Optional: Use lighttaepipe.enable_lightvae( use_tae=True, tae_path="/path/to/lighttaehy1_5.safetensors", use_lightvae=False, vae_path=None,)
# Create generatorpipe.create_generator( attn_mode="sage_attn2", infer_steps=50, num_frames=121, guidance_scale=6.0, sample_shift=9.0, aspect_ratio="16:9", fps=24,)
# Generate videoseed = 123prompt = "A beautiful sunset over the ocean with waves gently crashing on the shore."negative_prompt = ""save_result_path="/path/to/output.mp4"
pipe.generate( seed=seed, prompt=prompt, negative_prompt=negative_prompt, save_result_path=save_result_path,)from lightx2v import LightX2VPipeline
# Initialize pipelinepipe = LightX2VPipeline( model_path="/path/to/hunyuanvideo-1.5/", # Original model path model_cls="hunyuan_video_1.5", transformer_model_name="720p_i2v", task="i2v",)
# Enable quantizationpipe.enable_quantize( quant_scheme='fp8-sgl', dit_quantized=True, dit_quantized_ckpt="/path/to/hy15_720p_i2v_fp8_e4m3_lightx2v.safetensors", text_encoder_quantized=True, text_encoder_quantized_ckpt="/path/to/hy15_qwen25vl_llm_encoder_fp8_e4m3_lightx2v.safetensors", image_encoder_quantized=False,)
# Optional: Use lighttaepipe.enable_lightvae( use_tae=True, tae_path="/path/to/lighttaehy1_5.safetensors", use_lightvae=False, vae_path=None,)
# Optional: Enable offloading for lower VRAM usagepipe.enable_offload( cpu_offload=True, offload_granularity="block", text_encoder_offload=True, image_encoder_offload=False, vae_offload=False,)
# Create generatorpipe.create_generator( attn_mode="sage_attn2", infer_steps=50, num_frames=121, guidance_scale=6.0, sample_shift=7.0, fps=24,)
# Generate videoseed = 42prompt = "The image comes to life with smooth motion and natural transitions."negative_prompt = ""save_result_path="/path/to/output.mp4"
pipe.generate( seed=seed, image_path="/path/to/input_image.jpg", prompt=prompt, negative_prompt=negative_prompt, save_result_path=save_result_path,)# Requires torch == 2.8.0pip install sgl-kernel --upgradepip install vllm@misc{lightx2v, author = {LightX2V Contributors}, title = {LightX2V: Light Video Generation Inference Framework}, year = {2025}, publisher = {GitHub}, journal = {GitHub repository}, howpublished = {\url{https://github.com/ModelTC/lightx2v}},}