HunyuanVideo1.5 720p Text to Video

Note: All model files and custom nodes below must be downloaded via the client. If you do not have the client, Download >>>

This is a powerful AI video generation model developed by Tencent. It can create realistic, high-quality videos just from a text description. For example, if you type “a kitten rolling in the sunlight,” it will generate a short video that looks like it was filmed with a real camera.

Model Files

sigclip_vision_384 >1 files

Name	Size	Target Dir
sigclip_vision_patch14_384.safetensors	857 MB	clip_vision

hunyuanvideo15_latent_upsampler >2 files

Name	Size	Target Dir
hunyuanvideo15_latent_upsampler_720p.safetensors	85.85 MB	latent_upscale_models
hunyuanvideo15_latent_upsampler_1080p.safetensors	201.40 MB	latent_upscale_models

HunyuanVideo1.5 720p Text to Video >1 files

Name	Size	Target Dir
hunyuanvideo1.5_720p_t2v_fp16.safetensors	16.65 GB	diffusion_models

Qwen2.5 VL 7B >2 files

Name	Size	Target Dir
qwen_2.5_vl_7b_fp8_scaled.safetensors	9.38 GB	text_encoders
qwen_2.5_vl_7b.safetensors	16.58 GB	text_encoders

HunyuanVideo1.5 Super Resolution >2 files

Name	Size	Target Dir
hunyuanvideo1.5_1080p_sr_distilled_fp16.safetensors	16.66 GB	diffusion_models
hunyuanvideo1.5_720p_sr_distilled_fp16.safetensors	16.66 GB	diffusion_models

byt5_small_glyphxl >1 files

Name	Size	Target Dir
byt5_small_glyphxl_fp16.safetensors	438.64 MB	text_encoders

HunYuanvideo 1.5 VAE >1 files

Name	Size	Target Dir
hunyuanvideo15_vae_fp16.safetensors	2.52 GB	vae