| File | hunyuanvideo1.5_480p_t2v_cfg_distilled_fp8_scaled.safetensors |
| Model | HunyuanVideo 1.5 (video model, 8.3B) |
| Precision | FP8 |
| Size | 8.3 GB |
| VRAM to fit | about 12.6 GB |
| Folder | ComfyUI/models/diffusion_models/ |
| Loader node | Load Diffusion Model (UNETLoader) |
| Source | Comfy-Org/HunyuanVideo_1.5_repackaged on Hugging Face |
Download hunyuanvideo1.5_480p_t2v_cfg_distilled_fp8_scaled.safetensors (8.3 GB)
Where to put it
Put the file in ComfyUI/models/diffusion_models/ (portable version: ComfyUI_windows_portable/ComfyUI/models/diffusion_models/). Older guides say models/unet: that folder still works. Press R in ComfyUI or restart it, then pick the file in Load Diffusion Model (UNETLoader). Not for Mac: FP8 and INT8 files do not load on Apple Silicon.
If a workflow says “Value not in list” for that node, the workflow expects a file with another name. Click the node and choose this one.
Which graphics cards it fits
| VRAM | This file | Best file for that card (RTX 40/50) | |
|---|---|---|---|
| 6 GB | Offload only | Short by 6.6 GB: runs with part of it in system RAM, slower | hunyuanvideo1.5_720p_t2v-Q4_K_M.gguf (5.1 GB) |
| 8 GB | Offload only | Short by 4.6 GB: runs with part of it in system RAM, slower | hunyuanvideo1.5_720p_t2v-Q4_K_M.gguf (5.1 GB) |
| 10 GB | Offload only | Short by 2.6 GB: runs with part of it in system RAM, slower | hunyuanvideo1.5_720p_t2v-Q4_K_M.gguf (5.1 GB) |
| 12 GB | Offload only | Short by 0.6 GB: runs with part of it in system RAM, slower | hunyuanvideo1.5_720p_t2v-Q6_K.gguf (7.0 GB) |
| 16 GB | Runs well | Fits in VRAM, 3.4 GB to spare | this file |
| 20 GB | Runs well | Fits in VRAM, 7.4 GB to spare | this file |
| 24 GB | Runs well | Fits in VRAM, 11.4 GB to spare | hunyuanvideo1.5_720p_t2v_fp16.safetensors (16.7 GB) |
| 32 GB | Runs well | Fits in VRAM, 19.4 GB to spare | hunyuanvideo1.5_720p_t2v_fp16.safetensors (16.7 GB) |
| 48 GB | Runs well | Fits in VRAM, 35.4 GB to spare | hunyuanvideo1.5_720p_t2v_fp16.safetensors (16.7 GB) |
Need = file × 1 + 3.5 GB for the picture and 0.8 GB for Windows and the browser — the same rule as the rest of the site. FP8 files do not load on a Mac (Apple Silicon); use a 16-bit or GGUF file there.
Measured with this exact file
| GPU | Time | Size | Steps | Peak VRAM | Source |
|---|---|---|---|---|---|
| RTX 5060 Ti 16 GB | 663 s per video (121 frames) | 848x480 | 20 | 14.3 GB | measured by me, 2026-10-12 |
Time = sampling + VAE decode, after a warm-up run. Peak VRAM = memory in use on the whole card. How I measure.
What else you need
This file alone does not make a picture. With it you load:
| Role | File | Size | Folder |
|---|---|---|---|
| Model | hunyuanvideo1.5_480p_t2v_cfg_distilled_fp8_scaled.safetensors | 8.3 GB | models/diffusion_models |
| Text encoder | qwen_2.5_vl_7b_fp8_scaled.safetensors | 9.4 GB | models/text_encoders |
| Text encoder | byt5_small_glyphxl_fp16.safetensors | 0.4 GB | models/text_encoders |
| VAE | hunyuanvideo15_vae_fp16.safetensors | 2.5 GB | models/vae |
20.7 GB in total. Smaller text-encoder versions and other options are on the HunyuanVideo 1.5 page.
Other files of HunyuanVideo 1.5
| File | Precision | Size | VRAM to fit |
|---|---|---|---|
| hunyuanvideo1.5_720p_t2v_fp16.safetensors | 16-bit | 16.7 GB | 21.0 GB |
| hunyuanvideo1.5_720p_t2v-Q8_0.gguf | Q8_0 | 9.0 GB | 13.3 GB |
| hunyuanvideo1.5_480p_t2v_cfg_distilled_fp8_scaled.safetensors | FP8 | 8.3 GB | 12.6 GB |
| hunyuanvideo1.5_720p_t2v-Q6_K.gguf | Q6_K | 7.0 GB | 11.3 GB |
| hunyuanvideo1.5_720p_t2v-Q5_K_M.gguf | Q5_K_M | 6.1 GB | 10.4 GB |
| hunyuanvideo1.5_720p_t2v-Q4_K_M.gguf | Q4_K_M | 5.1 GB | 9.4 GB |
Same model, different compression. 8-bit files (FP8, INT8, Q8_0) look almost the same as 16-bit; below Q5 the loss starts to show.
Free workflow with this file
- HunyuanVideo 1.5 — 480p text to video, FP8 — 11 min for a 121-frame 848×480 clip
Drag the .json into ComfyUI. All free workflows →
Want the answer for your exact card? Check your GPU. Every file of every model: ComfyUI model files.
Size and source read from Hugging Face (2026-10-01).