HunyuanVideo 1.5

8089°

#video #effects #base model #hunyuanvideo15 #hunyuan #hunyuanvideo

NSFW

NSFW model. Its pictures are hidden while NSFW is off; turn NSFW on to see them.

Run this model

Offers / Ads

Easy Creator (Prism) Web

Unlimited · flat fee

Best for beginners. Describe what you want in a chat and the picture comes back, no learning curve.

PirateDiffusion Telegram

Unlimited · flat fee

Images and video from a chat, with short commands. The most convenient tool for Telegram users, with a web companion.

Pro studio (SpyGlass) Web

Unlimited · flat fee

Best for power users. Full control over models, settings and workflows in a browser studio.

Discord bot (Vector)

Unlimited · flat fee

Best for communities. Add it to your own server and run any workflow from a channel.

Unified Editor Web

Unlimited · flat fee

One screen for every model and workflow: prompts, references, edits and video, built into your Graydient account.

Civitai Web

Pay per use

Generate on Civitai's own site; every image is paid for with Buzz credits.

Local apps

Requires setup

Set up local programs if your computer has capable hardware.

ModelDuel Web

Pay per use

Generate the same prompt on up to 50 checkpoint/base models at a time.

Rent a GPU on the cloud

Graydient Cloud GPU

Unlimited · flat fee

Flat fee, unlimited use. This model installs with one click.

RunPod Cloud GPU

Charged by the minute

Rent a GPU by the minute and set the model up yourself.

Guides for this model

Flat fee vs tokens: why unlimited plans like Graydient.ai are the best value for AI creators in 2026

Best open-source AI video models in 2026: what you can actually download

HunyuanVideo 1.5 vs Wan 2.2: which open video model to run in 2026

All guides

Workflow

animate huny q8

Created by

MrReclusive666

on Civitai

HunyuanVideo 1.5 is Tencent's open video model from November 2025, with 8.3 billion parameters. It makes 480p and 720p clips from a text prompt or a still image, and includes an upscaler toward 1080p. It is a different model from the original 13-billion-parameter HunyuanVideo, and it needs far less memory. This page is the official checkpoint. The Graydient image-to-video workflow runs the Q8 build of these weights.

Creator notes

HUNYUAN VIDEO 1.5 Official Releases (from Tencent, pulled from Comfy-Org's HuggingFace) Maintained and updated here for convenience. Not affiliated with Tencent — just a fan of Hunyuan Video. 🎉 Training code for Hunyuan Video 1.5 is now released! LoRA's incoming... Confirmed, Lora training working in musubi-tuner, its a bit picky, but it works. I find that T2V works best with er_sde and beta11, and I2V works best with ipndm and simple/beta11. TEXT TO VIDEO MODELS • 720p T2V — FP16 — 16GB • 480p T2V — FP16 — 16GB • 480p T2V — FP8 — CFG-Distilled Scaled — 8GB IMAGE TO VIDEO MODELS • 720p I2V — FP16 — 16GB • 480p I2V — FP16 — 16GB • 480p I2V — FP16 — Step-Distilled — 16GB (added Dec 5) • 480p I2V — FP8 — Step-Distilled Scaled — 8GB (added Dec 5) • 480p I2V — FP8 — CFG-Distilled Scaled — 8GB UPSCALE MODELS • 1080p SR — FP16 — Distilled — 16GB NOTES • Text-to-Video models can also be used for Image-to-Video. They behave differently from true I2V models, but still work. TENCENT UPDATE LOG (summarized) Dec 05, 2025 • 480p I2V Step-Distilled model released (8 or 12 steps recommended). • End-to-end generation ~75% faster on RTX 4090 (≈75 seconds per video). • Step-distilled quality remains close to the original. • Optional 4-step mode available for ultra-fast output. • Training code now open-sourced (Muon optimizer). • HunyuanVideo-1.5 available on Hugging Face Diffusers. Nov 27, 2025 • Cache inference support added (deepcache, teacache, taylorcache). • Major speedups. Nov 24, 2025 • Deepcache inference introduced. Nov 20, 2025 • Inference code and model weights released. LightX2V COMPATIBILITY Tested and WORKING (4 or 8 step generation): • T2V 720p FP16 • T2V 480p FP16 • I2V 720p FP16 • I2V 480p FP16 • I2V 480p FP8 CFG-D Scaled (Distilled) Tested and NOT WORKING (full 50-step generation): • T2V 480p FP8 CFG-D Scaled (Distilled)

1,461 downloads · 39 likes on Civitai

SHA256

4F05E2A31B51B7DDEE3EF336D234E0932001CBDC85887DA15451069FDA3E1D05

HunyuanVideo 1.5 Popularity Trend

Heat score since 24 Nov 2025

Heat score

8,089°

This week

▼

0.2%

8,090° then, 8,089° now

This month

▼

0.8%

8,097° then, 8,089° now

Past year

n/a

Wasn't released/tracked

7,000°

Floor

The scale runs from 0° to 9,999°. Everything below 7,000° is kept for models no source reports on yet, which carry a stand-in number there so lists stay complete. 7,000° is where measured data begins: a model with real data but almost no downloads sits at the floor, and the measurements fill the degrees above it. The floor says nothing about the model; only the degrees above it do, and they are what separates one model from another.

+962°

Civitai downloads

1,461 downloads of this exact version on Civitai. Downloads are the heaviest ingredient and are counted on a log scale: ten times the downloads adds the same 300°, so a model with a million downloads is not a thousand times hotter than one with a thousand. The six download sources share that one term, split between them in proportion to their counts.

+240°

Likes

39 likes and thumbs up across the sources. A like weighs half a download, on the same log scale.

+20°

Adoption rate

About 1 downloads a day, measured between two readings of the sources, never guessed from a lifetime average. Speed weighs a quarter of the download term, so a fresh surge shows without letting a one-day spike outrank years of use.

+150°

Full model

+150° because this is a full model: a checkpoint, the weights themselves. A LoRA or an embedding is an add-on to someone else's weights and does not outrank a checkpoint of equal popularity.

−283°

Age

−283° because the Huny weights came out in 2024. Every model inherits the age of the weights it is built on: 150° a year, up to 750°, and it keeps growing until then. Without it the top of the list would be 2022 and 2023 checkpoints on the strength of downloads that had years to pile up.

Show detailed breakdown

Every number on this site can be checked. This model's heat score is 8,089°, and here it is built one ingredient at a time, with the running total after each: the floor, the degrees each source adds, the bonus for the kind of model and what the age of its weights takes away. The colors are the bands of the chart above. The glossary at the end defines every term.

1
Start at the floor.
Why 7,000° and not zero: the scale runs from 0° to 9,999°, and the part below 7,000° is reserved for models no source reports on yet, which carry a stand-in number there so the lists stay complete and never outrank a model with data. 7,000° is where measured data begins. A model with real data but almost no downloads sits here; everything that follows is measurement, and the room above the floor holds ten tenfold steps in downloads at 300° each. The floor is the same for every model, so it decides nothing; the degrees above it do.
7,000°
running total
2
Add the downloads.
1,461 download-equivalents in all, from Civitai downloads. Ten times the downloads adds the same 300°, so size matters but never runs away with the score.
+962°
7,962°
running total
3
Add the likes.
39 likes and thumbs up, at half the weight of a download.
+240°
8,202°
running total
4
Add the adoption rate.
About 1 downloads a day right now, measured between two readings, at a quarter of the weight.
+20°
8,222°
running total
5
Bonus for a full model.
A checkpoint carries the weights themselves; add-ons do not outrank one of equal popularity.
+150°
8,372°
running total
6
Take off the age.
The Huny weights came out in 2024: 150° a year, up to 750°, growing until then.
−283°
8,089°
running total
=
The heat score.
Where this model stands on every list of this site. Nothing else adjusts it.
8,089°

Glossary: the terms used here

Heat score: One number for how much a model is used and wanted right now, from 0° to 9,999°. Every list on this site that says hottest is sorted by it and nothing else.
Floor: The 7,000° every model with real data starts from. The scale runs from 0° to 9,999°; the part below the floor is reserved for stand-ins (models without data), so that a model with data always ranks above one without. The floor is the same for everyone and decides nothing; the degrees above it are the measurement.
Download-equivalents: Everything the score treats as a download, added up: downloads themselves, each torrent seeder as 1,000, each AI Horde image and each run on a generation site as one.
Log scale: Counting by tens, not by ones: going from 1,000 to 10,000 downloads adds the same degrees as going from 10,000 to 100,000. It keeps giants from crowding out everything else.
Likes: Thumbs up and likes from every source, worth half a download each on the log scale.
Adoption rate: How many downloads a day a model gets right now, from the difference between two readings of a source. A quarter of the weight of the download term.
Measured and estimated: Measured means two readings of a source exist and the difference is real. Estimated means only today's total is known and the past is spread over the model's life; the site says which one it is showing.
Seeder: Someone who keeps a copy of the weights online for others to download over a torrent, or a hosted mirror doing the same. Each one counts as 1,000 downloads.
AI Horde: A volunteer network that generates images for free on donated computers. The number of images it has made with a model is public, and each counts as one download.
Generation sites: Sites that host their own copies of a model and let people generate with it, such as PixAI, SeaArt and Yodayo. Their downloads count like Civitai's and each generation run as one download.
OpenRouter tokens: A text model served through an API, such as Claude or GPT, has no weights to download, so its usage is measured in tokens: the pieces of text it read and wrote through OpenRouter, a gateway many apps use, over the last 30 days. Every 10,000,000 tokens count as one download. Source: OpenRouter (openrouter.ai/rankings), CC BY 4.0.
Full model (checkpoint): The weights themselves, the file that generates on its own. It gets a bonus because add-ons depend on it.
LoRA and embedding: Small add-on files that steer someone else's weights toward a style, a character or a concept. They cannot run alone.
Family and weights: The base a model is built on, such as SD 1.5, SDXL, Flux or Wan. Every model inherits the release date of its family's weights.
Age: Degrees taken off for how long ago the family's weights came out: 150° a year, up to 750°. It keeps old downloads that had years to pile up from freezing the top of the list.
Family boost: A small, bounded nudge for LoRAs of a family this site is pushing forward right now, always listed in the breakdown.
Stand-in score: A stable number below the floor given to a model no source reports on yet, so lists stay complete. It never ranks above a model with data.
New! (grace period): A model less than 7 days old shows New! instead of a score and holds no place in the rankings. Its score is computed from day one, but a model one day old grows faster than anything, so without the wait the week's #1 would always be whatever came out yesterday rather than what held up for a week.
Trend: How a model's growth over a period compares with the typical model's growth over the same period. Faster than typical reads as a rise, slower as a fall.
Typical model: The middle of the catalog: half the models with a figure grew faster over the period, half slower.

How this model's popularity has moved against the rest of the catalog: its growth in downloads, likes and usage over each period, measured against the typical model's growth over the same period, with its heat score at the time. Above the typical growth reads as a rise, below it as a fall. The past is reconstructed from today's totals, the model's first day and its measured download speed where two readings exist; a model that did not exist at the start of a period shows n/a.

Example renders

NSFW

Prompts and settings shared by the people who made these renders on Civitai. Pick a render to see how it was made.