Hunyuan AI models
Hunyuan is Tencent's open model family: HunyuanVideo, the 13 billion parameter text-to-video and image-to-video model known for natural motion and strong prompt following, and HunyuanDiT for images. The video model was the first open weight release to compete with closed services on realism, and it trains LoRAs well, so the community has produced hundreds of motion, style and character LoRAs for it. This page ranks them by heat and links each one to its example clips, trigger words and source page.
Hottest Hunyuan models
8470°
HunyuanVideo POV Missionary
8422°
SECRET SAUCE
8408°
HunyuanVideo Female Masturbation
8400°
Better Titfuck (MiniMax, Wan, HunYuan) C...
8386°
HunyuanVideo Cumshot
8385°
HunyuanVideo POV Blowjob
8342°
Sideview DeepThroat Blowjob HunyuanVideo...
8339°
Riding Dildo for Hunyuan Video
8332°
HunyuanVideo POV Missionary
8330°
HunyuanVideo POV Blowjob
8321°
HunyuanVideo Reverse Cowgirl
8306°
Pussyjob Hunyuan Video LoRA
Hunyuan guides
Cloud services
Flat fee vs tokens: why unlimited plans like Graydient.ai are the best value for AI creators in 2026
A ranked cost comparison, with prices checked on 8 October 2026, of flat-fee unlimited plans like Graydient.ai against token and credit pricing from Midjourney, Leonardo, fal.ai, Replicate, Runway and Kling: what 1,000 images and 1,000 videos a month really cost on each, and why one fixed fee for unlimited images, video, audio, Grok LLM chat and web apps is the best value for creators who iterate.
Errors & fixes
CUDA out of memory: how much VRAM each AI model needs and how to fit it
A VRAM table for SD 1.5, SDXL, Flux, FLUX.2, Qwen-Image, Z-Image, Wan 2.2 and HunyuanVideo, and the techniques that make a model fit: fp8 and GGUF quantisation, CPU offload, tiled VAE, resolution and frame limits, and when to stop fighting and run it hosted.
Video models
Best open-source AI video models in 2026: what you can actually download
The best open-weight AI video models you can download in October 2026, ranked by use: Wan 2.2 A14B for quality and a clean license, LTX-2.5 for video with sound, HunyuanVideo 1.5 for 12 to 16 GB cards, Wan 2.2 5B and FramePack for 8 GB, MiniMax H3 as the most capable with a regional license catch. Sizes, licenses, audio and practical VRAM for each.
ComfyUI
HunyuanVideo text to video ComfyUI workflow: the 13B model that started local video
The ComfyUI example workflow for Tencent's HunyuanVideo: the 13B 720p model with clip_l and the LLaVA-Llama 3 encoder, a SamplerCustomAdvanced chain with FluxGuidance 6 and shift 7, tiled VAE decode, 848x480 at 73 frames. Four files, the fp8 switch for 8 to 16 GB cards, and the prompts it likes. Workflow JSON hosted here.
Apps
How to install Wan2GP: AI video and images on low-VRAM GPUs
Wan2GP runs Wan, LTX, Hunyuan, Flux and Qwen on GPUs with as little as 6 GB of VRAM. How to install it on Windows, Linux or an AMD card (Pinokio, the included scripts or by hand), which settings to use and what to do when it runs out of memory.
Errors & fixes
VRAM requirements for every popular AI image and video model (2026): full precision, FP8 and GGUF
How much VRAM you need for SD 1.5, SDXL, SD 3.5, Z-Image Turbo, FLUX.1, FLUX.2 Klein and Dev, Qwen-Image, Wan 2.2, HunyuanVideo 1.5 and LTX-2, at full precision, FP8 and 4-bit GGUF, with the comfortable card and licence for each, what every GPU size from 8 to 48 GB can run, and the order of fixes when a model does not fit.
Other model families
Text / LLM Models
434
Anima Models
528
Chroma Models
19
Fibo Models
2
Flux Models
1,496
Flux 2 / Klein Models
1,239
Flux 3 Models
3
Moss Models
3
Iris Models
1
MiniMax H3 Models
364
Ideogram Models
20
Krea2 Models
717
Qwen Models
20
Qwen2 Models
47
Ltx2 Models
153
Stable Diffusion 1.5 Models
7,042
Stable Diffusion XL 1.0 Models
17,446
Zimage Models
815
Wan Models
1,067
ACE-Step Models
2
AuK Models
1
Boogu Models
2
Chatterbox TTS Models
1
Cosmos Models
1
Ernie Image Models
2
FireRed Models
1
HeartMuLa Models
1
HiDream Models
3
Higgs Audio Models
1
JoyAI Echo Models
1
Lumina Models
2
MiniMax Music Models
1
MisoTTS Models
1
Microsoft Lens Models
1
PixelDiT Models
1
Stable Diffusion 3.5 Models
12
SFX Bank Models
1
Upscalers Models
14
YuE Models
2