💥 Hunyuan 💥 Vid2Vid & Txt2Vid | FAST Test Bench V1 |
5.0
0 reviewsDescription
HUNYUAN | Test bench
12 seconds generation time per video*
*rtx3090
💥 INCREDIBLE MODEL JUST CAME OUT TODAY 💥 i'm shocked.
Kijai, our lord, has already made huge improvements to allow us to run this gold on consumer hardware with great speed. So, here we go:
With settings included in this workflow you can easily explore the latent space capabilities of this 13B beast and do all stress tests you want.
⚠️To run this model you need to install torch on windows, wich is kinda pain in the ass.
Fortunately purz wrote an installation guide for all of us:
⚠️ beware⚠️
this model is completly uncensored. It has a understanding of human anatomy at all levels.
install:
https://github.com/kijai/ComfyUI-HunyuanVideoWrapper
get triton working on windows:
https://purz.notion.site/Get-Windows-Triton-working-for-Mochi-6a0c055e21c84cfba7f1dd628e624e97
Discussion
(No comments yet)
Loading...
Resources (2)
Reviews
No reviews yet
Versions (1)
- latest (a year ago)
Node Details
Primitive Nodes (61)
Anything Everywhere? (2)
DF_Int_to_Float (1)
DownloadAndLoadFlorence2Model (1)
DownloadAndLoadHyVideoTextEncoder (1)
Fast Groups Bypasser (rgthree) (1)
FinalFrameSelector (1)
Florence2Run (1)
GetNode (15)
HyVideoDecode (1)
HyVideoEncode (1)
HyVideoModelLoader (1)
HyVideoSampler (1)
HyVideoTextEncode (1)
HyVideoVAELoader (1)
If ANY return A else B-🔬 (1)
Label (rgthree) (11)
SetNode (13)
Switch any [Crystools] (1)
mxSlider (6)
Custom Nodes (34)
- CM_IntBinaryOperation (2)
- CR Text Concatenate (1)
ComfyUI
- ImageScale (1)
- LoadImage (1)
- PreviewImage (1)
- easy cleanGpuUsed (1)
- easy compare (1)
- easy showAnything (1)
- ImpactSwitch (1)
ComfyUI_tinyterraNodes
- ttN seed (1)
- Float (1)
- TextInput_ (1)
- VHS_VideoCombine (1)
- VHS_LoadVideo (1)
- Image Switch (JPS) (1)
- ImagePass (2)
- ShowText|pysssss (2)
- Int Literal (12)
- Text Find and Replace (2)
Model Details
Checkpoints (0)
LoRAs (0)