Stable Diffusion Tutorials
@SD_Tutorial
๐ Ai models local installation
๐ Comfy Workflows
๐ Tutorials (Image Gen, Video gen)
FOLLOW WEBSITE ๐๐
88 Following 6.9K Followers
๐คจ They are watching and taking down ! ๐
Mnimax H3 ๐๐ ๐N$FW
The Uncensored variant, built for content creators, educators, indie studios, and everyone who wants a video model that stops saying no.
๐
MiniMax H3 ๐คFast Gen Tip
Add these nodes for faster gen time: EasyCache + Patch-Sol-Attn + Patch Sage Attention KJ
From Kijai:
Patch Sol Attention
Patch Sage Attention KJ:
Show more
Will Smith x Spaghetti remix ๐คช
MiniMax-H3 on RTX 3060 6GB & 64GB RAM
(A 5s 480p T2V clip took around 4โ5 mins using EasyCache + SageAttention)
FLUX 3 Video is here.
Serious, fun, creative, real, cinematic, whatever you need it to be.
Native audio, Text to Video, Image to Video with multiple frames, video continuation, dialogue in multiple languages.
Comes with Draft mode so you can explore ideas fast at a fraction of the cost.
Up to 20 seconds and 1080p native.
Available in the API or in your favorite tool. 2K, 4K, and Open Weights coming soon.
Show more
Will Smith x Spaghetti remix ๐คช
MiniMax-H3 on RTX 3060 6GB & 64GB RAM
(A 5s 480p T2V clip took around 4โ5 mins using EasyCache + SageAttention)
More details on this :
MiniMax H3 โก๏ธ Spectrum acceleration
in ComfyUI
โ 34% lower Euler sampling time, 30% lower RES time
Tested at approximately 0.5 MP, 8 seconds and 20 steps on an RTX PRO 6000 under WSL, using High VRAM mode
๐
Show more
MiniMax H3 โก๏ธ Spectrum acceleration
in ComfyUI
โ 34% lower Euler sampling time, 30% lower RES time
Tested at approximately 0.5 MP, 8 seconds and 20 steps on an RTX PRO 6000 under WSL, using High VRAM mode
๐
Show more
MiniMax H3 ๐๐๐ Naughty Times LoRA
Tip-
Run it with a lora loader at value 0.5 using the model
(minimax_h3_fl2va_pruned_int8_convrot.safetensors)
๐
MiniMax-H3 ๐ Multishot Workflow
Chain multiple MiniMax-H3 shots into one continuous video with audio - in one node.
Make 30 sec long video
๐
Wan 3 ๐ง
on the way
-Audio+video
-30 sec max video
-at 1080 res
Mnimax H3 ๐๐ ๐N$FW
The Uncensored variant, built for content creators, educators, indie studios, and everyone who wants a video model that stops saying no.
๐
๐ฒ Minimax H3 on 3rd ...
Trending list of Hugging face
Ostris AI Toolkit now supports training LoRAs for @MiniMax_AI MiniMax H3. Only T2V and I2V for now. I will be adding reference, more features, and optimizations over the next few days. This one uses Comfy quantized weights, read the model notes for more info.
Show more
Minimax H3 ๐Video Gen models + workflows
(NVFP4/BF16/FP8/INT8/INT4/GGUFs)
community released
All listed at one place
๐๐ฒ
MiniMax H3 ๐ ( INT4, INT8, Mixed, NVFP4)
Community-compiled collection of quantized and pruned weights
for 12GB to 24 GB VRAMS users
๐
Some H3's new variants is coming !!!
Hell yaa.. ๐the wait is over
Minimax H3 ๐Open weights
on ComfyUI
๐๐
Hell yaa.. ๐the wait is over
Minimax H3 ๐Open weights
on ComfyUI
๐๐
Krea 2+ Lenovo ultrareal lora
mostly generated on K2 raw with cfg 4-5, some generated with cfg 1 + K2 turbo lora
Used loras
workflow
Show more
