Stable Diffusion Tutorials
@SD_Tutorial
๐ Ai models local installation
๐ Comfy Workflows
๐ Tutorials (Image Gen, Video gen)
FOLLOW WEBSITE ๐๐
90 Following 11.1K Followers
Minimax H3 ๐๐นSnorricam LORA
For intense, chaotic cinematic camera angle Snorrcam Style like iconic body-bound camera rig used in movies
๐
Minimax H3๐TaoMate LORA for Comfy
3Step LORA๐
Use this with TaoMate-H3 ๐
Minimax H3 ๐
All workflow types listed at one place
-Basic/apis
-FastH3
-VFX control
-VSA/VDA
-upscaler etc....
Source HF repo:๐
YuE2 ๐ถ๐ต Comfy Support
an open music generation model with frontier song quality competitive with Suno v5/v6,Turn lyrics and a style prompt into a complete song with vocals and accompaniment, then shape its melody and chords through an editable score
๐
Show more
LTX-2.5 ๐๐ IC-LoRA Day-to-Night Relighting
It re-renders a daytime video as the same shot at night while preserving composition, framing, camera movement, and subject motion frame-for-frame.
๐
Show more
LTX-2.5 ๐๐ง IC-LoRA Water Simulation
It adds water to a clip rivers, surf, rain, waterfalls, floods, splashes, spray, and wet-surface specularities while keeping everything identical to the reference.
๐
Show more
LTX 2.5 ๐ Clean Plate IC-LoRA
It removes people and other dynamic subjects from a source video and reconstructs the empty background, producing a clean "clean plate" of the same scene
๐
Show more
LTX-2.5 ๐ค IC-LoRA Deblur
It restores sharpness to out-of-focus / defocused video by conditioning on the blurry clip and regenerating it in sharp focus while preserving the original subject, framing, and scene geometry.
๐
Show more
LTX-2.5 ๐ ๐๏ธ IC-LoRA Decompression
It removes compression artifacts from low bit-rate / heavily-compressed video โ macroblocking, chroma bleed, ringing, and banding โ while preserving subject identity, framing, and geometry.
๐
Show more
LTX-2.5 ๐ง IC-LoRA Colorization
restores natural color to grayscale, monochrome, or desaturated video while keeping subject identity, framing, and geometry untouched โ only the color information changes.
๐
Show more
Lightricks
LTX-2.5 ๐Cinemagraph LoRA
Transforms still images into smooth, looping cinemagraphs with selective motion while keeping the rest of the scene frozen.
๐
Show more
Lightricks
LTX 2.5 ๐ Ingredients Ref Sheet IC LORA
conditions video generation on a reference sheet-a single composite image inventorying the characters, props, and location of a scene so that generated videos keep those elements visually consistent
๐
Show more
Minimax H3 ๐ ๐ฅ VFX Camera control
Visual camera planner for MiniMax H3 inside ComfyUI. You drag the camera around a 3D sphere, place keyframes on a timeline, and the node compiles that trajectory into prompts that H3 understands.
Workflow on civitAI:๐
Show more
Marigold V2 ๐ง Comfy Support
designed by HUAWEI Bayer Lab for dense visual prediction, it takes a standard 2D image and calculates detailed, pixel-by-pixel convert into 3D structured data and surface properties.
๐
Show more
MiniMax H3 ๐ถโ๐ซ๏ธ Sharpness LORA
This supports ref2VA/fl2va, sharpens a source video while keeping it photorealistic. It conditions on the source through guide latents rather than through the model's native reference-video node.
๐
Show more
FLUX 3 ๐ง ๐ฅฒ
Minimax H3 ๐ Human Motion Lora
To get Smoother human motion and body movement for T2V/I2V
๐
Minimax H3 ๐คณ๐ฑ Influencer Lora
For Instagram and TikTok aesthetics style
Supports T2V/I2V
Resolution: 720x1280
Weight: 0.75-0.8
Steps: 15-30
๐
MiniMax H3 ๐Facial Realism CloseUp LORA
trained on a high-quality, human-centric face portrait dataset composed of video buckets featuring subtle facial details and micro-expressions.
๐
Show more
MiniMax H3 ๐Facial Realism CloseUp LORA
trained on a high-quality, human-centric face portrait dataset composed of video buckets featuring subtle facial details and micro-expressions.
๐
Show more
