Analysis
Opinion, explainers and guides from people worth reading.
Overwhelmed with Minimax 3 combinations
I've been testing MiniMax H3 in ComfyUI for a while now, and I'm definitely not new to ComfyUI, but I'm getting frustrated with the sheer number of configurations people recommend.
microsoft/AesCode 8B and 32B
AesCode generates information-rich visual artifacts such as slides, posters, and dashboards as HTML/CSS.
Best way to use H3 ref2video. Not even joking. it just works and is easier to manage than any replacing attempts fighting the Model
Just draw your composition and let Minimax figure it out instead of using references from the internet
Long Shot Studio v0.6.13 (degradation test)
After more back and forth with Claude for optimization and UI change, here is the latest update of Long Shot Studio.
qwen 2.1 turbo or normal - fixed the artifacts
hi guys, i fixed the confyui workflow with sigmas recommended by qwen 2.1 so artifacts are very reduced or no more...
I am building a web application to transform images into Gaussian Splats
I’ve been playing with orbit-style videos from video models (lately Minimax H3 in ComfyUI) and kept thinking they’d make great input for Gaussian Splatting.
Update: Kroma, A Krea-2 Fine Tune
Hey everyone, First of all, thank you to everyone for supporting this project, and to the Krea team who made the best uncompromised base model.
Some realistic / cinematic Kroma gens
Euler / Simple / 8 steps / CFG = 1.0
I built GOAT’d Text Generator 🐐 - generate prompts directly in ComfyUI
I made a custom node that brings cloud and local LLMs into your ComfyUI workflows.
Updated ComfyUI-SeedVR2-VideoUpscaler-with-TensorRT v1.6.6 - Native ConvRot W4A8 Support & DisTorch2 Scope
The other day, when I published information about v1.5.7, I received a request in the comments regarding support for w4a8.
I built a free anime character & prompt library for AI art creator
I'm an AI art creator, and for a while now I've been wanting a better way to organize character prompts, find inspiration, and experiment with different scenes without having to dig through a bunch of different sources.
AuroraIMG-6M Released!
It's a tiny 6M parameter text to image model, and it can make recognizable images at 64x64.
I fine-tuned SD1.5 to make 16×16 Minecraft item textures
I fine-tuned SD1.5 on Minecraft item textures.
how do you maintain style in minimax h3 ref mode?
I'm providing images with certain style (unique illustration) and the model (regular one) simply change the style.
Building prompts with LLMs
I’ve been into AI image and video generation for a while, and I’ve been a bit obsessed with H3 for the past two months.
How to pick the right models and dramatically speed up image and video generation speeds & What I wish I knew when starting on AMD hardware with ComfyUI
For the below I’ll be referring mostly to ComfyUI workflow and model efficiency (using examples for Radeon AI PRO R9700 (32GB) which has a bandwidth of 680GB/sec.
Minimax h3 veterans (share your wisdom)
When I use Minimax h3 to generate a video with any mode (fl2va/r2va) in most cases it generates good output with really good prompt adherence (mostly).
4090 VS 5090 MINIMAX H3 SPEED
To those who used to have a 4090, what percentage of speed improvement have you noticed after upgrading to a 5090?
TensorSharp now supports Qwen Image 2.1 Turbo + LoRA — Here's a quick image editing demo
I've been working on adding more image generation and editing capabilities to TensorSharp, and I'm happy to share that it now supports Qwen Image 2.1 Turbo and LoRA!
Need help with Illustrious inage gens
I have also been looking around to see which model does anime image best and a lot of people don’t even mention Pony, most people seem to use Illustrious but from what I have experienced Illustrious isn’t doing it for me, is it again due the version of Illustrious?
Qwen Image 2.1 Turbo - extend 'magic' 8 steps sigmas further
So, I've decided to try Qwen Image 2.1 Turbo with the following 'magic' sigmas, taken directly from their Diffusers implementation:
Will there be another, more up-to-date Anime DIT Model project in the open-source community besides Anima?
My info isn't very current, so I'd like to ask if anyone knows whether there's another, more up-to-date Anime DIT Model project in the open-source community besides Anima?