ai images

It is still possible to achieve more natural cinematic realism for videos with open source models vs proprietary models with even basic workflows | Z-Image-Turbo and LTX 2.3

Overview Z-Image Turbo and LTX 2.3 img2vid combo (also with Flux 2 Klein 9B for additional controls) are actually really…

1 month ago

Model Drop | ZIT + LTX 2.3 + Music Video | Arca Gidan contest

The idea came from something I'm pretty sure most of us live every single day: you wake up, check your…

1 month ago

LTX Desktop 1.0.3 is live! Now runs on 16 GB VRAM machines

The biggest change: we integrated model layer streaming across all local inference pipelines, cutting peak VRAM usage enough to run…

1 month ago

Comparing 7 different image models

Tested a couple of prompts on different models. Only the base model, no community-made loras or finetunes except for SDXL.…

1 month ago

iPhone 2007 [FLUX.2 Klein]

A Lora trained on photos taken with the original Apple iPhone (2007). Works with FLUX.2 Klein Base and FLUX.2 Klein.…

2 months ago

Mugen – Modernized Anime SDXL Base, or how to make Bluvoll tiny bit less sane

Your monthly "Anzhc's Posts" issue have arrived. Today im introducing - Mugen - continuation of the Flux 2 VAE experiment…

2 months ago

Mugen – Modernized Anime SDXL Base, or how to make Bluvoll tiny bit less sane

Your monthly "Anzhc's Posts" issue have arrived. Today im introducing - Mugen - continuation of the Flux 2 VAE experiment…

2 months ago

What model did they use here?

I’ve been seeing this TikTok account a lot where they make mini vlogs as if they lived in the Harry…

2 months ago

[Update] ComfyUI VACE Video Joiner v2.5 – Seamless loops, reduced RAM usage on assembly

Github | CivitAI Point this workflow at a directory of clips and it will automatically stitch them together, fixing awkward…

2 months ago