Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

LTX-2.5 is native in ComfyUI, day zero with the weights Model highlights: → Diffusion Fidelity Rendering - compute allocated by scene complexity, not spread evenly → Diffusion Video Decoder - replaces VAE decoding, sharper faces and legible text → Native multi-shot - one run, multiple connected shots, consistent across...

2,406,572 görüntüleme • 3 ay önce •via X (Twitter)

17 Yorum

ComfyUI profil fotoğrafı
ComfyUI3 ay önce

Click the link below:

Prince does AI profil fotoğrafı
Prince does AI3 ay önce

legible text in video is the part i care about

ComfyUI profil fotoğrafı
ComfyUI3 ay önce

That I 100% agree with.

Rob Hoffman (No longer redacted) profil fotoğrafı
Rob Hoffman (No longer redacted)3 ay önce

In my meager tests, it's a big speed improvement. Looking forward to giving it a real workout this weekend.

LabMike 3D profil fotoğrafı
LabMike 3D3 ay önce

I'm currently testing LTX 2.5 on my RTX 3060 12GB, and it's pretty fast with great quality. Cheers!

泰多宝 profil fotoğrafı
泰多宝3 ay önce

The decoder swap is the one that changes what you can ship. A VAE trained on reconstruction loss averages high-frequency detail, and faces and glyphs are made of exactly that — you get texture that looks like text rather than text. A diffusion decoder generates the detail instead of averaging it, which is why it comes out legible. The tradeoff rides along though: legible isn't correct, since it synthesises plausible strokes rather than recovering the encoded ones.

LabMike 3D profil fotoğrafı
LabMike 3D3 ay önce

LTX 2.5 on RTX 3060: Impressive Speed & Quality Out of the Box

JSFILMZ profil fotoğrafı
JSFILMZ3 ay önce

10 sec max duration in 2026 is wild

smallzero profil fotoğrafı
smallzero3 ay önce

I got you! Already created a video showing how to launch inside ComfyUI

Vini profil fotoğrafı
Vini3 ay önce

Allocating compute by scene complexity instead of evenly is smart engineering.

Mr Zoulll profil fotoğrafı
Mr Zoulll3 ay önce

Mon RTX 5090 l'adore. 🥰

Hao profil fotoğrafı
Hao3 ay önce

拿中文语境做了2次实验,跟h3对比…🤦

Nazar profil fotoğrafı
Nazar3 ay önce

Replacing VAE decoding is the line people will skim past and shouldn't. Faces and text going soft in the decode has been the tell on every open video model. If that is genuinely fixed, it changes what these are usable for beyond b-roll.

Narine Saw profil fotoğrafı
Narine Saw2 ay önce

Ltx lol Mini Max h3 !!!

derrick has started yet another project profil fotoğrafı
derrick has started yet another project3 ay önce

No more Israeli models thanks

ReAiLity Labs profil fotoğrafı
ReAiLity Labs3 ay önce

Is a new template being pushed out in Comfyui or did the existing ltx templates get updated?

Edgex profil fotoğrafı
Edgex3 ay önce

Wow, the Diffusion Fidelity Rendering really changes the game - love how it adapts to scene complexity.

Benzer Videolar

Auto regressive LLMs are officially on notice. run Gemma 4 26B diffusion gguf with llama.cpp Google just dropped DiffusionGemma-26B, and it completely flips how we generate text. instead of predicting words one by one, it generates 256 tokens in parallel using bi-directional attention. its like stable diffusion, but for language. the model starts with random text "noise" and iteratively refines and self-corrects the entire block in real-time to fix formatting and reasoning errors on the fly. since it’s a Mixture of Experts (MoE) that only activates 3.8B parameters during inference, it fits perfectly on consumer hardware. You can run the Q4_K_M quant with an 18GB VRAM budget on a single RTX 3090 or RTX 4090 with exceptional throughput. Tested on Ubuntu 22 with CUDA 13.1 using the cutting edge experimental llama.cpp branch. Here is how to compile and run it with the live terminal denoising visualizer: # 1. Clone & check out the experimental PR (#24423) - 1) git clone && cd llama.cpp -git fetch origin 2) pull/24423/head:diffusiongemma && --git checkout diffusiongemma # 2. Build with CUDA support 1) cmake -B build -DGGML_CUDA=ON -DCMAKE_CUDA_ARCHITECTURES=native 2) cmake --build build -j $(nproc) --config Release --target llama-diffusion-cli # 3. Run with live visual denoising (llama.cpp flags) ./build/bin/llama-diffusion-cli \ -m /path/to/diffusiongemma-26B-A4B-it-Q4_K_M.gguf \ -ngl 99 -cnv -n 2048 --diffusion-visual Watch the video below to see the live --diffusion-visual canvas iteratively de noising the prompt output in real time. guide and unsloth's hugging face GGUF model links are in the comments below! Is auto regressive generation officially legacy tech? Let me know what you think.

Alok

52,656 görüntüleme • 5 ay önce