I built a free local video captioner specifically tuned for LTX-2.3 training —
https://redd.it/1rrsd9i
@rStableDiffusion
https://redd.it/1rrsd9i
@rStableDiffusion
New FLUX.2 Klein 9b models have been released.
https://huggingface.co/black-forest-labs/FLUX.2-klein-9b-kv-fp8
https://redd.it/1rrw4lx
@rStableDiffusion
https://huggingface.co/black-forest-labs/FLUX.2-klein-9b-kv-fp8
https://redd.it/1rrw4lx
@rStableDiffusion
huggingface.co
black-forest-labs/FLUX.2-klein-9b-kv-fp8 · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Flux 2 Klein 9B is now up to 2× faster with multiple reference images (new model)
https://x.com/bfl_ml/status/2032110512381837735
https://redd.it/1rrvnu2
@rStableDiffusion
https://x.com/bfl_ml/status/2032110512381837735
https://redd.it/1rrvnu2
@rStableDiffusion
X (formerly Twitter)
Black Forest Labs (@bfl_ml) on X
FLUX.2 [klein] 9B just got 2x faster at image editing, especially when you use multiple reference images. Same quality, no price increase.
This media is not supported in your browser
VIEW IN TELEGRAM
Down to 32s gen time for 10 seconds of Video+Audio by using DeepBeepMeep's UI. LTX-2 2.3 on a 4090 24gb.
https://redd.it/1rrre4d
@rStableDiffusion
https://redd.it/1rrre4d
@rStableDiffusion
This media is not supported in your browser
VIEW IN TELEGRAM
Can't believe I can create 4k videos with a crap 12gb vram card in 20 mins
https://redd.it/1rya228
@rStableDiffusion
https://redd.it/1rya228
@rStableDiffusion
ComfyUI Tutorial: First Last Frame Animation LTX 2.3 Workflow
https://youtu.be/O1gUVbfC2tI
https://redd.it/1rxw0k3
@rStableDiffusion
https://youtu.be/O1gUVbfC2tI
https://redd.it/1rxw0k3
@rStableDiffusion
YouTube
ComfyUI Tutorial: First Last Frame Animation LTX 2.3 Workflow #comfyui #comfyuitutorial
hello everyone, welcome back in this tutorial, i will show you how to use the first and last frame workflow with the LTX2.3 Model for amazing ai video generation. this comfyui workflow is perfect for creating video with two images and it is optimized for…
KittenML/KittenTTS: State-of-the-art TTS model under 25MB 😻
https://github.com/KittenML/KittenTTS
https://redd.it/1rye1wb
@rStableDiffusion
https://github.com/KittenML/KittenTTS
https://redd.it/1rye1wb
@rStableDiffusion
GitHub
GitHub - KittenML/KittenTTS: State-of-the-art TTS model under 25MB 😻
State-of-the-art TTS model under 25MB 😻 . Contribute to KittenML/KittenTTS development by creating an account on GitHub.
ZIT Rocks (Simply ZIT #2, Check the skin and face details)
ZIT Rocks!
Details (including prompt) all on the image.
https://redd.it/1rykbhe
@rStableDiffusion
ZIT Rocks!
Details (including prompt) all on the image.
https://redd.it/1rykbhe
@rStableDiffusion
This media is not supported in your browser
VIEW IN TELEGRAM
Sharing my Gen AI workflow for animating my sprite in Spine2D. It's very manual because i wanted precise control of attack timings and locations.
https://redd.it/1ryqfe9
@rStableDiffusion
https://redd.it/1ryqfe9
@rStableDiffusion