Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

LTXV 2.3 OmniNFT RL Lora T2V test

toyxyz3's profile picture

toyxyz

31,335 subscribers

30,983 Aufrufe • vor 3 Monaten •via X (Twitter)

Kunst
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

ichika (SVI lora test)
0:14

ichika (SVI lora test)

BluCopi 🔞

15,916 Aufrufe • vor 7 Monaten

This LTX 2.3 Video Outpainting LoRA by Mohamed Oumoumad is no joke. So cool!!!!
0:13

This LTX 2.3 Video Outpainting LoRA by Mohamed Oumoumad is no joke. So cool!!!!

Purz.ai

42,290 Aufrufe • vor 4 Monaten

Kling 3.0 Multishots 15s 1080p t2v Car chase sequence test Prompt below
0:15

Kling 3.0 Multishots 15s 1080p t2v Car chase sequence test Prompt below

MayorkingAI

12,509 Aufrufe • vor 6 Monaten

Really impressed by this outpaint IC-LoRA for LTX 2.3 from Mohamed Oumoumad, it fills in quite seamlessly 🔥 demo coming ✨
0:11

Really impressed by this outpaint IC-LoRA for LTX 2.3 from Mohamed Oumoumad, it fills in quite seamlessly 🔥 demo coming ✨

Linoy Tsaban

17,753 Aufrufe • vor 4 Monaten

これ原因判明！LTX-2.3で追加されたLTXScheduler(左)だった。これをLTX-2のWorkflowにあるManualSigmas(右下)にまんま入れ替えるか、Steps数増やす時にはBasicScheduler(右上)入れ替えればOK。で、LTX-2用の顔LoRAも似る様になった(笑) ↓非蒸留版+DistilledLoRA(0.85)でt2v これならt2vも行けるw
0:15

これ原因判明！LTX-2.3で追加されたLTXScheduler(左)だった。これをLTX-2のWorkflowにあるManualSigmas(右下)にまんま入れ替えるか、Steps数増やす時にはBasicScheduler(右上)入れ替えればOK。で、LTX-2用の顔LoRAも似る様になった(笑) ↓非蒸留版+DistilledLoRA(0.85)でt2v これならt2vも行けるw

Photogenic Weekend

15,973 Aufrufe • vor 5 Monaten

My first test with Seedance 2.0. T2V. One-shot. It absolutely cooked! The bar has been set. This is the standard now.
0:15

My first test with Seedance 2.0. T2V. One-shot. It absolutely cooked! The bar has been set. This is the standard now.

WuxIA Rocks

12,902 Aufrufe • vor 6 Monaten

LTX 2.3 Creative Upscale IC-LoRA. - Generative second-pass refiner for soft or low-resolution video; - enhances detail and clarity without standard upscaling; - output varies based on workflow/settings.
0:14

LTX 2.3 Creative Upscale IC-LoRA. - Generative second-pass refiner for soft or low-resolution video; - enhances detail and clarity without standard upscaling; - output varies based on workflow/settings.

Wildminder

17,151 Aufrufe • vor 3 Monaten

I made the workflow for comfyui to use Ltx 2.3 render to real Ic-lora ! If you want to go fast you can just use our endpoint : workflow available here :
0:14

I made the workflow for comfyui to use Ltx 2.3 render to real Ic-lora ! If you want to go fast you can just use our endpoint : workflow available here :

Lovis Odin

30,292 Aufrufe • vor 1 Monat

Updated: 😃LTX 2.3 Video Edit Lora📽️✂️ -Helpful for video editing, background/subject removal, motion transfer etc. -The new updated version improves on consistent results and prompt adherence Model + Workflows:👇
0:15

Updated: 😃LTX 2.3 Video Edit Lora📽️✂️ -Helpful for video editing, background/subject removal, motion transfer etc. -The new updated version improves on consistent results and prompt adherence Model + Workflows:👇

Stable Diffusion Tutorials

21,400 Aufrufe • vor 1 Monat

my favorite of the new LTX 2.3 LoRAs ✨ Remember when a year ago we need a full on model like VACE to do that? and now an IC LoRA is even better
0:13

my favorite of the new LTX 2.3 LoRAs ✨ Remember when a year ago we need a full on model like VACE to do that? and now an IC LoRA is even better

Linoy Tsaban

12,814 Aufrufe • vor 2 Monaten

The LTX 2.3 desktop tool has been updated, now supporting LoRA and multi-frame insertion. Download: Video tutorials are not yet available; please follow my channel: More effects are in the comments section.
0:13

The LTX 2.3 desktop tool has been updated, now supporting LoRA and multi-frame insertion. Download: Video tutorials are not yet available; please follow my channel: More effects are in the comments section.

大雄

14,986 Aufrufe • vor 4 Monaten

LTX 2.3 is now live on Krea. this video model generates for 1/10th the cost of other top models and can learn any style or character - just upload some references and train a lora try it now 👇
0:12

LTX 2.3 is now live on Krea. this video model generates for 1/10th the cost of other top models and can learn any style or character - just upload some references and train a lora try it now 👇

Krea

21,845 Aufrufe • vor 3 Monaten

I'm currently training a "DeArchive" IC-LoRA, still cooking, some weird warp in the hair, but for those who'd like to test the early steps with me :
0:10

I'm currently training a "DeArchive" IC-LoRA, still cooking, some weird warp in the hair, but for those who'd like to test the early steps with me :

Mohamed Oumoumad

26,711 Aufrufe • vor 3 Monaten

reshooting a video from a camera that was never there 📹 This LTX-2.3 IC-LoRA re-renders real footage from a NEW angle - same scene, same action, different camera. Pick "far to the left, higher, further" and it just… moves Cooked by Cseti 🧑‍🍳 try it live on Hugging Face: ▶️
0:10

reshooting a video from a camera that was never there 📹 This LTX-2.3 IC-LoRA re-renders real footage from a NEW angle - same scene, same action, different camera. Pick "far to the left, higher, further" and it just… moves Cooked by Cseti 🧑‍🍳 try it live on Hugging Face: ▶️

Hugging Apps

16,809 Aufrufe • vor 27 Tagen

New open source LoRA Multi-Angles I created with fal for Flux.2 🔥 Flux2.-Lora-Multi-Angles: give a camera angle in degrees → get your image from that view. To build this, I created a system that captures 72 positions from Gaussian Splatting to generate the training dataset fully automatically in a webgl viewer. ▶️ Test: 📥 Weights: Should I open source my WebGL viewer so you can train your own from gaussian splatting ?
0:14

New open source LoRA Multi-Angles I created with fal for Flux.2 🔥 Flux2.-Lora-Multi-Angles: give a camera angle in degrees → get your image from that view. To build this, I created a system that captures 72 positions from Gaussian Splatting to generate the training dataset fully automatically in a webgl viewer. ▶️ Test: 📥 Weights: Should I open source my WebGL viewer so you can train your own from gaussian splatting ?

Lovis Odin

43,693 Aufrufe • vor 8 Monaten

LTX 2.3 Video Outpainting LoRA デフォルトのWFだと元動画も微細な影響受けるから元動画部分はマスク合成したほうがキレイにはなりそう 横長と縦長行き来とか、ちょっと足りない部分の補完がこんなに簡単になるのは凄い
0:15

LTX 2.3 Video Outpainting LoRA デフォルトのWFだと元動画も微細な影響受けるから元動画部分はマスク合成したほうがキレイにはなりそう 横長と縦長行き来とか、ちょっと足りない部分の補完がこんなに簡単になるのは凄い

852話(hakoniwa)

21,311 Aufrufe • vor 4 Monaten

Inkling-small is out today! With SGLang, you can get 648 tok/s decode with DSpark (simulated acc len=4) and 288 tok/s w/o DSpark, under the same setup (8x NVIDIA AI B200, TP 8, NVFP4, bs=1). What makes this model different is the size. 276B total with 12B active is a sweet spot for RL, and both LoRA and full-parameter training become well within reach. Miles is ready and verified for multimodal RL on Inkling-small, so you can turn your multimodal data into real capability gains. At ~1/4 the size, Inkling-small matches the bigger version in capability and even wins on some benchmarks. Run Inkling-small with SGLang, and customize it with Miles.
0:18

Inkling-small is out today! With SGLang, you can get 648 tok/s decode with DSpark (simulated acc len=4) and 288 tok/s w/o DSpark, under the same setup (8x NVIDIA AI B200, TP 8, NVFP4, bs=1). What makes this model different is the size. 276B total with 12B active is a sweet spot for RL, and both LoRA and full-parameter training become well within reach. Miles is ready and verified for multimodal RL on Inkling-small, so you can turn your multimodal data into real capability gains. At ~1/4 the size, Inkling-small matches the bigger version in capability and even wins on some benchmarks. Run Inkling-small with SGLang, and customize it with Miles.

LMSYS Org

119,759 Aufrufe • vor 19 Tagen

🚀 Update Next Scene V2 only 10 days after last version, now live on Hugging Face 👉 🎬 A LoRA made for Qwen Image Edit 2509 that lets you create seamless cinematic “next shots” — keeping the same characters, lighting, and mood. I trained this new version on thousands of paired cinematic shots to make scene transitions smoother, more emotional, and real. 🧠 What’s new: • Much stronger consistency across shots • Better lighting and character preservation • Smoother transitions and framing logic • No more black bar artifacts Built for storytellers using ComfyUI or any diffusers pipeline. Just use “Next Scene:” and describe what happens next , the model keeps everything coherent. 🧩 Try it directly in ComfyUI, or check the thread to launch it on fal . Open-source, no restrictions, made for filmmakers, animators, and dreamers. ComfyUI #AIcinema #LoRA #Flux #Qwen #ComfyUI #AIart #GenerativeVideo you can test on comfyui or to try on you can go here : and use my lora link : start your prompt with "Next Scene:" and lets go !!
0:17

🚀 Update Next Scene V2 only 10 days after last version, now live on Hugging Face 👉 🎬 A LoRA made for Qwen Image Edit 2509 that lets you create seamless cinematic “next shots” — keeping the same characters, lighting, and mood. I trained this new version on thousands of paired cinematic shots to make scene transitions smoother, more emotional, and real. 🧠 What’s new: • Much stronger consistency across shots • Better lighting and character preservation • Smoother transitions and framing logic • No more black bar artifacts Built for storytellers using ComfyUI or any diffusers pipeline. Just use “Next Scene:” and describe what happens next , the model keeps everything coherent. 🧩 Try it directly in ComfyUI, or check the thread to launch it on fal . Open-source, no restrictions, made for filmmakers, animators, and dreamers. ComfyUI #AIcinema #LoRA #Flux #Qwen #ComfyUI #AIart #GenerativeVideo you can test on comfyui or to try on you can go here : and use my lora link : start your prompt with "Next Scene:" and lets go !!

Lovis Odin

43,276 Aufrufe • vor 10 Monaten

we just released a new blog "Training a coding agent using the OpenCode harness in remote HF sandboxes with TRL and OpenEnv" you can take a real coding agent (OpenCode), let it run its own tool loop against real coding problems, and train it with RL on the exact tokens it produced and every rollout runs in its own remote HF sandbox, so rollouts scale out beyond one machine the loop: - OpenCode owns its tool loop inside an OpenEnv sandbox - an in-sandbox proxy records the real token ids + logprobs, per turn - a hidden-test verifier scores the result, and that is the reward - TRL trains with AsyncGRPO, weights sync back to vLLM over NCCL blog + runnable example:
0:13

we just released a new blog "Training a coding agent using the OpenCode harness in remote HF sandboxes with TRL and OpenEnv" you can take a real coding agent (OpenCode), let it run its own tool loop against real coding problems, and train it with RL on the exact tokens it produced and every rollout runs in its own remote HF sandbox, so rollouts scale out beyond one machine the loop: - OpenCode owns its tool loop inside an OpenEnv sandbox - an in-sandbox proxy records the real token ids + logprobs, per turn - a hidden-test verifier scores the result, and that is the reward - TRL trains with AsyncGRPO, weights sync back to vLLM over NCCL blog + runnable example:

Sergio Paniego

36,159 Aufrufe • vor 13 Tagen