Repository Issue Activity (beta)

#288 [ltx-pipelines] i2v at 1216x832 crashes DiffVAE decoder with illegal memory access (t2v same res OK, i2v 704/768 OK)

#287 LTX2.t

#286 OneTrainer support

#285 anuncio

#284 Omni-Rewriter now expands prompts into the public LTX-2.5 paragraph dialect

#283 Bug - Train/inference parity: three divergences between ltx-trainer and ltx-core / ltx-pipelines

#282 Feature request — LTX‑2.3 local inference on Intel Macs with AMD GPUs

#214 which text_encoder ？

#232 Per-component offload: streaming text encoder while transformers stay GPU-resident (warm-serving OOM at 96 GB)

#281 Before iran had a name

#278 Recommendations on GGUF's versatility and using Qwen.

#277 [LTX-2.5] DiffVAE AUTO tiling produces gray tails at the 2^32 stage-5 element boundary

#275 Confirm: LTX-2.5 video/audio VAE *encoders* are byte-identical to LTX-2.3 (undocumented)

#274 temp: README demo video upload

#270 [ltx-core] Prompt enhancement returns a repetition loop: inputs are right-padded before `generate()` on a decoder-only model

#271 FileExistsError on Windows at end of training when optimization.steps is a multiple of checkpoints.interval

#269 [ltx-pipelines] `--enhance-prompt` is accepted and silently dropped by `ti2vid_two_stages`

#268 LTX2

#267 LTX2

#261 PEL

#223 Artifacts in high-frequency regions when generating videos

#200 Request: publish bundled ltx-av-step-1751000_vocoder_24K checkpoint (or equivalent audio-to-video bundle)

#252 What command line options I need to setup to work with nvfp4 model?

#259 DMD training

#257 LTX Desktop for Linux