--- title: LTX-2.5 Text Encoder 4bit 8GB emoji: 🎬 colorFrom: indigo colorTo: purple sdk: gradio sdk_version: 5.49.1 app_file: app.py pinned: false license: other short_description: t2v, i2v and v2v on an 8.46 GB 4-bit LTX-2.5 encoder models: - topabaem/LTX-2.5-Text-Encoder-4bit-8GB - Lightricks/LTX-2.5 --- # LTX-2.5 with a 4-bit text encoder Text-to-video, image-to-video and video-to-video driven by [`topabaem/LTX-2.5-Text-Encoder-4bit-8GB`](https://huggingface.co/topabaem/LTX-2.5-Text-Encoder-4bit-8GB) — the Gemma4-12B text encoder compressed from 26.264 GB to 8.46 GB with no compute-capability floor, paired with the distilled 22B DiT as `Q3_K_M` GGUF. Video and audio are generated together; the clips carry their own soundtrack. ## What is actually being demonstrated This Space exercises the packed encoder in a complete LTX-2.5 pipeline. The serving stack also includes pinned ComfyUI and LTX VAE revisions, a third-party `Q3_K_M` DiT, custom audio-video guide handling, adaptive scheduling and an optional refinement pass. A generated clip is therefore an end-to-end smoke test, not an isolated proof of encoder quality. Live prompts use the `gemma4-raw-intermediate-slots-v1` conditioning contract: an explicit BOS token, a 1024-token left-padded Gemma forward, extraction of the valid-token suffix, and the raw intermediate hidden-state slots returned by the model (whose final slot is already final-normalized). The static sample pairs were generated before this correction. They remain historical comparisons of two checkpoints under the same older preprocessing, but they do not validate the corrected live path; a corrected BF16 oracle comparison is not yet published. Image- and video-to-video need one thing ComfyUI does not ship: `LTXVAddGuide` cannot take a combined audio-video latent, because it calls `torch.cat` on a `NestedTensor`. The model, sampler and mask plumbing all support it already, so `ltx_av_guide.py` unwraps the pair, runs the stock node on the video half and re-wraps. The guide maths stays the vendor's.