---
license: other
license_name: ltx-2.x-community-license
license_link: https://huggingface.co/Lightricks/LTX-2.5/blob/main/LICENSE
base_model:
- Lightricks/LTX-2.5
- jdopensource/JoyAI-Echo
base_model_relation: merge
tags:
- comfy-native
- comfy-quant
- quantized
- comfyui
- ltx-2
- ltx-2.5
- joyai-echo
- video-generation
- text-to-video
- audio-video
- lip-sync
- merge
pipeline_tag: text-to-video
---
# JoyAI-Echo x LTX-2.5 (echoVid) - comfy-native (int8 / w4a8 / w4a4 / nvfp4 / mixed)
**Try it in the browser:** [ZeroGPU demo Space](https://huggingface.co/spaces/joeygambino/joyai-echo-ltx25-echovid-comfy-native) - these exact files, the two-pass ladder, no install.
**LTX-2.5's engine with JoyAI-Echo's performance.** LTX-2.5 renders picture and sound in
one pass, at any length, in one generation. JoyAI-Echo (a fine-tune of LTX-2.3) has the
better *actor*: natural lip-sync, expressive faces, a voice that stays put. The two
transformers are shape-identical, so JoyAI-Echo's video attention/feed-forward delta was
transplanted onto the official **LTX-2.5 dev** transformer, and the official LTX-2.5 distilled LoRA (`ltx-2.5-22b-distilled-lora-450`) is baked in at 0.5 - so these are few-step files with the same speed, VRAM and nodes as LTX-2.5 distilled. Nothing was retrained. (**v2**: the first build put the delta on the distilled transformer and came out over-saturated with hard contrast; those files are gone. The plain dev merges, for people who want to apply their own distill LoRA at their own strength, are here: https://huggingface.co/joeygambino/joyai-echo-ltx25-echoVid-dev.)
What you get over stock LTX-2.5 distilled is the acting JoyAI-Echo was trained for - lip-sync,
expression, a voice that stays put - at the same speed, VRAM and nodes.
> **Workflow + nodes:** https://github.com/jlucasmcrell/ComfyUI-JoyLTX25 (the *Joy-LTX 2.5*
> canvases: one-prompt take with a VRAM planner, and multishot with AV-extend joins; the release zip bundles the writer).
> **GGUF files (Q3_K_M .. Q8_0):**
> https://huggingface.co/joeygambino/joyai-echo-ltx25-echoVid-gguf
> **All models:** https://huggingface.co/joeygambino
> **Try it live:** https://huggingface.co/spaces/joeygambino/joy-ltx-25 (one take, ZeroGPU)
> **Civitai:** *Joy-LTX 2.5* (models being uploaded now).
## What it looks like
Rendered with the files on this page (070T30, distilled LoRA baked at 0.5), the [ComfyUI-JoyLTX25](https://github.com/jlucasmcrell/ComfyUI-JoyLTX25) canvases, 8 steps at cfg 1. Sound is generated with the picture, in the same pass - turn it on.
**Three shots joined into one take**
Multishot, 3 x 8 s at 1280x736, AV-extend joins - the speech and the room carry across both joins with no reference photo attached.
**Beach, hard sun**
10 s, single generation, picture and sound together.
**Wet neon street**
10 s, single generation. Reflections and rain with a voice over them.
**Snow, flat overcast**
10 s, single generation. The grade holds in high key - the failure mode of the first build.
## Two doses
| dose | what it is | pick it when |
|---|---|---|
| **070T30** *(default)* | 0.7 x Echo delta on video attention/FF, 0.3 x on the modulation tables, distill LoRA 0.5 | the default - cleaner skin, natural grade |
| **100T50** *(strong)* | 1.0 x / 0.5 x, distill LoRA 0.5 | loud, comic, animated performances - the livelier read, a touch hotter on contrast |
Both were reviewed blind on 20+ paired renders: scores tie; 070T30 reads a touch less
rubbery on still faces, 100T50 lands laughter and big expressions better. Start with 070T30.
## Which file (stock ComfyUI 0.32+, no custom loader - the fast family on RTX 50)
These use ComfyUI's own quantisation (`comfy_quant` + comfy-kitchen kernels), the same
machinery as Lightricks' official `int8-convrot` build. Load them with the plain **Load
Diffusion Model** node. Sizes are decimal GB. Timings: 960x544, 8 s, two-pass x2 to 1920x1088.
| file | GB | fits | RTX 5090 | RTX 3090 |
|---|---|---|---|---|
| `LTX25dist-echoVid--v2-DiT-comfy-w4a4.safetensors` | 11.2 | 12 GB (tight) / 16 GB | 87 s | 3121 s (avoid on Ampere) |
| `LTX25dist-echoVid--v2-DiT-comfy-w4a8.safetensors` | 12.5 | 16 GB | ~90 s | ~580 s |
| `LTX25dist-echoVid--v2-DiT-comfy-nvfp4.safetensors` | 12.5 | 16 GB (RTX 50 only) | ~100 s | n/a |
| `LTX25dist-echoVid--v2-DiT-comfy-mix4x8-13.8GB.safetensors` | 13.8 | 16 GB | 110 s | 1685 s |
| `LTX25dist-echoVid--v2-DiT-comfy-mix4x8-17.0GB.safetensors` | 17.0 | 24 GB | 111 s | 3093 s (offloads) |
| `LTX25dist-echoVid--v2-DiT-comfy-int8.safetensors` | 21.5 | 32 GB (24 GB tight) | 120 s **(32 GB default)** | - |
Rule of thumb: **RTX 50 -> this repo. RTX 30/40 -> the GGUF repo** (Q5_K_M / Q6_K are 4-8x
faster there than any 4-bit comfy-native arm). `--enable-triton-backend` on the ComfyUI
launch line roughly halves w4a8/int8 step time where triton is installed.
## fp8 and the bf16 master
Two more cuts, straight from the v2 master (same bake: dev + Echo delta + distill LoRA 0.5):
| file | GB | note |
|---|---|---|
| `LTX25dist-echoVid--v2-DiT-comfy-fp8.safetensors` | 21.5 | comfy fp8_e4m3fn scaled; stock **Load Diffusion Model** |
| `LTX25dist-echoVid--v2-DiT-bf16.safetensors` | 42.0 | the master; needs a card that streams 42 GB (or offload); the file to quantise from |
## Install (ComfyUI)
1. ComfyUI 0.32 or newer (the comfy-kitchen kernels ship with it).
2. Put the `.safetensors` in `models/diffusion_models/`.
3. From [Lightricks/LTX-2.5](https://huggingface.co/Lightricks/LTX-2.5): `vae/ltx-2.5-video-vae-bf16.safetensors`
and `vae/ltx-2.5-audio-vae-bf16.safetensors` -> `models/vae/`;
`latent_upscale_models/ltx-2.5-latent-spatial-upscaler-x2-bf16-1.0.safetensors` -> `models/latent_upscale_models/`;
text encoder `text_encoders/gemma4-12b-with-proj-ltx-2.5-comfy-int8-convrot.safetensors` -> `models/text_encoders/`
(16 GB cards: the 10.6 GB `gemma4-12b-ltx25-comfy-w4a8.safetensors` from
[LTX-2.5-Quantized](https://huggingface.co/joeygambino/LTX-2.5-Quantized)).
4. Load the workflow from the node pack above (or any LTX-2.5 workflow: pick this file in the
stock **Load Diffusion Model** loader). Distilled schedule: 8 steps pass 1, 3 steps pass 2,
`euler_ancestral`, CFG 1.
## Credits
JoyAI-Echo by JD ([jdopensource/JoyAI-Echo](https://huggingface.co/jdopensource/JoyAI-Echo));
LTX-2.5 by Lightricks. Merge, quantisation and workflows by joeygambino. Licensed under the
LTX-2.x Community License (inherited from both parents).