You need to agree to share your Hugging Face information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

This is a modified copy of LTX-2.5 (Lightricks/LTX-2.5-Diffusers), distributed under the LTX-2.x Community License Agreement (LICENSE in this repository). Its use is subject to that agreement, including Section 4 and Attachment A (use restrictions), in their entirety. Entities with annual revenues of at least US$10,000,000 must obtain a paid license from Lightricks (licensing@ltx.io) before any use other than a Non-Commercial Purpose.

LTX-2.5 distilled, FP8 — radiance container

LTX-2.5 — video with a synchronized stereo soundtrack from text, or from text and a first frame — as a single .rad container for the radiance inference engine (AMD RDNA4, ROCm).

This is not an official Lightricks release and is not endorsed by Lightricks.


File	`ltx-2.5-distilled-fp8.rad` — 36.73 GiB
Weights	the Gemma 4 text encoder's, the text connectors' and the diffusion transformer's linears FP8 E4M3 per 128×128 block (bf16 scales); the vocoders f32; everything else (the video and audio VAEs, the latent upsampler, the duration head, the diffusion decoder, the small linears and norms) as released, bf16
Steps	8, the distilled release's trained sigmas, unguided (a request may not name another count)
Needs	radiance built from main after 1.8.1 — LTX-2.5 support is not in 1.8.1 and comes with the next release

Serve

radiance --model ltx-2.5-distilled-fp8.rad --vision-tower-placement ram

LTX-2.5 runs on one card (--tp above 1 is refused). The text encoder (13 GiB in FP8) does not fit a 32 GB card beside the DiT: --vision-tower-placement ram keeps it in pinned host memory, read once a prompt.

The server speaks OpenAI's video API: POST /v1/videos queues a job (JSON, or multipart as OpenAI's SDKs send it), GET /v1/videos/{id} reports its progress and GET /v1/videos/{id}/content downloads the MP4 (H.264 and 48 kHz stereo AAC).

curl -s http://localhost:8000/v1/videos -H 'Content-Type: application/json' -d '{
  "prompt": "A red fox trots through fresh snow at golden hour, snow crunching under its paws",
  "size": "960x544", "seed": 7}'

seconds: rounded up to steps of 8 frames at 24 a second, 17 to 161 frames. Left out (or "auto"), the release's duration head chooses the length the prompt implies, as diffusers does when num_frames is omitted.
size: sides multiples of 32 from 256, at most 1920x1088 of area (121 frames at that size), at most 3:1; 960x544 by default. A frame larger than 960x544 is decoded in diffusers' VAE tiles.
input_reference: a first frame (image to video), resized to size and put through H.264 at CRF 18 first, as the release was trained.
decoder: "vae" (the default) or "diffusion", the release's diffusion decoder: neighbourhood-attention stages that upsample the latent, then one diffusion step over pixel patches, a tile at a time with diffusers' tiling. Frames up to 960x544 of area (a larger size is refused with it). Its weights stay in host memory with --vision-tower-placement ram.
Two-stage: latent_upscale 2 (sides multiples of 64) runs the 8 steps at half the size, enlarges the clean latent with the release's latent upsampler, re-noises it and refines at the full size in 3 more steps.

On one Radeon AI PRO R9700 (gfx1201): 5 seconds (121 frames) at 960x544 in about 20 s; the README's two-stage recipe, "size": "1920x1088", "latent_upscale": 2, 121 frames in about 70 s (18 s of steps at 960x544, 44 s of three refinement steps at full size, 7 s of tiled decode). With "decoder": "diffusion", 5 seconds at 960x544 decode in about 24 s instead of 2.

The model was trained on long, single-paragraph captions describing the shot, the motion, the light and the sound; short prompts give generic results.

How this file was made

rad-convert Lightricks/LTX-2.5-Diffusers --recipe ltx-2.5-fp8.recipe -o ltx-2.5-distilled-fp8.rad

Lightricks/LTX-2.5-Diffusers is the diffusers download of that repository; its transformer/ is the distilled DiT. transformer_full/ (the full model, its own container) is not read.

The recipe (ltx-2.5-fp8.recipe in this repository) names what is quantised or cast; everything it does not name is the checkpoint's own dtype:

te.blk.*.attn_q.weight               rtn  codes=fp8_e4m3 block=128x128 scale=bf16
te.blk.*.attn_k.weight               rtn  codes=fp8_e4m3 block=128x128 scale=bf16
te.blk.*.attn_v.weight               rtn  codes=fp8_e4m3 block=128x128 scale=bf16
te.blk.*.attn_output.weight          rtn  codes=fp8_e4m3 block=128x128 scale=bf16
te.blk.*.ffn_gate_up.weight          rtn  codes=fp8_e4m3 block=128x128 scale=bf16
te.blk.*.ffn_down.weight             rtn  codes=fp8_e4m3 block=128x128 scale=bf16
conn.*.proj.weight                   rtn  codes=fp8_e4m3 block=128x128 scale=bf16
conn.*.blk.*.qkv.weight              rtn  codes=fp8_e4m3 block=128x128 scale=bf16
conn.*.blk.*.out.weight              rtn  codes=fp8_e4m3 block=128x128 scale=bf16
conn.*.blk.*.ff_up.weight            rtn  codes=fp8_e4m3 block=128x128 scale=bf16
conn.*.blk.*.ff_down.weight          rtn  codes=fp8_e4m3 block=128x128 scale=bf16
dit.blk.*.qkv.weight                 rtn  codes=fp8_e4m3 block=128x128 scale=bf16
dit.blk.*.q.weight                   rtn  codes=fp8_e4m3 block=128x128 scale=bf16
dit.blk.*.kv.weight                  rtn  codes=fp8_e4m3 block=128x128 scale=bf16
dit.blk.*.out.weight                 rtn  codes=fp8_e4m3 block=128x128 scale=bf16
dit.blk.*.ff_up.weight               rtn  codes=fp8_e4m3 block=128x128 scale=bf16
dit.blk.*.ff_down.weight             rtn  codes=fp8_e4m3 block=128x128 scale=bf16
dit.blk.*.audio_ff_up.weight         rtn  codes=fp8_e4m3 block=128x128 scale=bf16
dit.blk.*.audio_ff_down.weight       rtn  codes=fp8_e4m3 block=128x128 scale=bf16
voc.conv_*                           cast dtype=f32
voc.upsamplers.*                     cast dtype=f32
voc.resnets.*                        cast dtype=f32
voc.act_out.*                        cast dtype=f32
bwe.*                                cast dtype=f32

License

LTX-2.5 is licensed under the LTX-2.x Community License Agreement (LICENSE), and its use is subject to that agreement in its entirety, including the use restrictions of Section 4 and Attachment A. Entities with annual revenues of at least US$10,000,000 must obtain a paid license from Lightricks before any use other than a Non-Commercial Purpose. This container is a modified copy (NOTICE says how); no rights beyond the agreement's are granted with it.

Downloads last month: -; Downloads are not tracked for this model. How to track

Model tree for StillDeadcode/radiance-ltx-2.5-distilled-fp8

Base model

Lightricks/LTX-2.5-Diffusers

Finetuned

(3)

this model