upstream-archive/stable-diffusion.cpp
1
0
Fork 0
mirror of https://github.com/leejet/stable-diffusion.cpp.git synced 2026-07-23 11:20:53 -05:00
Code Issues Packages Projects Releases Wiki Activity

feat: add ltx2.3 support (#1463)

Browse Source 
* add GemmaTokenizer

* add basic ltx2.3 support

* change vocab file encoding

* fix ci

* fix ubuntu build

* add temporal tiling support

* add ltx audio support

* update ggml submodule url

* fix generate_video

* add i2v support

* minify bundled Gemma tokenizer vocab sources

* pass video fps into temporal rope embeddings

* fix av_ca_timestep_scale_multiplier

* add LTX2Scheduler support

* update docs

* fix ci
This commit is contained in:
leejet
2026-05-17 16:46:20 +08:00
committed by GitHub
parent 3b4d26f3d9
commit 67dda3f897
44 changed files with 6393 additions and 240 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
examples/cli/README.md
View File

@@ -103,8 +103,9 @@ Generation Options:
--hires-upscaler <string> highres fix upscaler, Lanczos, Nearest, Latent, Latent (nearest), Latent
(nearest-exact), Latent (antialiased), Latent (bicubic), Latent (bicubic
antialiased), or a model name under --hires-upscalers-dir (default: Latent)
--extra-sample-args <string> extra sampler args, key=value list. Currently lcm supports noise_clip_std,
noise_scale_start, noise_scale_end
--extra-sample-args <string> extra sampler/scheduler args, key=value list. lcm supports noise_clip_std,
noise_scale_start, noise_scale_end; ltx2 supports max_shift, base_shift,
stretch, terminal
-H, --height <int> image height, in pixel space (default: 512)
-W, --width <int> image width, in pixel space (default: 512)
--steps <int> number of sample steps (default: 20)
@@ -160,6 +161,7 @@ Generation Options:
--disable-auto-resize-ref-image disable auto resize of ref images
--disable-image-metadata do not embed generation metadata on image files
--vae-tiling process vae in tiles to reduce memory usage
--temporal-tiling enable temporal tiling for LTX video VAE decode
--hires enable highres fix
-s, --seed RNG seed (default: 42, use random seed for < 0)
--sampling-method sampling method, one of [euler, euler_a, heun, dpm2, dpm++2s_a, dpm++2m,
@@ -169,8 +171,8 @@ Generation Options:
dpm++2m, dpm++2mv2, ipndm, ipndm_v, lcm, ddim_trailing, tcd, res_multistep,
res_2s, er_sde, euler_cfg_pp, euler_a_cfg_pp] default: euler for Flux/SD3/Wan, euler_a otherwise
--scheduler denoiser sigma scheduler, one of [discrete, karras, exponential, ays, gits,
smoothstep, sgm_uniform, simple, kl_optimal, lcm, bong_tangent], default:
discrete
smoothstep, sgm_uniform, simple, kl_optimal, lcm, bong_tangent, ltx2], default:
model-specific
--sigmas custom sigma values for the sampler, comma-separated (e.g.,
"14.61,7.8,3.5,0.0").
--skip-layers layers to skip for SLG steps (default: [7,8,9])