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 LTX spatial latent upscale hires support (#1533)

Browse Source
This commit is contained in:
leejet
2026-05-20 22:27:09 +08:00
committed by GitHub
parent bdd937f29a
commit b3374e6a71
12 changed files with 1073 additions and 137 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
docs/ltx2.md
View File

@@ -13,6 +13,8 @@
- safetensors: https://huggingface.co/unsloth/LTX-2.3-GGUF/tree/main/vae
- Download audio vae
- safetensors: https://huggingface.co/unsloth/LTX-2.3-GGUF/tree/main/vae
- Download LTX spatial latent upscaler
- safetensors: https://huggingface.co/Lightricks/LTX-2.3/resolve/main/ltx-2.3-spatial-upscaler-x2-1.1.safetensors
## Examples
@@ -50,4 +52,26 @@
src="../assets/ltx2/flf2v.webm"
controls
muted
style="max-width: 100%; height: auto;"></video>
### LTX-2.3 spatial latent upscale
LTX spatial latent upscale runs a model-backed x2 latent upsampler between the low-resolution video pass and the high-resolution refine pass. `-W` and `-H` are the pre-upscale generation size; the spatial upsampler produces x2 latent dimensions.
Put `ltx-2.3-spatial-upscaler-x2-1.1.safetensors` under the directory passed to `--hires-upscalers-dir`, then use the model name without path or extension in `--hires-upscaler`.
```
.\bin\Release\sd-cli.exe -M vid_gen --diffusion-model ..\..\ComfyUI\models\diffusion_models\ltx-2.3-22b-dev-UD-Q4_K_M.gguf --vae ..\..\ComfyUI\models\vae\ltx-2.3-22b-dev_video_vae.safetensors --audio-vae ..\..\ComfyUI\models\vae\ltx-2.3-22b-dev_audio_vae.safetensors --llm ..\..\ComfyUI\models\text_encoders\gemma-3-12b-it-qat-UD-Q4_K_XL.gguf --embeddings-connectors ..\..\ComfyUI\models\text_encoders\ltx-2.3-22b-dev_embeddings_connectors.safetensors --hires-upscalers-dir ..\..\ComfyUI\models\latent_upscale_models --hires-upscaler ltx-2.3-spatial-upscaler-x2-1.1 --hires --hires-steps 4 -p "a lovely cat" --cfg-scale 6.0 --sampling-method euler -v -W 640 -H 360 --diffusion-fa --offload-to-cpu --video-frames 33 -i ..\assets\ernie_image\turbo_example.png -o hires_i2v.webm
```
By default, the hires refine pass uses the main sampler and scheduler, then trims the second-pass sigma schedule by `--hires-denoising-strength` (`0.7` by default). To reproduce a ComfyUI-style explicit refine schedule, pass custom hires sigmas:
```
--hires-sigmas "0.85,0.725,0.421875,0.0"
```
<video
src="../assets/ltx2/hires_i2v.webm"
controls
muted
style="max-width: 100%; height: auto;"></video>