mirror/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2026-05-30 19:47:47 -04:00
Code Issues Packages Projects Releases Wiki Activity

fix(gallery/ltx-2.3): add vae_decode_only:false for i2v / flf2v

Browse Source 
LTX-2.3 i2v inference fails inside generate_video with:

  [ERROR] LTXAV image conditioning requires VAE encoder weights;
  create the context with vae_decode_only=false

Without vae_decode_only:false in the options block, gosd.cpp creates
the sd_ctx with VAE encoder weights freed, so latent encoding of the
init_image is impossible. Adding the option mirrors what we already
do for Wan i2v entries.

Affects all six LTX-2.3 entries (dev/distilled × UD-Q4_K_M, Q4_K_M,
Q8_0). T2V wasn't impacted by the missing option since it has no
init image to encode, which is why the T2V smoke earlier passed.

Assisted-by: Claude:claude-opus-4-7
This commit is contained in:
Ettore Di Giacinto
2026-05-25 19:33:55 +00:00
parent b3300ef207
commit 11c5fd677d
1 changed files with 6 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
gallery/index.yaml
View File

@@ -30845,6 +30845,7 @@
model: ltx-2.3-22b-dev-UD-Q4_K_M.gguf
options:
- diffusion_model
- "vae_decode_only:false"
- llm_path:gemma-3-12b-it-qat-UD-Q4_K_XL.gguf
- vae_path:ltx-2.3-22b-dev_video_vae.safetensors
- audio_vae_path:ltx-2.3-22b-dev_audio_vae.safetensors
@@ -30877,6 +30878,7 @@
model: ltx-2.3-22b-dev-Q4_K_M.gguf
options:
- diffusion_model
- "vae_decode_only:false"
- llm_path:gemma-3-12b-it-qat-UD-Q4_K_XL.gguf
- vae_path:ltx-2.3-22b-dev_video_vae.safetensors
- audio_vae_path:ltx-2.3-22b-dev_audio_vae.safetensors
@@ -30909,6 +30911,7 @@
model: ltx-2.3-22b-dev-Q8_0.gguf
options:
- diffusion_model
- "vae_decode_only:false"
- llm_path:gemma-3-12b-it-qat-UD-Q4_K_XL.gguf
- vae_path:ltx-2.3-22b-dev_video_vae.safetensors
- audio_vae_path:ltx-2.3-22b-dev_audio_vae.safetensors
@@ -30969,6 +30972,7 @@
model: ltx-2.3-22b-distilled-UD-Q4_K_M.gguf
options:
- diffusion_model
- "vae_decode_only:false"
- llm_path:gemma-3-12b-it-qat-UD-Q4_K_XL.gguf
- vae_path:ltx-2.3-22b-distilled_video_vae.safetensors
- audio_vae_path:ltx-2.3-22b-distilled_audio_vae.safetensors
@@ -31000,6 +31004,7 @@
model: ltx-2.3-22b-distilled-Q4_K_M.gguf
options:
- diffusion_model
- "vae_decode_only:false"
- llm_path:gemma-3-12b-it-qat-UD-Q4_K_XL.gguf
- vae_path:ltx-2.3-22b-distilled_video_vae.safetensors
- audio_vae_path:ltx-2.3-22b-distilled_audio_vae.safetensors
@@ -31031,6 +31036,7 @@
model: ltx-2.3-22b-distilled-Q8_0.gguf
options:
- diffusion_model
- "vae_decode_only:false"
- llm_path:gemma-3-12b-it-qat-UD-Q4_K_XL.gguf
- vae_path:ltx-2.3-22b-distilled_video_vae.safetensors
- audio_vae_path:ltx-2.3-22b-distilled_audio_vae.safetensors