zlei6/OpenMontage
1
0
Fork 0
mirror of https://github.com/calesthio/OpenMontage.git synced 2026-08-05 15:20:40 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix(comfyui): use WAN 2.1 VAE in bundled 14B T2V workflow

Browse Source 
The bundled wan22-t2v-4step.json workflow loads the 14B FP8 diffusion
pair (wan2.2_t2v_high/low_noise_14B_fp8_scaled.safetensors), which
produce 16-channel latents, but its VAELoader referenced
wan2.2_vae.safetensors — the WAN 2.2 5B model's VAE, which expects
48-channel latents. Every T2V run therefore failed at VAEDecode with:

  Expected tensor to have size 48 at dimension 1, but got size 16

Switch the workflow to wan_2.1_vae.safetensors, matching the 14B
models and the sibling wan22-i2v-4step.json, and update the T2V
required-models list in tools/video/comfyui_video.py to match so
preflight checks for the VAE that is actually used.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Mandaar
2026-07-05 13:59:27 +05:30
parent e09afaa280
commit 37e4ef7831
2 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tools/_comfyui/workflows/wan22-t2v-4step.json
View File

@@ -24,7 +24,7 @@
"4": {
"class_type": "VAELoader",
"inputs": {
"vae_name": "wan2.2_vae.safetensors"
"vae_name": "wan_2.1_vae.safetensors"
}
},
"5": {

2
tools/video/comfyui_video.py
View File

@@ -57,7 +57,7 @@ _REQUIRED_MODELS_T2V = [
*_REQUIRED_MODELS_COMMON,
"wan2.2_t2v_high_noise_14B_fp8_scaled.safetensors",
"wan2.2_t2v_low_noise_14B_fp8_scaled.safetensors",
"wan2.2_vae.safetensors",
"wan_2.1_vae.safetensors",
"wan2.2_t2v_lightx2v_4steps_lora_v1.1_high_noise.safetensors",
"wan2.2_t2v_lightx2v_4steps_lora_v1.1_low_noise.safetensors",
]