DarthAffe/stable-diffusion.cpp
1
0
Fork 0
mirror of https://github.com/leejet/stable-diffusion.cpp.git synced 2026-08-10 14:16:50 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: avoid crash and warn when using Qwen 2D VAE for Wan video (#1721)

Browse Source
This commit is contained in:
stduhpf 2026-06-29 15:44:05 +02:00 committed by GitHub
parent 0484600284
commit 3ec374aecc
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 16 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
src/model/vae/wan_vae.hpp
View File

@ -1119,6 +1119,10 @@ namespace WAN {
GGML_ASSERT(b == 1); GGML_ASSERT(b == 1);
GGML_ASSERT(decode_only == false); GGML_ASSERT(decode_only == false);
if (x->ne[2] > 1 && is_2D) {
LOG_WARN("Using 2D VAE to encode video, expect poor results");
}
clear_cache(); clear_cache();
if (wan2_2) { if (wan2_2) {
@ -1138,7 +1142,8 @@ namespace WAN {
auto in = ggml_ext_slice(ctx->ggml_ctx, x, 2, 0, 1); // [b*c, 1, h, w] auto in = ggml_ext_slice(ctx->ggml_ctx, x, 2, 0, 1); // [b*c, 1, h, w]
out = encoder->forward(ctx, in, b, _enc_feat_map, _enc_conv_idx, i); out = encoder->forward(ctx, in, b, _enc_feat_map, _enc_conv_idx, i);
} else { } else {
auto in = ggml_ext_slice(ctx->ggml_ctx, x, 2, 1 + 4 * (i - 1), 1 + 4 * i); // [b*c, 4, h, w] // if is_2D, drop 3 out of 4 frames
auto in = ggml_ext_slice(ctx->ggml_ctx, x, 2, 1 + 4 * (i - 1), (is_2D ? 1 - 3 : 1) + 4 * i); // [b*c, 4, h, w]
auto out_ = encoder->forward(ctx, in, b, _enc_feat_map, _enc_conv_idx, i); auto out_ = encoder->forward(ctx, in, b, _enc_feat_map, _enc_conv_idx, i);
out = ggml_concat(ctx->ggml_ctx, out, out_, 2); out = ggml_concat(ctx->ggml_ctx, out, out_, 2);
} }
@ -1161,6 +1166,10 @@ namespace WAN {
// z: [b*c, t, h, w] // z: [b*c, t, h, w]
GGML_ASSERT(b == 1); GGML_ASSERT(b == 1);
if (z->ne[2] > 1 && is_2D) {
LOG_WARN("Using 2D VAE to decode video, expect poor results");
}
clear_cache(); clear_cache();
auto decoder = std::dynamic_pointer_cast<Decoder3d>(blocks["decoder"]); auto decoder = std::dynamic_pointer_cast<Decoder3d>(blocks["decoder"]);
@ -1185,6 +1194,12 @@ namespace WAN {
auto in = ggml_ext_slice(ctx->ggml_ctx, x, 2, i, i + 1); // [b*c, 1, h, w] auto in = ggml_ext_slice(ctx->ggml_ctx, x, 2, i, i + 1); // [b*c, 1, h, w]
auto out_ = decoder->forward(ctx, in, b, _feat_map, _conv_idx, i); auto out_ = decoder->forward(ctx, in, b, _feat_map, _conv_idx, i);
out = ggml_concat(ctx->ggml_ctx, out, out_, 2); out = ggml_concat(ctx->ggml_ctx, out, out_, 2);
if (is_2D) {
// repeat frames to avoid mismatch
for (int j = 0; j < 4 - 1; j++) {
out = ggml_concat(ctx->ggml_ctx, out, out_, 2);
}
}
} }
} }
if (wan2_2) { if (wan2_2) {