Skip to content

make Wan2.2 5B FLF2V work #1110

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
leejet wants to merge 3 commits into
base: master
Choose a base branch
from
+11 −0
Open

make Wan2.2 5B FLF2V work #1110

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
60c0001
make Wan2.2 5B FLF2V work
leejet Dec 17, 2025
d745078
Merge branch 'master' into wan2.2_5B_flf2v
leejet Mar 4, 2026
6e5fa00
Merge branch 'master' into wan2.2_5B_flf2v
leejet Mar 29, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 11 additions & 0 deletions src/stable-diffusion.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3275,6 +3275,17 @@ static std::optional<ImageGenerationLatents> prepare_video_generation_latents(sd
latents.denoise_mask = sd::full<float>({latents.init_latent.shape()[0], latents.init_latent.shape()[1], latents.init_latent.shape()[2], 1, 1}, 1.f);
sd::ops::fill_slice(&latents.denoise_mask, 2, 0, init_image_latent.shape()[2], 0.0f);

if (!end_image.empty()) {
auto end_img = end_image.reshape({end_image.shape()[0], end_image.shape()[1], 1, end_image.shape()[2], 1});
auto end_image_latent = sd_ctx->sd->encode_first_stage(end_img); // [b, c, 1, h/vae_scale_factor, w/vae_scale_factor]
if (end_image_latent.empty()) {
LOG_ERROR("failed to encode end video frame");
return std::nullopt;
}
sd::ops::slice_assign(&latents.init_latent, 2, latents.init_latent.shape()[2] - 1, latents.init_latent.shape()[2], end_image_latent);
sd::ops::fill_slice(&latents.denoise_mask, 2, latents.init_latent.shape()[2] - 1, latents.init_latent.shape()[2], 0.0f);
}

int64_t t2 = ggml_time_ms();
LOG_INFO("encode_first_stage completed, taking %" PRId64 " ms", t2 - t1);
} else if (sd_ctx->sd->diffusion_model->get_desc() == "Wan2.1-VACE-1.3B" ||
Expand Down
Loading