Skip to content

Update flash attention warnings #805

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

Merged
merged 2 commits into from
Sep 10, 2025
Merged

Update flash attention warnings #805

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
118863a
chore: add warning about Chroma and Flash Attention
wbruna Sep 8, 2025
2fd34c6
chore: tweak warning about SD3 and Flash Attention
wbruna Sep 8, 2025
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: 10 additions & 1 deletion stable-diffusion.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -345,7 +345,7 @@ class StableDiffusionGGML {
}
if (sd_version_is_sd3(version)) {
if (sd_ctx_params->diffusion_flash_attn) {
LOG_WARN("flash attention in this diffusion model is currently unsupported!");
LOG_WARN("flash attention in this diffusion model is currently not implemented!");
}
cond_stage_model = std::make_shared<SD3CLIPEmbedder>(clip_backend,
offload_params_to_cpu,
Expand All @@ -362,6 +362,15 @@ class StableDiffusionGGML {
}
}
if (is_chroma) {
if (sd_ctx_params->diffusion_flash_attn && sd_ctx_params->chroma_use_dit_mask) {
LOG_WARN(
"!!!It looks like you are using Chroma with flash attention. "
"This is currently unsupported. "
"If you find that the generated images are broken, "
"try either disabling flash attention or specifying "
"--chroma-disable-dit-mask as a workaround.");
}

cond_stage_model = std::make_shared<T5CLIPEmbedder>(clip_backend,
offload_params_to_cpu,
model_loader.tensor_storages_types,
Expand Down
Loading