Skip to content

Fix Flux2 non-diffusers guidance LoRA conversion #13486

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
sayakpaul merged 5 commits into from
Apr 18, 2026
Merged

Fix Flux2 non-diffusers guidance LoRA conversion #13486

Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
7a1a7ce
Fix Flux2 LoRA guidance conversion
yadferhad Apr 15, 2026
533ba59
Handle expanded Flux2 LoRA block names
yadferhad Apr 16, 2026
d1d7f7c
Address Flux2 PR review feedback
yadferhad Apr 17, 2026
63d8679
Merge branch 'main' into oss/13484-lora-loading-on-text-pipe-for-modu…
yadferhad Apr 17, 2026
ffa00dd
Merge branch 'main' into oss/13484-lora-loading-on-text-pipe-for-modu…
sayakpaul Apr 18, 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
16 changes: 16 additions & 0 deletions src/diffusers/loaders/lora_conversion_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2331,6 +2331,20 @@ def _convert_non_diffusers_flux2_lora_to_diffusers(state_dict):
temp_state_dict[new_key] = v
original_state_dict = temp_state_dict

# Some Flux2 checkpoints skip the ai-toolkit `single_blocks` / `double_blocks`
# layout and already store expanded diffusers block names. Accept those
# directly, and normalize the legacy `sformer_blocks` alias used by some exports.
possible_expanded_block_prefixes = {
"single_transformer_blocks.": "single_transformer_blocks.",
"transformer_blocks.": "transformer_blocks.",
"sformer_blocks.": "transformer_blocks.",
}
for key in list(original_state_dict.keys()):
for source_prefix, target_prefix in possible_expanded_block_prefixes.items():
if key.startswith(source_prefix):
converted_state_dict[target_prefix + key[len(source_prefix) :]] = original_state_dict.pop(key)
break

num_double_layers = 0
num_single_layers = 0
for key in original_state_dict.keys():
Expand Down Expand Up @@ -2421,6 +2435,8 @@ def _convert_non_diffusers_flux2_lora_to_diffusers(state_dict):
"txt_in": "context_embedder",
"time_in.in_layer": "time_guidance_embed.timestep_embedder.linear_1",
"time_in.out_layer": "time_guidance_embed.timestep_embedder.linear_2",
"guidance_in.in_layer": "time_guidance_embed.guidance_embedder.linear_1",
"guidance_in.out_layer": "time_guidance_embed.guidance_embedder.linear_2",
"final_layer.linear": "proj_out",
"final_layer.adaLN_modulation.1": "norm_out.linear",
"single_stream_modulation.lin": "single_stream_modulation.linear",
Expand Down
Loading