theluyuan/DiffSynth-Studio
1
0
Fork 0
mirror of https://github.com/modelscope/DiffSynth-Studio.git synced 2026-03-18 22:08:13 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix flux-eligen bug

Browse Source
This commit is contained in:
mi804
2025-08-06 20:07:21 +08:00
parent d0b9b25db7
commit 970403f78e
3 changed files with 3 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
diffsynth/models/flux_dit.py
View File

@@ -375,8 +375,7 @@ class FluxDiT(torch.nn.Module):
return attention_mask
def process_entity_masks(self, hidden_states, prompt_emb, entity_prompt_emb, entity_masks, text_ids, image_ids):
repeat_dim = hidden_states.shape[1]
def process_entity_masks(self, hidden_states, prompt_emb, entity_prompt_emb, entity_masks, text_ids, image_ids, repeat_dim):
max_masks = 0
attention_mask = None
prompt_embs = [prompt_emb]

2
diffsynth/pipelines/flux_image.py
View File

@@ -762,7 +762,7 @@ def lets_dance_flux(
hidden_states = dit.x_embedder(hidden_states)
if entity_prompt_emb is not None and entity_masks is not None:
prompt_emb, image_rotary_emb, attention_mask = dit.process_entity_masks(hidden_states, prompt_emb, entity_prompt_emb, entity_masks, text_ids, image_ids)
prompt_emb, image_rotary_emb, attention_mask = dit.process_entity_masks(hidden_states, prompt_emb, entity_prompt_emb, entity_masks, text_ids, image_ids, 16)
else:
prompt_emb = dit.context_embedder(prompt_emb)
image_rotary_emb = dit.pos_embedder(torch.cat((text_ids, image_ids), dim=1))

2
diffsynth/pipelines/flux_image_new.py
View File

@@ -1233,7 +1233,7 @@ def model_fn_flux_image(
# EliGen
if entity_prompt_emb is not None and entity_masks is not None:
prompt_emb, image_rotary_emb, attention_mask = dit.process_entity_masks(hidden_states, prompt_emb, entity_prompt_emb, entity_masks, text_ids, image_ids)
prompt_emb, image_rotary_emb, attention_mask = dit.process_entity_masks(hidden_states, prompt_emb, entity_prompt_emb, entity_masks, text_ids, image_ids, latents.shape[1])
else:
prompt_emb = dit.context_embedder(prompt_emb)
image_rotary_emb = dit.pos_embedder(torch.cat((text_ids, image_ids), dim=1))