wangbo/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2026-06-10 16:27:33 +08:00
Code Issues Actions 27 Packages Projects Releases Wiki Activity

Merge branch 'master' into alexis/save_audio_advanced
Some checks failed
Python Linting / Run Ruff (push) Has been cancelled
Details
Python Linting / Run Pylint (push) Has been cancelled
Details
Build package / Build Test (3.10) (push) Has been cancelled
Details
Build package / Build Test (3.11) (push) Has been cancelled
Details
Build package / Build Test (3.12) (push) Has been cancelled
Details
Build package / Build Test (3.13) (push) Has been cancelled
Details
Build package / Build Test (3.14) (push) Has been cancelled
Details

Browse Source
This commit is contained in:
Alexis Rolland 2026-06-04 19:27:05 -07:00 committed by GitHub
commit 19ff4629a9
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
comfy/ldm/ideogram4/model.py
View File

@ -174,7 +174,7 @@ class Ideogram4Transformer(nn.Module):
llm = self.llm_cond_proj(llm) * text_mask
h[:, :L_text] = h[:, :L_text] + llm
h = h + self.embed_image_indicator((indicator == OUTPUT_IMAGE_INDICATOR).to(torch.long))
h = h + self.embed_image_indicator((indicator == OUTPUT_IMAGE_INDICATOR).to(torch.long), out_dtype=h.dtype)
# Qwen3-VL interleaved MRoPE; position_ids (B, L, 3) -> (3, L) (same across batch).
freqs_cis = precompute_freqs_cis(
@ -235,7 +235,7 @@ class Ideogram4Transformer2DModel(Ideogram4Transformer):
def _run_conditional(self, x_chunk, context_chunk, attn_mask_chunk, t_chunk, gh, gw, transformer_options):
B = x_chunk.shape[0]
device = x_chunk.device
img_tokens = self._img_to_tokens(x_chunk).to(self.dtype)
img_tokens = self._img_to_tokens(x_chunk)
L_img = img_tokens.shape[1]
L_text = context_chunk.shape[1]
L = L_text + L_img
@ -268,7 +268,7 @@ class Ideogram4Transformer2DModel(Ideogram4Transformer):
def _run_image_only(self, x_chunk, t_chunk, gh, gw, transformer_options):
B = x_chunk.shape[0]
device = x_chunk.device
img_tokens = self._img_to_tokens(x_chunk).to(self.dtype)
img_tokens = self._img_to_tokens(x_chunk)
L_img = img_tokens.shape[1]
position_ids = self._image_position_ids(gh, gw, device).unsqueeze(0).expand(B, L_img, 3)