theluyuan/DiffSynth-Studio
1
0
Fork 0
mirror of https://github.com/modelscope/DiffSynth-Studio.git synced 2026-03-22 08:40:47 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix long prompt for qwen-image

Browse Source
This commit is contained in:
mi804
2025-08-13 17:23:00 +08:00
parent 34766863f8
commit f7f5c07570
2 changed files with 35 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
diffsynth/pipelines/qwen_image.py
View File

@@ -372,7 +372,9 @@ class QwenImageUnit_PromptEmbedder(PipelineUnit):
template = "<|im_start|>system\nDescribe the image by detailing the color, shape, size, texture, quantity, text, spatial relationships of the objects and background:<|im_end|>\n<|im_start|>user\n{}<|im_end|>\n<|im_start|>assistant\n"
drop_idx = 34
txt = [template.format(e) for e in prompt]
txt_tokens = pipe.tokenizer(txt, max_length=1024+drop_idx, padding=True, truncation=True, return_tensors="pt").to(pipe.device)
txt_tokens = pipe.tokenizer(txt, max_length=4096+drop_idx, padding=True, truncation=True, return_tensors="pt").to(pipe.device)
if txt_tokens.input_ids.shape[1] >= 1024:
print(f"Warning!!! QwenImage model was trained on prompts up to 512 tokens. Current prompt requires {txt_tokens['input_ids'].shape[1] - drop_idx} tokens, which may lead to unpredictable behavior.")
hidden_states = pipe.text_encoder(input_ids=txt_tokens.input_ids, attention_mask=txt_tokens.attention_mask, output_hidden_states=True,)[-1]
split_hidden_states = self.extract_masked_hidden(hidden_states, txt_tokens.attention_mask)