BoxDiff icon indicating copy to clipboard operation
BoxDiff copied to clipboard

[ICCV 2023] BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion

Results 7 BoxDiff issues
Sort by recently updated
recently updated
newest added

will you add it on the sdxl model?

Feel free to check out https://github.com/huggingface/diffusers/tree/main/examples/community#stable-diffusion-boxdiff Example use case: ```python import torch from PIL import Image, ImageDraw from copy import deepcopy from examples.community.pipeline_stable_diffusion_boxdiff import StableDiffusionBoxDiffPipeline def draw_box_with_text(img, boxes, names): colors...

ptp_utils.py imports CrossAttention from diffusers/models/cross_attention.py: ```from diffusers.models.cross_attention import CrossAttention``` But as of July 26 2023, cross_attention.py is deprecated; attention_processor.py should be used instead: https://github.com/huggingface/diffusers/pull/4299

Hi. In the paper you're mentioning that BoxDiff can work as a plug and play with GLIGEN. But I want to ask if you can provide more details. Don't the...

what's the meaning of token index?

![image](https://github.com/user-attachments/assets/404cad97-47ac-4acc-9caa-8fe6783f2006) Hi, when I use BoxDiff, an error about grad appears at _update_latent function: "RuntimeError: One of the differentiated Tensors appears to not have been used in the graph. Set...

Hello, first of all, thank you very much for your excellent work! Secondly, where can I access the dataset you used for testing? Thank you!