RealCompo
RealCompo copied to clipboard
[NeurIPS 2024] RealCompo: Balancing Realism and Compositionality Improves Text-to-Image Diffusion Models
Hello, I'm interested in your perfect work. And I evaluated your method on the T2I-Compbench. The results are far from what you showed in the paper. I wonder if something...
Traceback (most recent call last): File "inference.py", line 334, in run(meta, args, starting_noise) File "inference.py", line 275, in run samples_fake = sampler.sample(S=steps, shape=shape, input=input, uc=uc, guidance_scale=config.guidance_scale, mask=inpainting_mask, x0=z0) File "/root/miniconda3/envs/RealCompo/lib/python3.8/site-packages/torch/utils/_contextlib.py",...
a -> an
Is api_key necessary in option 1?
Excuse me, how much video memory does this project require? I'm trying to reproduce it using a 4090 with 24GB of video memory, but it still runs out of memory.
This seems like great work, I will be trying it alongside RPG-DiffusionMaster. However, I saw that you also mention having support for segmentation maps, and did not see your code....
Hi, I am trying to run the RealCompo project using an NVIDIA RTX 3090 GPU, but I’m encountering CUDA out-of-memory errors. Since the RTX 3090 has 24 GB of VRAM,...