Issues
- 1
Is it possible to prompt 4m
#16 opened by antoan - 0
How to use semantic segmentation tokenizer for precomputing tokens for this modality?
#24 opened by HITESH2002-JAIN - 1
[Errno 2] No such file or directory: './fourm/utils/hmr2_utils/model_cfg.pkl'
#15 opened by kaz12tech - 3
How to use RGB DiVAE tokenizer?
#22 opened by shaibagon - 0
Typo for tokenizer_path arg
#23 opened by carlosjedwab - 1
- 0
Depth tokenizer
#21 opened by Shar-01 - 0
Input masks for generation - Potential small bug.
#20 opened by nilsec - 0
CUDA? Are you kidding me?
#19 opened by MikeyBeez - 0
Training details of RGB tokenizer
#13 opened by Cerf-Volant425 - 0
- 1
Question on Token Masking in 4M Implementation
#11 opened by yzhang511 - 0
Fine-tune using LoRA
#10 opened by audreyeternal - 2
Object Detection with Caption
#3 opened by hungphongtrn - 0
VRAM Requirements and Multi-GPU Inference Support
#5 opened by lifrary - 2
What’s the best way to use Color palette and another image to condition outputs?
#9 opened by amaarora - 11
- 0
- 1