showlab/Show-o

Issues

• Request for external caption files

  #52 opened a day ago by mmderakhshani
  0

• 二维码又过期啦

  #43 opened a month ago by sunzhens
  5

• Training Loss Values.

  #50 opened 9 days ago by mmderakhshani
  10

• 关于Loss的疑问

  #51 opened 9 days ago by tulvgengenr
  1

• Import BUG

  #37 opened 11 days ago by Masaaki-75
  4

• 代码中会把t2i、llm、mmu三部分的数据集混合起来训练

  #48 opened 24 days ago by sherlockma11
  8

• Small bug in Showo.mmu_generate？

  #49 opened 23 days ago by CladernyJorn
  2

• 代码中会把t2i、llm、mmu三部分的数据集混合起来训练？

  #47 opened 24 days ago by sherlockma11
  0

• 生成只能用magvit吗

  #46 opened 24 days ago by sherlockma11
  1

• 二维码又过期啦

  #45 opened 25 days ago by guoti777
  4

• About checkpoints to be used by finetune

  #44 opened a month ago by trmzpi02
  1

• lora

  #42 opened a month ago by Zhao-ZD
  2

• About multimodal sequence input

  #38 opened 2 months ago by tulvgengenr
  4

• FileNotFoundError

  #41 opened a month ago by Hannieliao
  2

• 二维码过期啦~！

  #40 opened a month ago by Strike1999
  1

• Does the dataset of Show-o contain synthetic data?

  #1 opened 3 months ago by nunbuzor
  6

• input_ids_mmu not appended to input_ids in train_w_clip_vit.py

  #39 opened a month ago by lzn87
  0

• Generation inference with interleaved input

  #35 opened 2 months ago by ys-zong
  2

• Evaluation on NLP tasks and training time

  #36 opened 2 months ago by KebinWu
  1

• Question about SHOW-O's CLIP version

  #34 opened 2 months ago by hills-code
  3

• Questions about generation quality

  #33 opened 2 months ago by xizaoqu
  1

• multimodal input -> image output

  #28 opened 2 months ago by Redtides0
  0

• Omni-Attention Implementation

  #32 opened 2 months ago by ChocoWu
  1

• 这个diffusion在哪里体现的？？

  #4 opened 3 months ago by Robootx
  4

• Does Show-o directly complete generation in pixel space？

  #31 opened 2 months ago by Delicious-Bitter-Melon
  3

• Please can you elaborate on the experiemntal setups for Table 4?

  #30 opened 2 months ago by zhaoyanpeng
  2

• Does show-o support multimodal-in multimodal-out?

  #27 opened 2 months ago by URRealHero
  6

• Dataset Preparation Script

  #29 opened 2 months ago by mmderakhshani
  3

• Keyframes generation inference code

  #11 opened 3 months ago by qqphung
  4

• 微信二维码过期了，麻烦更新下，谢谢

  #26 opened 2 months ago by tgyy1995
  1

• 图像生成推理问题

  #25 opened 2 months ago by william-ljz
  1

• What are the meaning of special tokens

  #24 opened 3 months ago by Doctor-James
  1

• ImportError: cannot import name 'SAFE_WEIGHTS_INDEX_NAME' from 'diffusers.utils'

  #23 opened 3 months ago by kurolykin
  3

• Question about the training of MAGVIT-v2

  #22 opened 3 months ago by RobertLuo1
  4

• The reason of continuous feature is better than discrete feature is before the codebook size is small?

  #19 opened 3 months ago by dongzhuoyao
  1

• No module named 'parquet.parquet_dataset'

  #21 opened 3 months ago by mrswang1
  2

• No module named 'parquet.parquet_dataset'

  #20 opened 3 months ago by mrswang1
  0

• FlexAttention example (for `mmu_vit` mask)

  #8 opened 3 months ago by Chillee
  4

• env issue

  #9 opened 3 months ago by TT2TER
  6

• Comparison with Transfusion

  #12 opened 3 months ago by NickGao96
  1

• Impact of Various Representations for Multimodal Understanding

  #13 opened 3 months ago by Doctor-James
  1

• How's the benchmark score on understanding?

  #6 opened 3 months ago by MonolithFoundation
  1

• runtime error

  #10 opened 3 months ago by junwenxiong
  1

• Can Flash Attention be used?

  #7 opened 3 months ago by wusize
  1

• GPU

  #5 opened 3 months ago by yuzhongruicn
  2