VectorSpaceLab OmniGen issues

VectorSpaceLab / OmniGen

OmniGen: Unified Image Generation. https://arxiv.org/pdf/2409.11340

MIT License

2.89k stars 228 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

feat: rm unused character

#95 a1364533187 closed 3 weeks ago
2
Add Replicate demo and API

#94 chenxwh closed 3 weeks ago
1
Are there any ways to make this run faster on low-end GPUs?

#93 runshouse opened 3 weeks ago
0
Stuck on either loading safetensors or fetching the files.

#92 tedcar opened 3 weeks ago
2
OmniGenCache makes Omnigen CUDA only is there an option to not use it.

#91 Vargol opened 3 weeks ago
7
CUDA out of memory

#90 TanvirHafiz opened 3 weeks ago
2
RuntimeError: OffloadedCache can only be used with a GPU

#89 TanvirHafiz opened 3 weeks ago
2
1Torch was not compiled with flash attention.

#88 ialhabbal opened 3 weeks ago
4
The performance on DreamBooth benchmark

#87 XavierCHEN34 opened 3 weeks ago
3
Excellent Work - Made auto installers for Windows (run locally - using 5.5 GB VRAM), RunPod and Massed Compute (run on cloud) - installs into venv , Python 3.10

#86 FurkanGozukara opened 3 weeks ago
5
allow custom device specification inside OmniGenPipeline

#85 bghira closed 3 weeks ago
1
update error message when attention mask is not supplied

#84 bghira closed 3 weeks ago
1
gradio is missing , but installed

#83 anigno opened 3 weeks ago
5
Is it possible to save the image in any format other than WEBP?

#82 amoebatron opened 3 weeks ago
2
remove duplicate from requirements

#81 Tialo closed 3 weeks ago
1
cannot import name 'OmniGenPipeline'

#80 runshouse closed 3 weeks ago
0
Multi gpu feasible?

#79 matbee-eth opened 3 weeks ago
3
Update PEFT to v0.13.2

#78 bghira closed 3 weeks ago
1
Python version and conda environment?

#77 PixelArmony opened 3 weeks ago
5
app.py Typo on Line 365

#76 diegonunez77 opened 3 weeks ago
1
app.py gives RuntimeError: Numpy is not available

#75 rzoun opened 3 weeks ago
2
OmniGen would be more useful if it only editted images instead of regenerating them

#74 fluthru opened 3 weeks ago
4
I am getting Error OffloadedCache can only be used with a GPU

#73 chnisar515 opened 3 weeks ago
10
Extremely slow while loading OmniGen

#72 zc1023 opened 3 weeks ago
4
ValueError: Default process group has not been initialized, please make sure to call init_process_group.

#71 WuYeeh opened 3 weeks ago
4
Output image error

#70 vcoopers opened 3 weeks ago
5
delete npu

#69 staoxiao closed 3 weeks ago
0
After pip install -e . I'm getting this Error, I have python in path, and I'm using miniconda

#68 LeoRibkin opened 3 weeks ago
1
NameError: name 'is_torch_npu_available' is not defined. Did you mean: 'is_torch_xla_available'?

#67 fbauer-kunbus opened 3 weeks ago
21
NameError: name 'is_torch_npu_available' is not defined. Did you mean: 'is_torch_xla_available'?

#66 larini closed 3 weeks ago
1
What does the num_cfg do?

#65 MoonBlvd opened 3 weeks ago
2
8bit

#64 werruww opened 3 weeks ago
1
great job, but why not vae of sd3

#63 Robootx opened 3 weeks ago
1
Image editing loss function

#62 brycegoh opened 3 weeks ago
9
How to deal with "Numpy is not available"

#61 freemank1224 opened 3 weeks ago
6
fix: typo on saving of ema state dict

#60 brycegoh closed 3 weeks ago
1
Saving of EMA state dict in train.py

#59 brycegoh closed 3 weeks ago
2
Is it possible to try to support llm of other architectures as the backbone?

#58 win10ogod opened 3 weeks ago
1
Open weights or frozen?

#57 DarkAlchy closed 3 weeks ago
2
How/where to change host IP settings?

#56 NicodemPL opened 3 weeks ago
4
Errors when running on Macos Sonoma - M1 RuntimeError: OffloadedCache can only be used with a GPU

#55 adamreading opened 3 weeks ago
7
Why is my image output just a bunch of noise? I'm sure the settings are correct, and the GPU is indeed running.

#54 dzbb2 opened 3 weeks ago
7
Add project page

#53 staoxiao closed 4 weeks ago
0
Would it be possible to do OmniGen type prompting with FLUX?

#52 nikshepsvn closed 4 weeks ago
1
Thank you

#51 nitinmukesh closed 3 weeks ago
1
Update Readme

#50 staoxiao closed 4 weeks ago
0
new inference code

#49 staoxiao closed 4 weeks ago
0
please allow fp16 in model to reduce VRAM as option

#48 gavytron opened 4 weeks ago
3
Please improve the fine-tuning script!

#47 win10ogod opened 4 weeks ago
10
Can I replace phi3 llm?

#46 win10ogod opened 4 weeks ago
3

Previous Next