Repository Issue Activity (beta)

#21 Support OmniGen2 in ComfyUI

#129 输入图是否过了vit？

#138 about training data of in-context editing in Figure 6

#137 Question about `num_images_per_prompt` Setting in OmniContext Benchmark

#86 image generation metric results

#100 Any RL plan?

#127 Inquiry regarding the OmniGen2's reinforcement learning aspects

#108 Plans of releasing finetuning code for Image Understanding Task and Reinforcement Training?

#136 OmniGen2在UniGenBench上的效果

#131 Inquiry about training compute setup

#135 [2img2img] Not possible to replace texture in 1.jpg with 2.jpg

#134 [Bug]: CUDA error: device-side assert triggered with long prompts in T2I script

#133 about video_icgen

#132 question about noise_scheduler

#124 Number of T2I pairs

#28 Possible AMD/Zluda support?

#130 edit_pf_one data still broken after Aug 13 update

#125 For interleaved video data, what is the time interval between every two frames in video clips?

#128 数据集中多图输入的部分

#111 How to load LoRA weights in Omnigen2ChatPipeline?

#126 Any plan for distilled version of model?

#116 Where can I get the demo image?

#1 Thank you for the new release

#45 Great Work! Question on Hyperparameters Used in GEdit-Bench

#13 inference code not use reference image in MLLM