nolan4

Hi @krigeta — here’s a screenshot of my workflow, which is based on the Qwen text-to-image template. I’m also using the same EliGen LoRA from Diffsynth Studio that you linked....

Looks like you have multiple loras, try just one for testing purposes. I tried your prompt with a few minor modifications:

@geroldmeisinger @krigeta Latest version supports 8 entities! Below is a screenshot for the referenced DiffSynth [example](https://github.com/modelscope/DiffSynth-Studio/blob/538017177a6136f45f57cdf0b7c4e0d7e1f8b50d/examples/qwen_image/model_inference_low_vram/Qwen-Image-EliGen.py#L100).

2nd'ing @Spyridonidis98's workaround. I've done something similar to produce 2D BEV dynamic occupancy grids: https://github.com/nolan4/carla-2D-dogmas