Input reference image txt2img XL + ColorFix + ControlNet + Tile txt2img Flux + ColorFix + ControlNet + LoRA Tile ColorFix Patcher Patches the model to apply color correction at every denoising step.

My main environment is an M1 Max (64GB unified memory). I run FLUX / SD3.5 / WanVideo on ComfyUI, with a pipeline that operates day and night to automatically generate eye-catching images and ...

Abstract: The generation of remote sensing images plays a vital role in applications such as urban planning, urban development simulation, and environmental monitoring. The advent of diffusion models ...

This README consolidates and updates all features in this project, including the latest DiffSynth integration, Distill behavior, VRAM strategies, and Blockwise ControlNet Inpaint support.

Abstract: This paper investigates the application of generative models in simulating radar images, highlighting their capacity in generating realistic images from text description. To overcome the ...

Have you tried the new NVIDIA Cosmos-based anime-specialized model "Anima" (and its derivative, WAI-ANIMA) yet? It is reputed to be lightweight at 2B, with faces that don't melt, strong performance in ...