真实感ComfyUI SDXL Refiner from 1.x Models Workflow
此模型的原作者为「@MysteryWrecked」,我们致力于推动原创模型的分享和交流,因此转载了该模型、供大家非商用地交流、学习使用。请使用该模型的用户,遵守原作者所声明的使用许可。
如果您是该模型的原作者,请与我们联系,我们期待您入驻、并将第一时间把模型转移至您的账号中。如您不希望在 分享该模型,我们也将遵循您的意愿在第一时间下架您的模型。
我们尊重每一位模型原创作者,更期待与每一位模型作者共同成长!
声明:若该转载模型引发知识产权纠纷或其他侵权行为,我们将立即下架模型,并不会向原作者追责。
Final Version 3.0! This workflow is meticulously fine tuned to accommodate LORA and Controlnet inputs, and demonstrates interactions with embeddings as well. It is highly recommended to use a 2x upscaler in the Refiner stage, as 4x will slow the refiner to a crawl on most systems, for no significant benefit (in my opinion). Also, use caution with the interactions between LORA, Controlnet, and embeddings with corresponding weights, as horrors may ensue. You have been warned ;)
Now you can run 1.x models through the SDXL refiner, for whatever that's worth! Use Loras, TIs, etc, in the style of SDXL, and see what more you can do. Let me know if this is at all interesting or useful!
Oh, you thought I was crazy before?! Well now look what I've done. The base stage now outputs to HiresFix before refining with SDXL. What.
暂无评论信息...