AndreRatzenberger
AndreRatzenberger
Can confirm that this happens with me too. Running with --no-half-vae and "scale by 2" LDSR Desktop (please complete the following information): OS: Win11 Browser: Chrome GPU: 2080
> It is an Apple M1 Pro, 32GB Ram, German macos Sonoma 14.4.1 Same configuration and same problem as OP. Funnily the performance of CommandR is improved by a lot...
You also can change your workflow so you can use both files, like this one: https://weirdwonderfulai.art/comfyui/stable-cascade-workflow-with-upscaler/ text encoder goes into clip, and stage c into unet. That's the beauty of...
What he means is that the AsyncMemory is missing the MemGraph implementation AsyncMemory only uses mem0.memory.graph_memory ```python if self.config.graph_store.config: from mem0.memory.graph_memory import MemoryGraph self.graph = MemoryGraph(self.config) self.enable_graph = True ```...