IMPORTANT The AMD optimizations need to be built/configured in your ComfyUI environment, drop <a target="_blank" rel="ugc" href="https://huggingface.co/PuppetVision/krea-2-amd-rocm-optimized-comfy-triton#copy-and-paste-implementation-instructions-for-chatgpt-or-other-flagship-llm">this guided setup prompt </a>into ChatGPT or other flagship LLM so it can guide you through optimizing your ComfyUI for AMD chips and use this <a rel="ugc" href="https://civarchive.com/models/2977983/krea-2-turbo-t2i-workflow-optimized-for-amd-rocm-comfyui">AMD Triton optimized workflow</a>. This is a merge of <a target="_blank" rel="ugc" href="https://civarchive.com/models/2775340/krea2-textfusion-refusal-reduction-lora-updated?modelVersionId=3359022">TextFusion Refusal Reduction lora</a> and <a target="_blank" rel="ugc" href="https://civarchive.com/models/2975872/krea-2-turbo-optimized-for-amd-rocm?modelVersionId=3372822">Krea2 Optimized for AMD ROCm INT8 checkpoint</a> Credits go to @puppet_vision and @Capitan01R

Files with SHA256: 507b31fc95a1bff823560f2a0a7c70859083471ffec4ed8840de8b576581e392