!!! Before installing custom nodes from manager you need to install this one from Git url<a target="_blank" rel="ugc" href="https://github.com/Suzie1/ComfyUI_Comfyroll_CustomNodes">https://github.com/Suzie1/ComfyUI_Comfyroll_CustomNodes</a>because manager for some reason installs it from wrong placeIf manager fails to find LLM and lora nodes install them from git urls<a target="_blank" rel="ugc" href="https://github.com/willmiao/ComfyUI-Lora-Manager">https://github.com/willmiao/ComfyUI-Lora-Manager</a><a target="_blank" rel="ugc" href="https://github.com/AlexYez/comfyui-timesaver">https://github.com/AlexYez/comfyui-timesaver</a>If you had older version of crt_nodes custom nodes it is better to remove it, restart comfyui and install againThis workflow support<ul><li>Z-Image, Ernie image, Wan, Flux, Flux Kontext, Flux 2, Flux 2 Klein, Anima, Qwen Image, Qwen Image Edit, SDXL/Pony, Chroma and Lumina-Image 2.0</li><li>txt2img, img2img, Inpaint functionality.</li><li>Face swap (not that perfect atm)</li><li>SeedVR2 upscaler</li><li>LLM to describe images and enhance prompts (on first run it try to download model to models\llm folder) (LLM node works without image input, but you need to bypass image input node)</li><li>Klein Enhance node in i2i group. Try to experiment with Preserve original setting from 8 to 12.</li><li>ControlNet only for Edit models in img2img group (just describe your image in prompt and add some instruction like "use input image as normal map reference")</li><li>Outpainting in Edit/Kontext mode</li><li>safetensor, gguf and <s>svdq (Nunchaku)</s> checkpoints</li><li>Powerful multi Lora loader (Lora manager)</li><li>Face Detailer</li><li>Multi or single images load for Edit/Kontext</li></ul>

All-in-One. Z-Image, Ernie, Klein, t2i, i2i, controlNet, inpaint, outpaint, LLM, WAN, Qwen image, SDXL, Chroma

Added support for:<ul><li>Qwen Image</li><li>SDXL\Pony\Illustrious</li><li>Chroma</li></ul>Each model have its own lora loader for keeping settings between model after swithcing.Due to difficulties with installing the Qwen_3 LLM node dependencies, it has been replaced with <a rel="ugc" href="https://github.com/gokayfem/ComfyUI_VLM_nodes?tab=readme-ov-file">ComfyUI_VLM_nodes</a>, which can be installed directly from the manager. At the moment, the LLM is used for describing images. The node supports many models, but my favorite option is using<a rel="ugc" href="https://huggingface.co/concedo/llama-joycaption-beta-one-hf-llava-mmproj-gguf/blob/main/Llama-Joycaption-Beta-One-Hf-Llava-Q8_0.gguf">Llama-Joycaption-Beta-One-Hf-Llava-Q8_0.gguf </a>as a model and<a rel="ugc" href="https://huggingface.co/concedo/llama-joycaption-beta-one-hf-llava-mmproj-gguf/blob/main/llama-joycaption-beta-one-llava-mmproj-model-f16.gguf">llama-joycaption-beta-one-llava-mmproj-model-f16.gguf</a> as clipBoth files must be located in models/LLavacheckpoints folder.

Files with SHA256: 3c1729cabed898d531f537e3f435bf9c3b789893eafdaebb792ad05aaf3e89b2