Blink's universal workflow | CivitAI metadata, upscaling, FaceDetailer (+indexing elements), inpainting, controlnet, IPAdapter (regional conditioning) and token counter (SDXL/PONYV6/ILLUSTRIOUS/NOOBAI-XL/ANIMAGINEXL4/SD1.5) ComfyUI beginner friendly all in one — v3

Use this ComfyUI workflow to inpaint and upscale images, with ControlNet, regional IPAdapter conditioning, and FaceDetailer. Choose LoRAs in the wildcard processor and copy them into a text field; the workflow produces inpainted or upscaled images and includes CivitAI metadata, a

Use shortcuts 1, 2, 3, and 4 to navigate the workflow.

To use FaceDetailer, upscaling, or ControlNet, click Enable Group in Fast Groups Bypasser (rgthree) at the top left.

For LoRAs, select them in the wildcard processor, then copy them into the text field.

Before downloading, check that the CivitAI listing shows version v3 by Blinkdotleh.

Suggestion

Listed node packs include ComfyUI_Mira, rgthree-comfy, comfyui-impact-subpack, comfyui_ultimatesdupscale, comfyui_ipadapter_plus, comfyui_controlnet_aux, comfyui-impact-pack, and comfyui-detail-daemon.

Other listed node packs are comfyui-inpaint-cropandstitch, comfyui-custom-scripts, comfyui_smznodes, ComfyUI_Comfyroll_CustomNodes, comfyui-image-saver, comfyui_fearnworksnodes, and ComfyLiterals.

Listed model files include bbox/face_yolov9c.pt, clip_vision_g.safetensors, Comfyui_00001_.safetensors, controlnet-union-sdxl-1-promax.safetensors, djmilxlvae_dminVae.safetensors, noobIPAMARK1_mark1.safetensors, RealESRGAN_x4plus_anime_6B.pth, sam_vit_b_01ec64.pth, and segm/`

For anime, consider leaving FreeU_V2 bypassed; the description says it does not work well with anime.

Suggestion · non vérifié

For SDXL-based checkpoints, the description links a ControlNet model.

3D posing requires a browser with hardware acceleration; the listing says the workflow is best on a 1440p display.

The listing does not state a license; check the source page's terms before reusing or sharing the workflow.

Suggestion