Simple Text2Image Workflow for Beginners — v1.1

Use Simple Text2Image Workflow for Beginners — v1.1 to generate large images with a prompt and styling, a checkpoint, VAE, LoRAs, and basic render settings; choose generated pictures for face detailing and upscaling.

An image filter lets you choose pictures for refinement and upscaling; the workflow includes a face detailer, an upscaler, and image comparisons.

Inputs include a prompt and styling node, checkpoint, VAE, multiple LoRA loaders, and basic render settings.

Generated pictures can be compared, and selected pictures can go through face detailing and upscaling.

Setup tip: download any missing nodes, then choose the VAE and upscaler you want to use.

Sugestão · não verificado

Node packs named for this workflow: all-in-one-style, cg-image-filter, ComfyLiterals, comfyui_ultimatesdupscale, comfyui-art-venture, comfyui-impact-pack, comfyui-impact-subpack, and rgthree-comfy.

Model files listed for the workflow: bbox/face_yolov8n_v2.pt, RealESRGAN_x4plus_anime_6B.pth, and waiNSFWIllustrious_v140.safetensors.

The listed base model is Illustrious, and the workflow version is v1.1.

The creator reports that the “anything everywhere” nodes seemed not to work when loading; v1.1 omits them and has a less tidy layout.

The source page does not list a license.