Create unique visuals from text prompts using SDXL/Flux models. Ideal for designers needing rapid concept visualization.
IPAdapter Plus style transfer. One reference image in, prompt drives content. Official example.
Depth ControlNet via FLUX.1 Depth LoRA. Foreground/midground/background stay locked.
Canny edge ControlNet with FLUX.1. Auto-extracts edges, locks composition, prompt drives style.
2-pass OpenPose ControlNet. AnythingV3 base, AOM3A3 refiner, pose-locked from a reference image.
Qwen 2511 multi-reference image editor. 12GB GGUF runs on RTX 3060, 1328x1328 native.
Artifact-free native 4K+ image generation with FLUX via direct UNet patching through DyPE.
Wan 2.2 text-to-image with fast render and cinematic color science for vivid film-like output.
Turn photos into Miyazaki-style anime art with a tuned LoRA on SD1.5; bright shots work best.
Fast multi-image editing with Qwen, a multi-LoRA loader, auto 1M-pixel scaling, and a slider.
OmniGen2 7B text-to-image with high fidelity, visual understanding, and integrated in-image text.
OmniGen2 7B: instruction-guided image editing, T2I, and clear in-image text generation.
Endless poses, outfits, and scenes of one subject from a single image via QwenEdit and SDXL.
Generate images from text prompts with ComfyUI. This category covers the core image generation workflows built on SDXL, Flux, and other stable diffusion models — covering concept art, illustrations, product mockups, and stylized portraits. Each template is a ready-to-run node graph combining checkpoint models, samplers, and prompt controls; load it into ComfyUI and start from a working pipeline instead of a blank canvas. Browse the image generation templates below.