The rest of the set (MOSS, Z-Image, img2img, upscaling): <a target="_blank" rel="ugc" href="http://tinytensor.gumroad.com">tinytensor.gumroad.com</a>LICENCE — IMPORTANTQwen-Image 2.1 is released under the Qwen Research License Agreement: research and evaluation use only, not for commercial output. The licence says "FOR NON-COMMERCIAL PURPOSES ONLY", and commercial use requires a separate licence from Tongyi (model-business@notice.qwencloud.com).If you need images you can sell, use Z-Image Turbo or MOSS-Image instead — both are Apache 2.0. The other workflows in my 8GB pack cover both of them.Qwen-Image 2.1 in 4 steps, running on an 8GB laptop GPU at 1024x1024 — about 20 seconds per image.Everything in this workflow is tuned for 8GB of VRAM, not 24GB.WHAT YOU NEEDComfyUI (current build) + ComfyUI-GGUFqwen-image-2.1-UC-Q4_K_M.gguf (4.6GB) → models/diffusion_modelsqwen3vl_8b_int8_convrot.safetensors (9.35GB) → models/text_encodersqwen_image_2.1_vae_bf16.safetensors (0.68GB) → models/vaeqwen-image-2.1-lightning-4step.safetensors (0.07GB) → models/loras32GB system RAMSETTINGS THAT MATTERsteps 4 · CFG 1.0 · euler · simple · denoise 1.0At CFG 1.0 the negative prompt has no effect — that is normal with this LoRA, not a bug.If you get noise instead of an image, the LoRA is not connected.WHY IT FITS IN 8GBThat 9.35GB text encoder cannot sit on an 8GB card. ComfyUI loads it, runs it, then offloads it to system RAM — which only works if the encoder is loaded separately with CLIPLoader instead of inside a combined checkpoint. That, plus the Q4 GGUF weights and the 4-step distillation, is the whole trick.Measured on RTX 3070 Ti Laptop 8GB / Ryzen 7 6800H / 32GB RAM / Windows 11: 32s on the first run (loads the model), then 20.1s and 20.3s.The other nine workflows (Z-Image, MOSS 2.5D Anime, IPAdapter character lock, instruction-based editing, 4x upscale) are in a paid pack on Gumroad:https://tinytensor.gumroad.com/l/comfyui-8gb-vramAsk in the comments if something breaks — I read them.

Qwen-Image 2.1 4-Step — 8GB VRAM (1024² in 20s)

4-step lightning LoRA workflow tuned for 8GB VRAM. Requires ComfyUI-GGUF and 32GB system RAM. Full setup notes, model filenames and troubleshooting are in the model description.

Files with SHA256: faae980b316a80eb8ae7f7e151a32a888805cea25826f2833dad253a2316328a