Comfyui workflow for text to video, image to video, video to video, video stylize, video character replacement, clothes swapper, long video generation, low VRAM, 6 steps, all in one simple ULTIMATE workflow.=====================v2 Coming soon add prompt progression/scheduler add xtend existing video add 2 image reference =====================v1.20250724 Ultimateadd xtend long video generator (with controlnet+masking available)add loopback featurebetter upscale and uprte methodhigher resolution for the same VRAMFramepack killer=====================READ ME‼️‼️Adjust only parameters in YELLOW nodesprompt the GREEN node in detailread the MUTER SWITCH GUIDE and MODEL GUIDEcheck additional switchs/adjustment in YELLOW nodesleave the BLACK nodes intactbypass SAGE ATTENTION node if you don't have it installed====================MODEL GUIDE Use VACE model + CauseVid and/or Self-Forcing lora14B for quality1.3B for faster inferenceChange GGUF Loader node to Load Diffusion Model node for .safetensor files===========================================================14B VACE model GGUF + CauseVid lora (6 steps only)<a target="_blank" rel="ugc" href="https://huggingface.co/QuantStack/Wan2.1_14B_VACE-GGUF/tree/main">https://huggingface.co/QuantStack/Wan2.1_14B_VACE-GGUF/tree/main</a><a target="_blank" rel="ugc" href="https://huggingface.co/julienssss/causevidlora/blob/main/Wan21_CausVid_14B_T2V_lora_rank32.safetensors">https://huggingface.co/julienssss/causevidlora/blob/main/Wan21_CausVid_14B_T2V_lora_rank32.safetensors</a>or14B FusionX VACE GGUF (CauseVid merged)<a target="_blank" rel="ugc" href="https://huggingface.co/QuantStack/Wan2.1_T2V_14B_FusionX_VACE-GGUF">https://huggingface.co/QuantStack/Wan2.1_T2V_14B_FusionX_VACE-GGUF</a>===========================================================1.3B VACE Self-Forcing model used (6 steps only, no CauseVid needed)<a target="_blank" rel="ugc" href="https://huggingface.co/lym00/Wan2.1_T2V_1.3B_SelfForcing_VACE/tree/main">https://huggingface.co/lym00/Wan2.1_T2V_1.3B_SelfForcing_VACE/tree/main</a>*1.3B VACE GGUF fails to give good result===========================================================Use <a target="_blank" rel="ugc" href="https://openmodeldb.info/models/4x-ClearRealityV1">https://openmodeldb.info/models/4x-ClearRealityV1</a> for upscaling=====================SWITCH GUIDEText to video = all OFFImage reference to video = Image1 ONImage to video = Image1 + FLF ONFirst &amp; Last Frame to video = Image1+2+FLF ONFLF video control = Image1+2+VidRef+FLF+control ONV2V style change = Image1+VidRef+controlnet ONV2V subject change = Image1+VidRef+control+SAM ONV2V background change = same as above+invert maskSwitch ON Xtends switches according your needs (monitor progress in the group)Loopback ON to make looping video

WAN2.1-VACE-14B 1.3B GGUF 6 steps AIO (t2v-i2v-v2v-FLF-controlnet-masking-long duration) simple ComfyUI workflow

Add Xtend (long duration) and loopback feature.Better upscaler and uprate method. Generate higher resolution with the same VRAM. Simpler settings with more features.

Files with SHA256: 6a4e1f84f774f92b1a1cf258037d76c6dcfbee465e67f61b3666ed4a9c01047f