SCAIL 2 GGUFs (by Rebel AI) GGUF quantizations of SCAIL 2 , the end to end character animation / video motion transfer model (Wan 2.1 14B backbone) from zai org. These run the SCAIL 2 DiT in ComfyUI at a fraction of the VRAM the full fp16/fp8 weights require. Quantized by RealRebelAI · GitHub · YouTube ⚡ Load with the GGUF Unet Loader (city96's ComfyUI GGUF — Unet Loader (GGUF) ). Place the .gguf in ComfyUI/models/unet/ . Quant tiers Tier Approx size Notes Q2 K ~6 GB Smallest — runs on minimal VRAM, expect quality loss Q3 K M ~8.1 GB Budget tier, better coherence than Q2 Q4 K M ~10 GB Recommended daily driver Q5 K M ~12 GB Sweet spot above Q4 Q6 K ~14 GB Higher fidelity Q8 0 ~17 GB Closest to fp16 The loader memory maps the model, so a larger file costs disk and streaming time, not resident RAM. Required files (NOT included in this repo) Download each of these separately and place them in the listed ComfyUI folder. 📝 Text Encoder ComfyUI/models/text encoders/ 🎛️ LoRA (LightX2V step/cfg distill) ComfyUI/models/loras/ 🎯 SAM 3.1 Multiplex ComfyUI/models/sam/ 👁️ CLIP Vision ComfyUI/models/clip vision/ 🎨 VAE ComfyUI/models/vae/ ➕ Optional: SCAIL 2 DPO LoRA (untested) ComfyUI/models…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy