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.

Folder structure

ComfyUI/models/
├── unet/
│   └── SCAIL-2-Q4_K_M.gguf            ← from this repo
├── text_encoders/
│   └── umt5-xxl-enc-fp8_e4m3fn.safetensors
├── loras/
│   ├── Wan21_I2V_14B_lightx2v_cfg_step_distill_lora_rank64.safetensors
│   └── wan2.1_SCAIL_2_DPO_lora_bf16.safetensors   (optional)
├── sam/
│   └── sam3.1_multiplex_fp16.safetensors
├── clip_vision/
│   └── clip_vision_h.safetensors
└── vae/
    └── wan_2.1_vae.safetensors

Generated Examples

Here are some outputs from the model:

---

Notes

WEIGHT NOT MERGED warning on patch_embedding is harmless. ComfyUI builds a 36-channel patch embedding and concatenates the mask channels at runtime; the model fills them internally. The stored 20-channel weight is expected. Generation proceeds normally.
The colored mask is a required input even in single-character Animation Mode — don't remove it from the workflow.
Set width and height explicitly (both divisible by 16; 832×480 is a good 480p start).
The SCAIL2ColoredMask node may require a recent / nightly ComfyUI build.

Credits

Model: zai-org / SCAIL-2
GGUF quantization: RealRebelAI
GGUF tooling: city96 / ComfyUI-GGUF

加载中…

SCAIL-2 GGUFs (by Rebel AI)

⚡ Load with the GGUF Unet Loader (city96's ComfyUI-GGUF — Unet Loader (GGUF)). Place the .gguf in ComfyUI/models/unet/.

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

Folder structure

ComfyUI/models/ ├── unet/ │ └── SCAIL-2-Q4_K_M.gguf ← from this repo ├── text_encoders/ │ └── umt5-xxl-enc-fp8_e4m3fn.safetensors ├── loras/ │ ├── Wan21_I2V_14B_lightx2v_cfg_step_distill_lora_rank64.safetensors │ └── wan2.1_SCAIL_2_DPO_lora_bf16.safetensors (optional) ├── sam/ │ └── sam3.1_multiplex_fp16.safetensors ├── clip_vision/ │ └── clip_vision_h.safetensors └── vae/ └── wan_2.1_vae.safetensors

Notes

WEIGHT NOT MERGED warning on patch_embedding is harmless. ComfyUI builds a 36-channel patch embedding and concatenates the mask channels at runtime; the model fills them internally. The stored 20-channel weight is expected. Generation proceeds normally.

The colored mask is a required input even in single-character Animation Mode — don't remove it from the workflow.

Set width and height explicitly (both divisible by 16; 832×480 is a good 480p start).

The SCAIL2ColoredMask node may require a recent / nightly ComfyUI build.

realrebelai/SCAIL-2_GGUF

SCAIL-2 GGUFs (by Rebel AI)

Quant tiers

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)

📝 Text Encoder

🎛️ LoRA (LightX2V step/cfg distill)

🎯 SAM 3.1 Multiplex

👁️ CLIP Vision

🎨 VAE

➕ Optional: SCAIL-2 DPO LoRA (untested)

Folder structure

Generated Examples

Notes

Credits

SCAIL-2 GGUFs (by Rebel AI)

Quant tiers

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)

📝 Text Encoder

🎛️ LoRA (LightX2V step/cfg distill)

🎯 SAM 3.1 Multiplex

👁️ CLIP Vision

🎨 VAE

➕ Optional: SCAIL-2 DPO LoRA (untested)

Folder structure

Generated Examples

Notes

Credits