Anima-base-v1.0-GGUF
This repository contains GGUF weights for Anima-base-v1.0, a 2B parameter diffusion model based on the NVIDIA Cosmos architecture.
These weights have been quantized using a specialized pipeline to ensure maximum compatibility and image quality on consumer hardware.
🚀 Model Details
- Architecture: Cosmos (Diffusion)
- Parameters: 2 Billion
- Original Model: circlestone-labs/Anima
- Quantization: GGUF (K-Quants)
🛠️ Quantization Process
To ensure the highest possible quality and avoid the "BF16 noise bug" common in diffusion quantization, the following steps were taken:
- FP32 Casting: The original BF16
safetensorswere cast toFP32before conversion. - Architecture Patching: Used a patched version of
llama.cpp(based on buildb3962) with thecity96diffusion patch to support thecosmosarchitecture. - Precision Preservation: Sensitive layers (normalizations and biases) were kept in
F32to prevent color banding and generation artifacts.
💾 Available Quants
| File Name | Quant Type | Size | Description |
|---|---|---|---|
anima-base-v1.0-Q8_0.gguf | Q8_0 | ~2.1 GB | Near-perfect fidelity, recommended for 16GB+ RAM. |
anima-base-v1.0-Q6_K.gguf | Q6_K | ~1.6 GB | Excellent balance of speed and quality. |
anima-base-v1.0-Q5_K_M.gguf | Q5_K_M | ~1.4 GB | The "Sweet Spot" for most users. |
anima-base-v1.0-Q4_K_M.gguf | Q4_K_M | ~1.2 GB | Highly efficient, great for low-VRAM/RAM. |
anima-base-v1.0-Q3_K_M.gguf | Q3_K_M | ~1.0 GB | Maximum compression. |
🧩 Required Components
To use these GGUF weights, you still need the following parts from the original Anima release:
- Text Encoder: qwen_3_06b_base.safetensors
- VAE: qwen_image_vae.safetensors
🎮 How to Use
ComfyUI
- Install ComfyUI-GGUF custom nodes.
- Place the GGUF files in
ComfyUI/models/unet/. - Use the Unet-Loader (GGUF) node to load the model.
- Ensure you are using the correct Cosmos-compatible VAE and Text Encoder nodes.
⚖️ License
This model follows the NVIDIA Cosmos License. Please refer to the original model card for full usage restrictions.