Anima-aesthetic-v1.0-GGUF

This is a quantized GGUF repository for the Anima-Aesthetic-v1.0 model originally created by CircleStone Labs. The model weights have been converted into F32 and subsequently quantized into multiple GGUF formats using a patched version of llama.cpp to enable efficient CPU and GPU-offloaded image generation in ComfyUI.

🌟 Model Overview

• Original Model: circlestone-labs/Anima
• Architecture: 2 Billion parameter text-to-image model. It is built on the nvidia/Cosmos-Predict2-2B-Text2Image base.
• Variant: Aesthetic v1.0 (Fine-tuned for better consistency and a higher quality default art style compared to the base model).
• Focus: It is focused mainly on anime concepts, characters, and styles. The model is designed for making illustrations and artistic images, and will not work well at realism.

💻 Hardware Compatibility & File Sizes

Select the quantization that best matches your system's RAM/VRAM constraints. Q4_K_M or Q5_K_M are generally recommended as the best balance of speed and visual fidelity.

Bit Depth	Quantization Type	File Size
3-bit	Q3_K_M	1.02 GB
4-bit	Q4_K_S	1.27 GB
4-bit	Q4_K_M	1.38 GB
5-bit	Q5_K_M	1.56 GB
6-bit	Q6_K	1.74 GB
8-bit	Q8_0	2.24 GB

⚙️ How to Use in ComfyUI

1. Requirements

• Update ComfyUI to v0.14.1 or higher.
• Install the ComfyUI-GGUF custom node to enable the UnetLoaderGGUF node.

2. File Placement

Ensure you download the supplementary files located in this repository's split_files directories and place them into your local ComfyUI folders:

• Diffusion Model (GGUF): Place your chosen anima-aesthetic-v1.0-[Quant].gguf file into ComfyUI/models/diffusion_models (or the unet folder).
• Text Encoder: Place qwen_3_06b_base.safetensors into ComfyUI/models/text_encoders.
• VAE: Place qwen_image_vae.safetensors into ComfyUI/models/vae.

3. Aesthetic Generation Settings

Unlike the Turbo variant, the Aesthetic version is a full diffusion model and requires standard generation parameters:

• Steps: 30 to 50
• CFG Scale: 4.0 to 5.0
• Samplers: er_sde (good neutral default), euler_a (softer lines), dpmpp_2m_sde_gpu, or euler.
• Resolution: Works well at resolutions between 512x512 and 1536x1536 pixels.

4. Prompting Guide

Anima-Aesthetic was fine-tuned exclusively on high-quality images with quality tags stripped from the captions.

Syntax & Formatting:

• Use lowercase for tags, and spaces instead of underscores (except for score tags).
• You do not strictly need quality tags in the positive prompt, though "masterpiece, best quality, " is safe to leave in.

Troubleshooting Noise/Artifacts: If you are getting too much noise, artifacts, or messy details:

1. Lower the CFG.
2. Remove score_* tags from both the positive and negative prompts.
3. Add "anime coloring" to the prompt (optionally at a lower weight like 0.8).

Natural Language Tips:

• If using pure natural language, more descriptive is better.
• Aim for at least 2 sentences. Extremely short prompts can give unexpected results.
• You can seamlessly mix Danbooru tags and natural language in arbitrary order.

🌳 Model Tree & Lineage

• Base Architecture: nvidia/Cosmos-Predict2-2B-Text2Image
• Fine-tuned / Distilled Version: circlestone-labs/Anima (Aesthetic v1.0 variant)
• Quantized Version: Abiray/Anima-aesthetic-v1.0-GGUF (This repository)

📜 License

This GGUF model inherits the license established by the original creator. This model is licensed under the CircleStone Labs Non-Commercial License. The model and derivatives are only usable for non-commercial purposes. Generation outputs (the images themselves) generally remain free for commercial use under the original terms.