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-Text2Imagebase. - 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
v0.14.1or higher. - Install the
ComfyUI-GGUFcustom node to enable theUnetLoaderGGUFnode.
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].gguffile intoComfyUI/models/diffusion_models(or theunetfolder). - Text Encoder: Place
qwen_3_06b_base.safetensorsintoComfyUI/models/text_encoders. - VAE: Place
qwen_image_vae.safetensorsintoComfyUI/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, oreuler. - 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:
- Lower the CFG.
- Remove
score_*tags from both the positive and negative prompts. - 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.