Krea2_Anything2RealCharacters-V2
🚀 Try Online / 在线一键体验
Don't have a high-end GPU? You can run and test this model directly on RunningHub without local setup:
无需本地部署显卡，点击下方链接即可在 RunningHub 上直接运行与体验该工作流： 👉 Click Here to Run on RunningHub / 在线运行链接
⚡ Compute Sponsor / 算力支持致谢
Special thanks to our compute sponsor for providing the GPU acceleration required to train and fine-tune this 2048px model!
本模型的 2048 高清微调训练离不开算力赞助方的大力支持，非常感谢！欢迎扫码关注/支持算力提供方：
Krea2_Anything2RealCharacters-V2 is a high-resolution Image-to-Image / stylization model fine-tuned on top of Krea2_Turbo. It is specifically optimized to translate any 2D, anime, or artistic input into a high-fidelity, photorealistic style with fine skin micro-textures and precise facial details.
✨ Key Features
- Native 2048px Resolution Training: Trained on a full dataset at 2048×2048 resolution, allowing high-resolution direct outputs without additional upscalers.
- Micro-Texture Detail: High-precision rendering of skin pores, hair strands, and realistic lighting.
- LoRA Compatibility: Fully compatible with Krea2 Text-to-Image (T2I) LoRAs for adjusting photography styles, lighting, and facial genetics.
- Embedded Style & Feature Triggers: Fine-tuned support for custom film filters, lighting setups, and specific feature keywords.
- Dual-Image Identity Transfer (Experimental): Supports transferring real-world identities from a reference image onto anime/stylized poses.
⚙️ Recommended Inference Settings
To achieve optimal outputs, use the following parameters:
| Parameter | Recommended Value | Description |
|---|---|---|
| Sampler Steps | 8 |
Matches the Krea2 Turbo architecture |
| CFG Scale | 1.0 |
Prevents over-saturation and artifacts |
| Target Resolution | 2048 × 2048 |
Native 2K output |
| CLIP / VAE | Standard ComfyUI Models | Download official weights from ComfyUI Repository |
🔑 Prompting & Trigger Words
Primary Trigger
Include the main trigger phrase at the start of your positive prompt:
Primary Style Trigger:
transform the image to realistic photograph
Auxiliary Triggers & Filters
Mix and match these trained keywords to modify style, lighting, or body features:
- Demographics:
caucasian,woman,man,muscular - Gaze & Angles:
looking at camera,look down,unfocused face - Lighting & Aesthetics:
backlight,Film filter,hazy,photorealistic,highly detailed - Attire & Features:
black stockings,white stockings - Anatomical Details:
pubic hair,labia
🧪 Dual-Image Persona Conditioning (Experimental)
For transferring a real-world face onto a 2D/anime pose:
- Figure 1: Base anime image (determines pose and structure).
- Figure 2: Reference person image (determines real-world identity).
Dual-Image Trigger Phrase:
with the character looking exactly like the one in Figure 2.
⚠️ Note: Dual-image feature transfer is experimental and results may vary depending on the seed and input alignment.
🖼️ Preview & Comparison
🙏 Acknowledgments
Special thanks to the Krea2 Team for providing the incredible foundational model to the open-source community.
📬 Links & Socials
- Online Workflow: RunningHub Demo
- GitHub: AIGC-Singularity
- Civitai: AIGC-Singularity
- Bilibili: AIGC特异点
- YouTube: AIGC-Singularity
- WeChat: aigctyd
- email:a592991299@gmail.com
- Downloads last month
- -