| Stable Diffusion |
1.x, 2.x, 3 (SD3) |
Text-to-image, inpainting, and outpainting |
General-purpose AI art |
✅ |
| Stable Diffusion XL (SDXL) |
1.0, 1.5 |
High-resolution, photorealistic outputs |
Professional visuals, print media |
✅ |
| Flux |
V1 (Core), V2 (Render), V3 (Scene), V4 (Pipeline) |
Distributed workflows, fast rendering |
Large-scale projects, team workflows |
✅ |
| ControlNet |
Pose, Depth, Scribble |
Structured and guided image generation |
Animation, architecture, precise visuals |
✅ |
| LoRA (Low-Rank Adaptation) |
Customizable |
Fine-tuning for specific styles |
Custom art styles, branded content |
✅ |
| Waifu Diffusion |
1.3, 1.4 |
Anime-style content |
Anime and fan art |
✅ |
| Anything V4 |
V4 |
Fantasy and niche artistic styles |
Fantasy art and illustrations |
✅ |
| Real-ESRGAN |
Latest |
Image upscaling |
Low-resolution image enhancement |
✅ |
| GFPGAN |
Latest |
Face restoration |
Portrait and old photo restoration |
✅ |
| Inpainting Models |
SD 1.5, 2.x, 3 |
Fill missing or damaged parts of images |
Photo edits, artistic repairs |
✅ |
| Outpainting Models |
SD 1.5, 2.x |
Expand image boundaries |
Cinematic scenes, storytelling visuals |
✅ |
| Video-to-Video (V2V) |
AniDiff, Flux V2V, LTXV |
Stylized video transformation |
Animated memes, video effects |
✅ |
| Text-to-Video Models |
Experimental |
Text-guided video generation |
Storyboarding, creative media |
✅ |
| Depth Models |
Latest |
Create 3D-like depth maps |
AR/VR and interactive content |
✅ |
| Masking Models |
Customizable |
Object removal, transparent PNG creation |
Transparent assets, scene edits |
✅ |
| SDXL LoRA |
Fine-Tuned Versions |
Combines SDXL quality with LoRA adaptability |
Customized high-res niche outputs |
✅ |
| ComfyUI Models |
All Models |
Integrated node-based workflows for all listed models |
Seamless multi-model workflows |
✅ |
