Solstice — The Icon's Checkpoint
🔔 Update: Solstice V2 is here
Solstice V2 retains the exact color tone and visual style established in V1 while introducing NSFW capability — the most requested improvement since launch.
Sample Generations
What V2 adds
NSFW generation is now functional without requiring external LoRAs for general use. However, this is not a hardcore model. For more explicit or specialized NSFW content, use of an additional LoRA is still recommended. Results are a significant improvement over V1, but not yet fully consistent across all scenarios.
V2 does not alter Solstice's visual identity. The cinematic realism, color grading, compositional behavior, material rendering, and lighting character from V1 remain intact.
Available Variants
| Variant | Description |
|---|---|
| FP8 | Default checkpoint |
| BF16 | Full-precision reconstruction. Loads using the standard "Load Diffusion Model" node (weight_dtype: default). No extra nodes required. |
| INT8 ConvRot | Quantized variant (~half file size) using INT8 weights with a Hadamard rotation applied to reduce quality loss versus plain INT8. |
Overview
Solstice is a Krea 2 Turbo checkpoint built around cinematic realism, visual harmony, elegant composition, premium image presentation and character LoRA compatibility.
It is not a simple checkpoint-to-checkpoint merge. Its development began with a collection of independently trained LoRAs, each contributing different visual characteristics, which were evaluated, refined through comparative testing, and merged into the official Krea 2 Turbo base.
Where the official Krea 2 Turbo base can lean toward semi-illustrative or semi-3D rendering — particularly with fantasy, character art, and stylized scenes — Solstice pushes those same concepts toward photographic realism.
Solstice also produces rich, naturally saturated color grading out of the box. Hues lean cinematic without requiring manual color correction, and the model maintains strong prompt adherence — what you describe tends to be what you get. Character LoRAs in particular integrate cleanly, with minimal interference to trained likenesses.
Visual Character
Solstice tends toward:
- Cinematic photographic realism over illustrative or CG rendering
- Rich color grading — naturally saturated, cinematic color and hues without requiring post-processing
- Refined material fidelity — skin, hair, fabric, leather, metal, glass, rain, wet surfaces
- Compositional harmony with clear subject hierarchy
- Natural cinematic lighting — backlight, rim light, neon spill, volumetric atmosphere
- Clean silhouettes, graceful posing, strong character presence
- Grounded fantasy realism — elves, warriors, cyberpunk rendered as live-action cinema
- Strong prompt adherence — follows intent closely without fighting the prompt or injecting unwanted elements
- Excellent character LoRA compatibility — minimal interference with existing LoRAs, preserving their likeness and style
- Genre versatility across fantasy, neo-noir, cyberpunk, editorial, action, and portraiture
Solstice vs. Serendipity vs. Soliloquy
| Model | Role | Strength |
|---|---|---|
| Soliloquy | The Photographer | Intimate photorealism, un-airbrushed skin, tactile surfaces, macro detail, beauty photography, close-range portraiture. The 85mm prime lens of the family. |
| Serendipity | The Director | Cinematic storytelling, camera placement, spatial depth, dynamic motion, multi-subject scenes, complex stage direction. Built around what is happening inside the frame. |
| Solstice | The Icon | Cinematic realism, elegance, visual harmony, refined subject presentation. Excels when you want fantasy, cyberpunk, glamour, action, or everyday scenes to feel photographed rather than illustrated. |
V1 to V2
V1 established Solstice's visual identity: cinematic realism, compositional intelligence, material fidelity, rich color grading, and premium character presentation. Its strong prompt adherence and clean LoRA compatibility quickly became standout traits recognized by the community.
However, V1 had effectively no reliable NSFW capability, which limited the model's usefulness for a significant portion of the community.
V2 addresses this directly. NSFW content is now achievable without external tools for general use cases. For more explicit or hardcore content, pairing with a dedicated LoRA is still the recommended approach — the model is improved but not yet fully mature in this area.
Visually, V2 is identical to V1. No changes were made to color grading, rendering behavior, compositional tendencies, or lighting character.
Version Notes
V2
- Introduced NSFW capability (general use; dedicated LoRA recommended for hardcore content)
- No changes to color grading, rendering style, or compositional behavior
- Visual identity identical to V1
V1
- Initial release establishing Solstice's core identity
- Cinematic photorealism, rich color grading, compositional harmony
- Strong prompt adherence and character LoRA compatibility
- NSFW capabilities unreliable — LoRA required
Content Notice
Solstice V2 is NSFW capable.
This is not a hardcore NSFW model. General NSFW content is now functional, but users looking for more explicit generations should pair with an appropriate LoRA for best results. This represents a significant step forward from V1, where NSFW was largely unreliable.
Users seeking strictly safe-for-work generations should still describe clothing clearly and use appropriate negative prompting or workflow-level safeguards.
Recommended Use
Solstice responds well to cinematic and photographic language. Effective prompts tend to include:
- Camera and lens language — 35mm photography, shallow depth of field, cinematic portrait
- Environmental context — rain, reflected light, architecture, haze, foreground elements
- Material descriptions — wet leather, translucent silk, brushed metal, weathered stone
- Clear lighting direction — sunset behind subject, neon from a storefront, candlelight
Solstice does not require tag-heavy prompts. A clear subject, environment, action, camera direction, and lighting concept are often enough.
Where Serendipity directs the scene, Solstice presents the image.
Make the impossible look photographed.
Licensing & Disclaimer
- Original Model Creators: All credit goes to KREA.ai for the original research, architecture, and weights.
- License: This model is subject to the KREA 2 License Agreement. Please read and comply with the official license terms before using these weights: KREA 2 Licensing Terms.
- Official Distribution: This model is only officially available on Hugging Face and CivitAI. Unauthorised redistribution, rehosting, or modification of these model weights is strictly prohibited. If you encounter this model on any other platform, it has been uploaded without permission.
Samples
"Sample #1"
"Sample #2"
"Sample #3"
"Sample #4"
"Sample #5"
"Sample #6"
"Sample #7"
"Sample #8"
"Sample #9"