Verified: 8 days ago
SafeTensor
Created on Civitai
The FLUX.1 [dev] Model is licensed by Black Forest Labs. Inc. under the FLUX.1 [dev] Non-Commercial License. Copyright Black Forest Labs. Inc.
IN NO EVENT SHALL BLACK FOREST LABS, INC. BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH USE OF THIS MODEL.
This LoRA gives your images a soft, cinematic, hazy glow.
It does a good "vintage"—think golden-hour glow, delicate film grain, and muted pastel tones.
It was trained on ~350 AI-generated photographs capturing a variety of subjects (portraits, urban scenes, still lifes) under diffused light, fog, and analog-style color palettes. Ideal for:
Portraits with warm, nostalgic skin tones
Environments rendered in gentle focus, with subtle haze
Still Lifes that feel like polaroid snapshots
Use it whenever you want your output to look like a well-worn vintage photograph: cinematic, romantic, and softly textured.
⚙️ Recommended Settings for SDXL V1
Sampler: k_euler_a, k_dpmpp_2m
Steps: 30–60
CFG Scale: 3.0–6.0
Resolution: 1024×1024 (or 1:1 bucketed)
Prompt Example: “an atmospheric vintage-style portrait of a [subject] in soft golden light, subtle film grain, cinematic haze”
Negative Prompt Example: “overly sharp, cartoonish, digital artifacts”
💡 Usage Tips
Keep prompts simple. Don’t stack “masterpiece, ultra-detailed” boilerplate—this LoRA already lives in that aesthetic.
Experiment with lower CFG (4–5) to maximize softness; or bump to 6 if you need a touch more structure.
Pair with a warm color bias (e.g., “warm sepia tones”), or muted color bias for an extra vintage boost.
Seed control: use fixed seeds for series/consistency, or randomize for organic imperfections.
No trigger word(s). Just plug and play.
Any way you rock it, enjoy it ;)