Download
1 variant available
fp16 SafeTensor
lora.TA_trained.safetensors
Half precision, best balance • 584.4 MB
Verified: 4 hours ago
Version 1 Krea Dev

1460 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
1830 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
2260 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
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.
Base Model
FLUX Krea Dev, use with this DiT for max compatibility.
Recommended Settings
LoRA strength: 0.4-0.6
Starting strength: 0.5
Steps: 20–30
Recommended: 25
Sampler: Euler
Upscaler: 4x UltraSharp
Guidance / CFG: Use the sampler's recommended FLUX range; start around 3.0–4.0 if your interface exposes guidance.
Resolution: 1024 × 1024
For wider automotive compositions, try 1216 × 832 or another landscape FLUX-compatible resolution.
Suggested Prompt Structure:
Use SunsetDrive as the LoRA trigger/concept and describe the scene naturally:
SunsetDrive, beautiful adult woman sitting in the passenger seat of a luxury car, cinematic portrait photography, warm sunset light streaming through the windows, detailed car interior, natural skin texture, realistic photography, shallow depth of field
Generative AI Resources:
KoFI: https://www.kofi.com/tensorvizion
Patreon: https://www.patreon.con/tensorvizion

