Verified: 3 months ago
SafeTensor
Type | |
Stats | 95 25 |
Reviews | (15) |
Published | Aug 27, 2024 |
Base Model | |
Training | Steps: 8,000 |
Trigger Words | cvttz06 car |
Hash | AutoV2 353B41743A |
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.
The main trigger words for this model are:
cvttz06 car
You can input this secondary words.
Flux not always follows them but is better than the SDXL version.
complete car
cropped
zoom
front view
rear view
3/4 front left view
3/4 front right view
3/4 rear left view
3/4 rear right view
side left view
side right view
zoom on headlamp
zoom on rear lamp
zoom on front wheel
zoom on rear wheel
front spoiler
rear spoiler
wheels turned
wheels spinning
motion blur
driver
FLUX:
This model was trained on 4090 using ai-toolkit
Lora intensity: 1
SDXL:
CFG scale: 3
Lora intensity: 0.7
Highly recommended to use highres.fix to 1.5x using one of this options:
upscaler: none or any you like with denoise: 0.4 (closer to original but less details)
upscaler: any latent with denoise: 0.5 or higher (more details but changes slightly)