Sign In

Fantastic Pic [Flux]

104
861
655
41
Verified:
SafeTensor
Type
LoRA
Stats
861
655
2.8k
Reviews
Published
Jan 29, 2025
Base Model
Flux.1 D
Usage Tips
Strength: 0.8
Hash
AutoV2
B0B9836817
surush's Avatar
surush
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.

Please post the first picture directly here in the Model Gallery. This is the best way to support creators ♡

This version doesn't require any trigger words - Best Strength: 0.8

To create this LoRA, I initially downloaded approximately 200 photos from Flickr, sourced from top photographers. I then edited roughly one-third of the images in Photoshop, applying my desired effect. Another third I modified using the Image to Image method with Flux. The remaining third I left unchanged.

Due to the large image count and limited VRAM on my graphics card, I processed each group separately. Finally, I merged these three resulting models with a previous model I had created from images by a landscape photographer.

Unfortunately, the initial LoRA was unsatisfactory. Following a friend's suggestion, I reduced the image count to 90 carefully selected photos and incorporated a few images from Civitai. Using the same three-group process, I edited and processed the images. I then merged four LoRAs with varying weights, creating over 20 LoRA variations and conducting more than 500 tests. Finally, I achieved the desired result, which is the uploaded LoRA.

This LoRA subtly enhances contrast, adds a touch of realism and fantasy, and increases detail. It also imparts a slightly aged look, introduces subtle dirt and dust, and often generates fog in landscapes. In portraits, it tends to add a sunlight effect. It can also give images, particularly vehicles, a classic and aged appearance, and generally darkens the overall mood.

However, being a beginner, I'm aware that this LoRA may still contain issues and bugs. I would greatly appreciate it if you could help identify these problems so I can fix and improve the model.

Hope you get a lot of beautiful results ♥