Sign In

flux-photo

207
4k
3.9k
96
Updated: Dec 4, 2024
stylephotophotorealisicflux1.d
Verified:
SafeTensor
Type
LoRA
Stats
685
381
1.7k
Reviews
Published
Nov 25, 2024
Base Model
Flux.1 D
Usage Tips
Strength: 1
Hash
AutoV2
079B92E9DF
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 use transparent alpha or beta for a more precise effect that won't change the overall composition too much. Use v6.0 for a stronger impressive photo/detail/realism enhancement.

Transparent Alpha and Beta: (more compatible, finer details)

  • Trained to target finer details only

  • More compatible

  • Preserves Context Better

  • Use like a slider, weight 0.5-3.0

V6: (stronger effect, can affect context)

  • Use simple prompts - "An old man in a wooden fishing boat",

  • Use Lora strength 1.0, but experiment with 0.2 - 2.0 as needed. Has a wide weight range

  • Only add 'realistic' or 'fine hairs, visible pores, etc.' if you're not getting results

  • dies sampler+simple scheduler or Euler sampler+beta/simple scheduler (others may also work well)

  • Guidance 2 - 5 (usually 3.5)

  • Steps 20 a 50 (usually 25 or 35)

Improved dataset, diffusers training back end used via SimpleTuner, weight tuned with custom script.

V5:

Improved dataset, trained for flux-dev on the flux-dev2pro fine-tune designed to improve training by pushing the model to work with smaller steps.

***Note: In my demo photos I had the file named 'flux-photo_v6.0_turbo' but it's the same file, there is no v6_turbo. I went through several versions and canned all but this one that stood out. Turbo? You might get away with a few less steps, but I didn't want to put turbo in the name.

V4-compatible/standard/extreme:

standard is usually the best, extreme with weight scaled down can be nice for exaggerated or forced photo realism, but can eat styles and turn things into normal people. compatible is pretty nuanced, could be nice with a higher weight.

V3-high-strength:

excellent on it's own with no prompt input about realism

V3-medium-strength:

excellent added to prompts that already have other loras or language about photorealism so it doesn't overbake the generation

flux lora trained on high quality photography images to produce realistic high quality photos without needing to add any tags or keywords (i.e. no 'a photo of' or 'realistic' etc.)