Sign In

2000s Digicam - Krea 2 RAW & Flux 2 Dev

37

Download

1 variant available

SafeTensor

372.04 MB

Verified:

Type
LoRA
Stats

951

0

Reviews
Published

Dec 29, 2025

Base Model

Flux.2 D

Usage Tips
Strength: 1
Hash
AutoV2
CA463DB1BF
default creator card background decoration
Likes - 882

882

Downloads - 5960

6K

Generations - 40636

40.6K

Krea 2 Training Contest Participant

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.

ComfyUI_00258_.png

Usage for Krea 2 RAW:

  • Trigger word is not needed, but if results are bad, add 2000s to the start.

  • Image resolution should be 1MP for best results, but 2MP works at higher weights.

  • I personally use 15 steps, ddim, and ddim_uniform

  • I use a turbo lora at 0.6 as well

Updates:

I am planning on training a v4.0 where I'll focus on improving image noise and finer details like that.

v3.0:

  1. Weights have been fixed and look good at 1.0. If the look is still missing, try adding 2000s to the prompt and/or raise the weight to 1.5 (Usually happens with modern subjects, like a cybertruck)

v2.0:

  1. No longer a struggle to get scenes void of people.

  2. Better skin textures.

  3. Lower LoRA weights change camera look, so flash photography, image noise, chromatic aberration, etc.

  4. Higher LoRA weights change people's clothes, hairstyle, and environment to a more 2000s adjacent look.

Usage for Flux.2 Dev:

I personally use 40 steps, Flux guidance at 4-5, Euler, Flux2Scheduler.

1024x1024/1024x768/1080x810 are the resolutions I've been using.

Updates:
There will be no more updates for the Flux.2 Dev version.