Updated: Jul 30, 2026
styleNot loaded
Download
1 variant available
256
1.2K
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.
Krea 2:
The Krea 2 version tends to add noise to the prompt, which can enhance textures and detail, but can also end up too noisy at times. I swap between er_sde and sgm_uniform for noisier generations where I want more detail and euler_ancestral and linear_quadratic when it gets too noisy. Lowering the strength can also help tone down the noise and artifacts.
Overall, I think it's a little quirkier than my Z-Image Turbo version, but it definitely has an impact on generation look.
Z-Image Turbo:
I really enjoyed the style of images ChatGPT would produce for a fictional film, so I trained a Z-Image Turbo LoRa on some ChatGPT generated images with prompts provided by ChatGPT itself. It did pretty much exactly what I wanted it to do.
I use it around 0.5-0.9 strength and I'd also play with samplers and schedulers as they have a fairly significant impact on final product. I think dpmpp and beta has worked the best for me, but it's also much slower than other samplers.