A pastel film photography style based on my personalized Midjourney style from the 7 model (with occasional 6.1 and flux images). Just like in the real Midjourney model, the eyes and hands might sometimes be messed up so it's best to use Adetailer at low denoise or better yet uDetection detailer where you can also add some gaussian noise for the complete film look.
Showcase shows the output directly unmodified from this model.
This lora would work nicely with other film style photography loras.
The trigger is P4st3l photo, you can also add Pastel Cinematic Film Photograph, vintage photo etc.
If you enjoy my models please support me on my ko-fi.com/mariegem <3
Happy creating~
I prohibit the illegal use of this model incl. the creation of indecent images.
DO NOT repost or reupload the model on other websites. I upload it there myself if I see fit.
(I do not allow it). If you notice my model on other websites not uploaded by me, please report it to me.
Should I discover the illegal use or reposting of this model, I reserve the right to take it down, and I will not be creating any subsequent models.
You are accountable for managing any intellectual property concerns related to the content generated through this model. It is your responsibility to ensure that the use of the generated content adheres to applicable laws, regulations, and the terms of this service. Unless otherwise permitted by laws and regulations, no one is allowed to integrate this model into any third-party software or service, nor reveal the connection between the generated content and this service to any third party, either directly or indirectly, in any explicit or implicit way. The model may not be used for commercial purposes, including but not limited to text-to-image, image-to-image, face swapping, etc. You will be held legally responsible for any breach of this agreement, and the author reserves the right to seek compensation for any losses incurred.
Description
FAQ
Comments (4)
Thank you! Works well this char loras, doesnt change the face.
That's why I had it redone, previous one had a "one face syndrome" :) thank you for feedback!
MarieGem I read somewhere about one method when lora training for a concept or style (which I assume this one is based on, Style?) is just blurring or coloring the face in and leaving only the body so you don't have any face anomalies when generating your own character lora. Is that what you did? Nonetheless, excellent job. Going to give a go!
ProvenFlawless nope, this one had more photos and more characters baked in. I will probably make more versions top, as Midjourney gets upgarded. This lora has photos from v 7 beta, I would like to make v7 standard lora too 🥰
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.








