Qwen image has been getting a lot of unjustified heat for something wonderful (consistancy when updating prompts). Now I understand why some people want that random factor, finding the perfect shot by just hitting generate so I made this custom workflow that uses Qwen24VL3BInstruct to generate variations of the initial prompt, improving it and simulating the “old ways” of doing things. This uses Qwen Image Edit as base model for generating image, but the initial prompt tweaking nodes in the left can be copy pasted to any workflow. Link bellow and samples + youtube tutorial:
Workflow for getting Midjorney like images Version 2 (with Borealism LORA) Workflow for SRPO Refiner Edit: Changend the workflow and updated with better prompt generation. There is now a midjourneyfier boolean at the beginning of the left group so you can either diversify the prompt like the first example with the wires below or midjourneyfi the hell out of it like the later photos.
Daca e ceva ce am invatat acum 5 ani cand am renuntat sa ascult ce spune presa si mi-am luat inima in dinti si am petrecut o zi alaturi de emigranti la granita Grecia/Macedonia a fost fix asta: Sa nu mai ascult ce spune presa.
Nu au trecut nici 5 secunde si deja aud tiuitul ala surd atât de familiar si îmi dau seama ca nu am cum sa mă mai întorc iar in încă 5 totul va dispărea într-o mare de culori. Mai arunc o ultima privire in jur chiar in clipa in care contururile imaginii se accentuează si imaginea seamănă cu un desen cubist de o claritate impecabila.
Ma sperie ocazional genul de rationament folosit de persoane din jurul meu in acest trend de islamofobie la nivel european. E acelasi gen de retorica si rationament folosit in discutiile electorale sau listele de comentarii de pe varii articole pe internet.
