Knowledge of genetic behavior and type of gene action controlling target traits is a basic principle to design an appropriate breeding procedure for genetic improvement purposes, this study was carried out to estimate combining ability and nature of gene action for yield and its components in a flax. Six parents (P1= S.1074, P2 = Giza 12, P3 = S.813/8/3, P4= S.809/2, P5= Sakha 3, and P6= Beraton) were crossed in diallel mating design excluding reciprocals to obtain 15 F1 in season 2017/2018, in season 2018/2019, crossing among parents was carried out again in order to have more seeds for recording F1 traits, in the same time F1 plants were raised in breeding nursery and selfed to obtain F2 seeds. Six parents and their 30 crosses (15F1and 15F2) were evaluated in a randomized complete block design with three replications in season2019/2020 at Giza research station, Giza Governorate. The analysis of variance showed significant differences among all genotypes, parents, crosses for all studied traits in F1 and F2 generations, except number of seeds per capsule for parents, fruiting zone length in F1 for crosses. Mean squares due to GCA and SCA were significant for all studied traits, except fruiting zone length in F1 and number of seeds per capsule in F2 generation, indicating the importance of additive and non- additive genetic variances controlling studied traits. The ratio of GCA/SCA was greater than the unity for all studied traits, except straw yield/plant and no. of seeds/capsule in F2. Giza 12 (P2)showed high general combining ability for all traits under study, except for fiber percentage in F2.Two cross (P1×P2,and P2×P5) exhibited significant and positive SCA effects for each of straw yield/plant (in F1), plant height, and technical stem length in both generations, this cross included high x high general combiner parents for straw yield .Straw yield per plant was significantly and positively correlated with both of plant height and technical stem length, seed yield per plant exhibited highly significant and positive correlation with each of no. of capsules/ plant , 1000-seed weight. Therefore, the possibility of using the two traits (plant height and technical stem length) as selection criteria for improving straw yield per plant as well as using 1000-seed weight and number of capsules per plant as selection criteria for improving seed yield per plant.