
Optimize training and aesthetic evaluation based on (V1_80+|V2_300+|V3_600+) high-quality training sets in 2.35:1/2.39:1 size(Prefer cool tones)
FLUX LORA WEIGHT recommend:0.8-1 (0.4 adapt with other lora together)
sampler recommend size:1024x432/1504x640/1920x816(best size for result with high vram)
sampler recommend step:30-50steps
sampler recommend: dpm_adaptive+simple/beta(best)
Flux Guidance recommend:2.5(best)-3.5cfg
____________________________________________________________________________________
All Reviews and feedback are welcome
PS:(model is not limited to fixed proportions and can optimize composition and aesthetics and add the appropriate cinematic feel at any size)
This version is expected to be the last version of FILM lora
Tag prompts can be triggered(In the Trigger Words of model details
____________________________________________________________________________________
Tag List:
1.SIZE: Close Up, Extreme Wide size
2.LEN: Wide len, Long len, Medium len, Ultra Wide len, Telephoto len
3.SHOT: Low angle shot, High angle shot, clean single shot, Aerial shot, Establishing shot,
2 shot, Over the shoulder shot, Insert shot
4.Composition: Balanced composition, Center Composition, Right Heavy Composition, Left Heavy composition, Symmetrical composition
5.Light: Soft light, Hard light, Top light, Under light, Side light, Edge light, backlight, Sithouette
6.Contrast: High contrast, Low contrast
PROMPT-TAG example:"Extreme Wide size, Wide len, High angle Clean single shot, balanced composition, Hard light, High contrast"
____________________________________________________________________________________
描述:
训练词语: Extreme Wide size,Close Up,Long Len,mid len,Center Composition,Right heavy Composition,left heavy Composition,Balanced Composition,Soft light,top light,backlight,underlight,Hard light,Clean single shot,Over the shoulder shot,High angle,Edge light,Side light,Medium Len,Low contrast,high contrast,Low angle,2 shot,Silhouette,Insert shot,Establishing shot,Aerial shot,longlen,wide len,Symmetrical composition,Telephoto len
名称: FILM-V3-FLUX.safetensors
大小 (KB): 138271
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success