Model
Trends
.ai
Model
Trends
.ai
nejlepší open source AI modely
Spustit lokálně
naoUrasawa_style_flux_v1.safetensors
18 MB · SafeTensor
Stahování zajišťuje Civitai. Někteří autoři vyžadují nejprve přihlášení na Civitai.
AD
<naoki-urasawa-flux>
O tomto modelu
FLUX · LoRA
Vytvořil
Yofaraway
na Civitai
by yofaraway - Trained on images from the manga "Monster" and "20th Century boys" by Naoki Urasawa. Start the prompt with : A naoUrasawa style image of Using this upscaler seems to improve the style towards a true manga scan most of the time (and get rid of colors). I've used it with hires fix and denoising strenght of 0.5.
Poznámky autora
KREA 2 Showcase images : - Turbo model : 10 steps / CFG 1 & Euler simple - 944x1408 - x2 Hires (10 steps, 0.35 with 4x_NMKD_Siax) - Lora strength 1.3 IDEOGRAM 4 Json caption style with : - art_style : Naoki Urasawa style - medium : manga - aesthetics : black_and_white KLEIN 9B v1: Showcase images : - Distilled model (same prompt images posted with the base model below) - 768x1152 - Euler / normal / 4 steps / CFG 1 - Hires steps : 4 / NMKD_SIAX / x2 - Lora strength of 0.8-1 ZIT v1: I'm relatively new to Z-Image turbo model, so still experimenting, but I had good results with these settings : - 1056*1584 // 10 Steps // CFG 1 - DDIM & Beta - Lora strength of 0.9 I've noticed that using previous prompts (like the ones from Qwen v2) doesn't work that well, so I've used a vision model (Qwen3-VL-8B) with to get updated caption which was giving way better results. Qwen v2: Same as for my , I've retrained with everything I've learned so far, and this version is way better : closer to the target style and more flexible. v1: Trained with Ostris Toolkit: Dataset is 44 images (mainly from "Monster", "20th Century Boys" and "Pluto" by Naoki Urasawa) with no trigger word (but sometimes it helps to add "black and white manga style image of"). All the image have been generated in 4 steps in addition to the The prompt adherence of Qwen is really impressive, but I feel like the likeness of the style is not as good as with Flux (even tho is still good), but I'm still experimenting so it's just an early opinion. Flux Trained on images from the manga "Monster" and "20th Century boys" by Naoki Urasawa. Start the prompt with : A naoUrasawa style image of Using seems to improve the style towards a true manga scan most of the time (and get rid of colors). I've used it with hires fix and denoising strength of 0.5.
Spouštěcí slova
naoUrasawa style image
1,347 stažení · 176 lajků na Civitai
SHA256
B3EF0466C74912E1FA424C692D5C444E17783D25B2E5F6395E6FE5777DE9D42D
ID modelu ModelTrends.ai
#5962
Nahlásit obsah
Ukázkové rendery
Prompty a nastavení sdílená lidmi, kteří tyto rendery vytvořili na Civitai. Vyberte render a uvidíte, jak vznikl.
Nastavení
Sampler
Undefined
Kroky
20
Guidance
3.5
Seed
2276128639
Velikost
832x1216
Clip skip
2
Použitá váha
1
Prompt
a naoUrasawa style image of a cosmonaut sitting on the moon playing guitar neer a campfire. There is the dark infinite space in background. There is a bubble next to his head with the text "I just need more space." The overal atmosphere of the image is melancholic and peaceful.
Nastavení
Sampler
Undefined
Kroky
25
Guidance
3.5
Velikost
832x1216
Clip skip
2
Použitá váha
0.6
Prompt
YFG-Aarchy, naoUrasawa style image. An important image of important technology. Seriously important.
Nastavení
Sampler
Euler
Kroky
20
Guidance
1
Seed
552200004
Velikost
896x1152
Prompt
a naoUrasawa style image of a girl standing on a street at night. She is pointing a glock 19 at the camera. She is wearing a dark top with a cleavage, a jeans and a necklace. She has long hair, and a serious expression on her face. There is a bubble with the text "Try this flux lora now." next to her head. <lora:naoUrasawa:1>
Nastavení
Sampler
Undefined
Kroky
20
Guidance
3.5
Seed
552200005
Velikost
832x1216
Clip skip
2
Použitá váha
1
Prompt
A naoUrasawa style image of a doctor woman standing in a hospital hallway. She has long black hair and glasses, and is wearing a white doctor's coat. She is holding a human brain dripping in her hands, and is offering it to the camera. She has a serious expression on her face. There is a speech bubble next to her head with the text "I think you may need this.". The overal atmosphere of the image is tense. <lora:naoUrasawa:1>
AI modely pro generování obrázků, videa a textu
naoki urasawa flux je LoRA pro rodinu Flux uvedený na ModelTrends.ai, katalogu open source AI modelů pro obrázky, video a text určeném jen ke čtení. Porovnejte ho s dalšími modely Flux, podívejte se na jeho skóre žhavosti a vyzkoušejte ho na PirateDiffusion nebo BitVector.
Procházet podle rodiny modelů
Procházet všechny modely