Happy Ai-Portrait Photography Realistic High Fashion Photo Filter Photo Adjustment Runway-Flux.1
V2-BF16-HappyAi
Newly upgraded! The V2 version is much better than the older version in terms of skin texture, artistic aesthetics & good photography composition. This model is trained based on the FLUX.1 DEV version, with optional precision formats of BF16 (recommended) or FP8 .This model not only creates a more aesthetic atmosphere but also provides greater flexibility and give something genuinely new and engaging to creators.I sincerely hope you like the model and enjoy using it.
Below is a comparison of the two models with the same prompts, seed and CFG values:
（left） FLUX.1-DEV-FP8
（right）V2-FP8-Happy Ai
The following is a comparison showing two models with same prompts, seeds and CFG:
（left） V2-BF16-Happy Ai
（right）V2-FP8 -Happy Ai
Advantages of this model:
1. short prompts can generate high-quality images with good composition & aesthetics.
2. Strong flexibility, feel free to change gender, clothing, colors, actions, and scenes...etc.
3. High-res image can be generated directly ,so no additional highers fix is required.
4. Negative prompts are not required
---------------------------------------------------------------------------------
No Trigger is required:
But for the optimal generation results,highly recommend to add some prompts:
for portrait images, suggest to add : high fashion style_CHLO, portrait photography, realistic, realistic photography,
for non-realistic images, then the trigger words can be removed: for example, like the fantasy characters/monsters..etc
---------------------------------------------------------------------------------
Webui Parameter Suggestions for Version V2-BF16-Happy Ai Model:
Sampler: Euler (recommended)
CFG Value: 3.5 or 6 (recommended,Range 3.5-9)
for my personal use for this model, 6 is with more flexible effects but less realistic.
Steps: 30 ( Range 20---60 steps)
Size: 1024x1024, 832x1216, 832x1344,768x1024, 768x1344,1024×1152,1024×1536, and other normal sizes and it is better bigger than 1024.
Adding with lora: for realistic images, suggest to decrease lora weight to 0.5 as a start;
for non-realistic images, recommend to increase lora weight.
---------------------------------------------------------------------------------
Comfyui Parameter Suggestions:
（This model is good to use with comfyui workflow, pls refer to the comfyui link for version V2-BF16)
---------------------------------------------------------------------------------
Below is kind instruction for newbies to use shakker.ai O(∩_∩)O
Quick Start Guide:
The best way: Firstly Please choose the first row's image from the gallery below, and then click on "REMIX" to quickly refer to the same prompt words and create artwork.
---------------------------------------------------------------------------------
❤️Hello everyone~~ Welcome to " Happy Ai Art Studio" ❤️
Bonjour~~Xin chào~~สวัสดี~~Hola~~Sveiki ~~大家好~~みなさんこんにちは~~
안녕하세요 여러분~~привет~~नमस्ते~~مرحبًا
If you like this model, please click on "Run Model" to try it out (please click it at least once, thank you very much!), as this is the greatest encouragement to our original model creator. Alternatively, for click"❤️"to support it or sharing artwork in gallery, please follow me and give the images lots of likes❤️, highly appreciated!O(∩_∩)O
STEP1: Click " RUN MODEL"
STEP 2: Click" Favorited" to collect it
(this step is to choose the correct model automatically)
This is a high-quality model! Definitely a classic in the FLUX base model series that is worth collecting!
Creative ideas Introduction and Model Style Description:
This base model is good at aesthetic portrait photography style. In terms of realistic portrait photography or paintings, it has good performance effects whether it is Asian people or Western portraits. It is suitable for portrait photography, realistic photography, fashion magazines design, fashion photography design, design, fashion show design, runway show design, fashion event photography design, realistic portrait photography design, magazine cover design, realistic paintings,and film and television costume design....etc.
Webui Parameter Suggestions:
Sampler: Euler (recommended)
CFG Value: 3.5 or 6 (recommended,Range 3.5-9)
for my personal use for this model, 6 is with more flexible effects but less realistic.
Steps: 30 ( Range 20---60 steps)
Size: 1024x1024, 832x1216, 832x1344,768x1024, 768x1344,1024×1152,1024×1536, and other normal sizes and it is better bigger than 1024.
Adding with lora: for realistic images, suggest to decrease lora weight to 0.5 as a start;
for non-realistic images, recommend to increase lora weight.
(Kind remind: Different CFG values, different steps, or random seeds, , will produce different effects, please adjust them up or down as needed, surprises are waiting for you to discover~~~O(∩_∩)O)
Basic Positive Prompts Example Guide:
( Red words underlined are the guide explanation, which needs to deleted)
high fashion style_CHLO
(no trigger word is required, but for optimal effects, can be put at the beginning)
portrait photography, high fashion,realistic photography,Professional fashion shot,
(not compulsory, but highly recommned to add them)
(high Fashion Magazine cover:1.3) cute 20-year-old swedish woman with (tanned skin:0.8) and (freckles:0.6) and piercing blue eyes and blonde hair tied back,wearing a chrome metal dress,natural skin texture,realistic skin texture,(skin pores:0.8),(skin oils:0.8),forest with flowers in the background,(looking off camera:1.2),fine art photography,award winning photography,analog photography,film grain,Fujifilm XT* *hoto,(masterpiece),ultra-detailed,best quality,8K,High-resolution,Extremely sharp detail without blurring,extremely intricate detail,extremely realistic,Award-winning artwork,HD32K,
(add your target main character and outfit details description )
(masterpiece),ultra-detailed,best quality,8K,High-resolution,Extremely sharp detail without blurring,extremely intricate detail,extremely realistic,Award-winning artwork,HD32K,
( Highly recommend fixed Quality words to create good images)
-------------------------------------------------------------------------------------------------
Model Usage Statement:
1. You cannot host this model and its derivative versions (such as fusion model versions) on websites/applications that plan to earn income or donations.
2. You cannot directly sell pictures generated by this model unless you have made sufficient manual modifications to the picture so that it can be completely determined as your personal work in a legal sense. If you violate this clause, you will be personally responsible for all legal consequences, and I will not be held responsible;
3. You cannot use this model to deliberately create or share illegal or harmful content for dissemination and output. Please abide by public order and morality and use this model for positive purposes.
Disclaimer:
This model follows the Flux-1-dev-non-commercial-license agreement. It is for study purposes only, not for commercial use. All images generated by the model are created by the users themselves, and the model author cannot control the images created by the users. The model author will not be held responsible for any potential copyright infringement or unsafe images.
-------------------------------------------------------------------------------------------------
Dear all friends, if search " happy ai" in the Shakker's home page, you can find all my models.
Comfyui Parameter Suggestions:
（This model is good to use with comfyui workflow, pls refer to the comfyui link for version V2-BF16)
for inquiry, please contact: happyaiart@gmail.com