Type | |
Stats | 588 141 |
Reviews | (62) |
Published | Jul 30, 2024 |
Base Model | |
Usage Tips | Clip Skip: 1 |
Trigger Words | photo of RAW photo of Analog photo of |
Hash | AutoV2 02EC35784D |
Before to use
You have to know how works Stable Diffusion. I recommend using ComfyUI or Automatic1111 like an interface to launch the model. Civitai doesn’t read the ComfyUI metadata, so you are welcome to experiment with it, and also consider that ComfyUI system is different from Automatic1111 (CFG, Steps, and configuration). Today I’m not using anymore Automatic1111, so these examples here are ComfyUI based. I tried to make a simple translation of the metadata.
This is a block-merge model based on XL models. I had to make so much testing before to arrive to a desirable generation. You have to consider that SD1.5 system is way different from SDXL, you can use both versions, but consider that.
This is a Checkpoint dataset, not a Lora.
It is a merge, so consider that it could sometimes generate NSFW images. Add in the negative prompt "(nudes:0.1)" or just "nudes", when is required.
I recommend you to follow me on my Instagram account, where I will explain about AI image generation: https://www.instagram.com/eddiemauro.design/
Intro
FRESH PHOTO (digital and 3d-eddiemauro mix) CHECKPOINT: Hi, I’m a product and car designer, and I’m so excited to test with AI, I think is a good tool for designing. It is a merged model that I created to facilitate my creations, and it has a SD1.5 version as well.
v1: it performs well in different types of photography. My idea is to create a "general model" to use it for realistic image creation. Also is sometimes creative, including some prompts, but for more creative models, use Fresh Magic or Fresh Draw (but you will lose reality).
v1 Lightning: Same than v1, but I consider that is better the normal model in quality. This model is faster in generation. This will work just with some samplers, like: DPM++SDE with scheduler: SIMPLE, HEUN +scheduler: SIMPLE. Steps from 4 to 6, and CFG from 1 to 2.
If you want to support my work and help me to upload more models (with better quality), you can do it by entering here and donating, I would greatly appreciate it: https://ko-fi.com/eddiemauro
Installation
I use ComfyUI, the best UI for Stable Diffusion image generation, so I recommend you to install locally or use it online with some Colab or other hosting. You can find online instructions or videos to do that.
You have to install the Checkpoint model to use. Put the file inside “Checkpoints” folder.
Please for image creation you have to follow some small recommendations, but please don't hesitate to experiment, XL system is more precise and interesting.
Recommendations for image generation
Activation token/caption: Inside prompt you can whatever you want, but you can start with "RAW photo of", “photo of” or "Analog photo of" (for a more retro style). If you want a more realistic representation, just put in the positive “realistic”, “photorealistic”, and to put more contrast, words like “dramatic lighting” or “cinematic”.
I recommend using “Wildcards” for prompt experimentation. Install any Node for ComfyUI, that works with Wildcards. This will put more creativity to your creations.
Textual inversion/embedding or Lora tool recommended: You can use whatever Lora or Embedding for XL system, for positive or negative. For negative prompt, I use: “low quality, worst quality, text, artifacts, strabismus, bad eyes, render”. If you want to put less realism, just put the opposite word inside the negative prompt. Sometimes is recommended to add in the negative prompt “asian”, to reduce asian face aspect, because of the results of the model merge, but is up to you to experiment. Put "nudes", or "(nudes:0.1) in the negative prompt, if you find that you are getting NSFW images.
VAE: This model is baked with VAE, and mostly the majority of the models are. But in case you wish to use the VAE, it works with the normal XL VAE.
Clip Skip: Use 1 mostly, and you will get more realism. You can use 2, for less realism, more contrast, colors and other effects, but is up to you to experiment.
Steps and CFG: It is recommended to use Steps from “30-40” and CFG scale from “5-6”.
Sampler: I use mostly “DPM++SDE - Karras”, but there are some interesting results with: “DPM++2S A - Normal” (simplier) and “DPM++SDE GPU - Karras”. For Lightning, is mandatory to use: DPM++SDE with scheduler: SIMPLE, HEUN +scheduler: SIMPLE. Steps from 4 to 6, and CFG from 1 to 2; also works DPM++SDE GPU +scheduler: SIMPLE or DPM++2M SDE +scheduler: SIMPLE.
Batch: In txt2img try to put a value of 4 to generate more than 1 image and watch the generations. If you have a good graphic card, you can use “Batch size”, this will create at same time 4 images, increasing generation time; but if your computer cannot handle this, change to “Batch count” that will create 4 images in a row (not a same time), but generation time will be more.
Image aspect: Try to use these dimensions: 1024x1024, or image size or aspects, related to 768 or 1024 on one or both sides. For example, I use the proportion of 768x1152. Then, for upscaling a rate of 1,5.
Create bigger images: There are 4 different methods to create large images in Stable Diffusion, you can check online how to. For the first method “txt2img hires.fix”, I recommend you to use upscale model called “8x-NMKD-Superscale_150000_G”, just “.pth” file, and then installing it, putting inside “ESRGAN” file. In hires.fix option put any “upscale by” value, and then with a “denoise strength” of “0.4-0.7”. For the second method, you have to select first the image generated in txt2img and then putting in img2img mode, increasing dimension at least “1,5 times” with a “denoise strength” from “0.4-0.7”. For the third method, you can use “tiled generation”, the same configuration of img2img, but activating “tile” mode of “ControlNet” extension or the script of “Ultimate SD Upscale”, but for that. For the last method, you have to pass the generated image in txt2img to “extras” and then select a GAN model and scale it, you can also use the “8x-NMKD-Superscale_150000_G” model.
Get more control of your creation: Use “ControlNet” extension to generate a more controlled shape of what you want, and even you can test it with sketches. Use “Scribble”, “OpenPose”, “Depht” or “Lineart” modes. For that, I recommend you to install this extension and then learn to how to use. There are plenty of online videos about it.
Example Prompting:
Positive prompt:
RAW photo of Laura Ojeda in casual clothes, little smile, Photorealistic, dramatic lighting
Negative prompt:
low quality, worst quality, text, artifacts, strabismus, bad eyes, render, (asian:0.1)
Steps: from 30-40. Lightning from 4-6.
CFG scale: 5-6. Lightning from 1-2.
What comes for the future
I’m already trying to enhance the model, with better merges. If you like a better model of this version, try to keep supporting me on ko-fi, if there are more people supporting me, I can invest more time to train and enhance models, but if this doesn't happen I cannot.
I launched my first private model for my Ko-fi membership lv.1, called "eddiemauro scene" minimalistic scenery creation for rendering. If you want to access to private models, you can support me and subscribe to this membership. I will also start to upload here more models centered on product and car design.
License
Watch here a Stable Diffusion license link. In the case of this specific model, use it for whatever you want in terms of image generation. It is prohibited:
Upload this model to any server or public online site without my permission.
Share online this model without my permission, using my exact model with a different name or uploading this model and then run it on services that generate images for money.
Merge it with a checkpoint or a Lora, and then publish it or share online, just talk to me first. In the future,
Sell this model or merges using this model.
Supporting
You can follow me on my social networks. I will show my process and also design tips and tools. Also, you can check my webpage and in case of you need a design service, I work like a freelance.
https://www.facebook.com/eddiemauro.design
https://www.instagram.com/eddiemauro.design