c-a-g-coinmaker / README.md
multimodalart's picture
Upload folder using huggingface_hub
2f2a26a
---
license: other
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: c01n
widget:
- text: c01n
---
# C.A.G. - Coinmaker
![Image 0](1722152.jpeg)
<p>Hi again! Long time no see.</p><p>Welcome to <strong>Coinmaker</strong>. Coinmaker is my second "concept art generator" here. This time I trained a coin-asset-generator LORA for SDXL 0.9 that will makes easier, more fun and aesthetics the coin assets creation for videogames, renders, etc. It's specially useful for 3D projecting and extrude-modelling in 3D softwares. So that's why instead of having an small coin it will generate a big coin to be able to extrude all details (as requested)... also he told me that could be used for logo/shield but that's not the main purpose.</p><p><br />Token is <strong>c01n.</strong></p><p><br /><strong>IMPORTANT</strong>: This was tested under <a target="_blank" rel="ugc" href="https://github.com/comfyanonymous/ComfyUI">ComfyUI</a>, I don't have any idea how it will go with Automatic1111. I strongly recommend you to use ComfyUI if you want good results and most important, <s>if you want the same settings I used just drag any image into the ComfyUI and it will show the full workflow, </s><strong>it seems CivitAI converted all samples to JPG so instead of dragging the images (if the workflow is not appearing):</strong></p><p><br /><a target="_blank" rel="ugc" href="https://huggingface.co/datasets/davizca87/C01nWorkflow/tree/main">https://huggingface.co/datasets/davizca87/C01nWorkflow/tree/main</a> <strong><span>&lt;- LOAD it via Json file in Comfyui</span></strong></p><p><br /><strong><u>How to prompt and which values to use?</u></strong><br />********************************************<br />- The LORA works perfectly with <u>values from 1-1.2</u> and bellow even IMO it's better to stay at 1 (you can see Clip and Model 1/1 values).<br />- Resolutions <strong>768x768</strong> and <strong>1024x1024 onwards</strong>, very important the <strong>ratio is a SQUARE.</strong></p><p>- You should prompt with a <u>little description of what you want having in mind it was trained to have a clean background and a type of meta</u>l. This is just for an specific purpose but currently support 4 metals (gold, silver, bronze, ancient).</p><p>- Structure as: "<u>photograph/design/artwork of a (type of metal) c01n with a concept-you-want inscription over black background</u>". Black background makes cleaner creations while inscription even optional push forward the trained aesthetics.</p><p></p><p><strong>This LORA is good for</strong><br /><strong>**********************</strong></p><p>- 3D renders of coins of different type and styles. &lt;- Main purporse<br />- Variations of a lot of coins inner properties. ex: bloody, melt, drip, damaged...<br />- Concepts engraved in the coins. Some may need prompt tweaking<br />- Realistic or semi-realistic results.</p><p></p><p><strong>This LORA is not to be used for:</strong><br /><strong>**********************************</strong></p><p>- Moving the coins between or across the scenes or putting them inside any recipient.<br />- Making ANY figure/character engraved, some won't work. Thats' AI limitations.<br />- Fill an scenery of coins.</p><p><br /><strong>Massive thanks to the original user</strong> who requested this LORA and let me upload this to CivitAI so all could enjoy. Hope you all enjoy this and thanks for the continue support in our <a target="_blank" rel="ugc" href="https://www.patreon.com/user?u=90661954">Patreon</a></p><p><br />Have fun! David.</p><p></p>
## Image examples for the model:
![Image 1](1722156.jpeg)
![Image 2](1722154.jpeg)
![Image 3](1722155.jpeg)
![Image 4](1722157.jpeg)
![Image 5](1722153.jpeg)
![Image 6](1722159.jpeg)
![Image 7](1722160.jpeg)
![Image 8](1722161.jpeg)
![Image 9](1722164.jpeg)