SXDL that looks like FLUX - v1.0

sxdlThatLooksLikeFLUX_v10.safetensors

v1.0

LEOSAM's HelloWorld XL

HelloWorld 6.0 Update - April 20, 2024Thank you for your patience. I have been job hunting recently, which caused some delays in the HelloWorld updates. Here are the main updates in version 6.0:<ul><li>HelloWorld 6.0 is an iterative improvement based on version 5.0. Based on my own testing, the realism effect is not significantly different from version 5.0. The main advantage of version 6.0 lies in its broader coverage of concepts in the training set. According to feedback, enhancements have been made in various themes including surrealism, boudoir, group photos, masks, origami, 3D renders, cars, dragons, and maternity photography. Some examples are provided in the illustrations.</li><li>HelloWorld 6.0 intentionally includes some low-quality images in the training to enhance the model's response to negative prompts. It is recommended to use the following terms in negative prompts: "low quality, jpeg artifacts, blurry, poorly drawn, ugly, worst quality".</li><li>The main body of the HelloWorld 6.0 training set employs GPT4v tagging. For images that GPT4v cannot tag, cogVQA guided by blip2-opt-6.7b is used for tagging. The tagging language style of these multimodal models differs significantly from the traditional WD1.4 tagger. To facilitate more accurate triggering of different concepts in the training set, I have compiled the top 250 high-frequency tagging words from the HelloWorld 6.0 training set. You can view these high-frequency words in<a target="_blank" rel="ugc" href="https://www.notion.so/LEOSAM-HelloWorld-6-0-Top-250-High-Frequency-Tagging-Word-List-1be4971bafb84c22a231ee2f6da29cc1"> this document</a>.</li></ul>Finally, although SD3 is about to be released, I will still update to HelloWorld XL 7.0, hoping to achieve greater enhancements in version 7.0!

leosamsHelloworldXL_helloworldXL60.safetensors

HelloWorld XL 6.0

HelloWorld XL 7.0

HW5.0_Euler_a_Lightning

HelloWorld XL 5.0 GPT4V

HelloWorld XL 4.0

HelloWorld XL 3.2 DPO

HelloWorld XL 3.0

HelloWorld XL 2.0

HelloWorld XL 1.0

Film Grain 2.0

Film Grain 1.0

Utopia 3.0

Utopia 2.0

Utopia

Reality 3.0

Fantasy2.0

Reality2.0

Reality

Fantasy

SXDL that looks like FLUX - v2.0

sxdlThatLooksLikeFLUX_v20.safetensors

v2.0

LEOSAM HelloWorld | SDXL Realism Checkpoint

HelloWorld 6.0 Model Ecological Other Content Guide:
- <a href="https://ovey8gb3jv7.feishu.cn/docx/ANw6dcuIoo12AKxEk2Ic1eyQnSZ?from=from_copylink" target="_blank">HelloWorld 6.0 Top 250 High-Frequency Tag Word List</a> 
- <a href="https://www.liblib.art/modelinfo/53f48a775e6f4e17ba475f421dcd08a7" target="_blank">HelloWorld 6.0 Lightning Acceleration Edition</a> 
- <a href="https://www.liblib.art/modelinfo/6c209b52c4894725aa37a05a7e15cbcb" target="_blank">HelloWorld 6.0 Inpainting Image Generation Special Edition</a>
 
Copyright Statement:
The HelloWorld series models (hereinafter referred to as "this model") were developed by me (hereinafter referred to as the "owner") with the support of the LiblibAI platform and were exclusively launched as XL large models on the LiblibAI platform. Except for the LiblibAI platform and Civitai platform, any individual or entity who releases this model on other platforms is not authorized by the owner.
The owner authorizes individuals or organizations to use the images generated by this model for non-commercial purposes of education or information dissemination, and:
- Comply with relevant laws and regulations, and do not infringe upon the legitimate rights and interests of this model or any third party.
- When using the images, it is necessary to indicate the image source as "Generated by LEOSAM's HelloWorld XL Model."
Prior to any commercial use, a commercial authorization agreement must be signed with the owner. For commercial authorization and model customization matters, please contact the owner through the homepage information on the LiblibAI platform.
The training and open-source sharing of the SDXL model are time-consuming, challenging work. The owner will continue to provide updates of the HelloWorld model for individual players for free, as an expression of support and gratitude to the community open-source contributors. Commercial cooperation from business users is an important driving force for the development and continuous improvement of this model. Thank you for the understanding and support of every user.
It should be noted that any unauthorized use may violate relevant laws and regulations and may incur legal liability. The final interpretation of this statement belongs to the owner and is subject to the relevant laws and regulations of the People's Republic of China.
 
2024.4.13 HelloWorld 6.0 Version Update
Thank you all for your patience. I have been looking for work recently, so the HelloWorld update has been delayed for a while. Below are the main updates for version 6.0:
- Version 6.0 is an iterative improvement based on version 5.0. According to my own tests, the realistic aspect of this version is not significantly different from 5.0. The main advantage of 6.0 lies in the broader conceptual coverage of the training set. Based on feedback, enhancements have been made to various themes including surreal, private rooms, children, group photos, masks, origami, 3D renderings, cars, dragons, maternity photography, and more. I have provided some reference examples in the demo images.
- In the training of version 6.0, some low-quality images were intentionally included to strengthen the model's negative prompts. It is recommended to use the following prompts in negative prompts: "low quality, jpeg artifacts, blurry, poorly drawn, ugly, worst quality."
- The main body of the HelloWorld 6.0 training set uses GPT4v tagging. For images that GPT4v cannot tag, cogVQA tagging guided by blip2-opt-6.7b is used. The tagging language style of such multimodal models is quite different from traditional WD1.4 taggers. In order to facilitate a more accurate triggering of different conceptual effects in the training set, I have compiled the top 250 high-frequency tag words in the HelloWorld 6.0 training set. You can view these high-frequency words in this document (<a href="https://ovey8gb3jv7.feishu.cn/docx/ANw6dcuIoo12AKxEk2Ic1eyQnSZ?from=from_copylink" target="_blank">https://ovey8gb3jv7.feishu.cn/docx/ANw6dcuIoo12AKxEk2Ic1eyQnSZ?from=from_copylink</a>).
 
Lastly, even though SD3 is coming soon, HelloWorld XL 7.0 will still be updated. Hopefully, version 7.0 will bring even greater enhancements!

Files with SHA256: 8ca0bade3c3fc4b412d34fb6a0ab99ec7f54aedd06bf7c61753dea863f86796f