cyber-meow / anime_screenshot_pipeline
A 99% automatized pipeline to construct training set from anime and more for text-to-image model training
☆203Updated 6 months ago
Related projects ⓘ
Alternatives and complementary repositories for anime_screenshot_pipeline
- Efficient Train Data Collector for Anime Waifu☆290Updated 2 months ago
- Merge models with separate rate for each 25 U-Net block (input, middle, output). Extension for Stable Diffusion UI by AUTOMATIC1111☆318Updated last year
- A convenient and user-friendly anime-style image data processing library that integrates various advanced anime-style image processing mo…☆212Updated this week
- ☆234Updated last year
- This extension replaces the built-in LoRA forward procedure.☆160Updated 10 months ago
- Color/Detail control for Stable Diffusion web-ui☆208Updated last month
- text-image dataset maker for anime-style images☆92Updated 2 months ago
- DAAM for Stable Diffusion Web UI☆161Updated 8 months ago
- LoRAの階層適用を手助けするツールとチュートリアルです。☆149Updated last year
- Low-rank adaptation for Erasing COncepts from diffusion models.☆317Updated 10 months ago
- Extension for Stable Diffusion web-ui enables negative prompt in prompt☆204Updated last month
- WebUI to edit dataset captions for txt2img models☆134Updated 3 months ago
- opinionated bayesian optimisation for stable diffusion models block merge☆120Updated 3 months ago
- A research about "NAI anime" art featruring pure negative prompt and a lot more.☆97Updated this week
- ☆128Updated 3 weeks ago
- An Image utils extension for A1111's sd-webui☆197Updated 5 months ago
- A sampler base on Euler, aim at generating better picture/一种基于Euler的采样方法，旨在生成更好的图片☆171Updated 2 months ago
- LoRA training extention for Stable Diffusion Web-UI☆148Updated last week
- ☆227Updated 10 months ago
- model convert extension for stable-diffusion-webui. supports convert fp16/bf16 no-ema/ema-only safetensors☆320Updated 5 months ago
- A sd-webui extension for utilizing DanTagGen to "upsample prompts".☆260Updated last week
- Stable Diffusion web UI の Latent Couple 拡張で、好きな位置にプロンプトを置くためのツールです。☆145Updated last year
- a1111 implementation of https://github.com/ChenyangSi/FreeU☆306Updated 6 months ago
- An Automatic1111 extension for dynamically controlling the weights of LoRAs during image generation☆242Updated last year
- Latent Couple extension (two shot diffusion port)☆140Updated last year
- Prevents the artifact that tends to occur with XL models☆73Updated 7 months ago
- Train generative models with pytorch lightning☆294Updated this week
- Extension that patches Hypernetwork structures and training☆116Updated last year
- ☆107Updated 10 months ago
- Makes the prompts for generating anime images more detailed by upsampling Danbooru tags.☆86Updated 6 months ago