KohakuBlueleaf / HakuLatent
A comprehensive codebase for training and finetuning Image <> Latent models.
☆31Updated last month
Alternatives and similar repositories for HakuLatent:
Users that are interested in HakuLatent are comparing it to the libraries listed below
- ☆19Updated 8 months ago
- ☆46Updated 5 months ago
- Model code for inferencing T5☆63Updated last month
- ☆78Updated this week
- ☆48Updated this week
- Understand Human Behavior to Align True Needs☆22Updated 9 months ago
- ☆28Updated 8 months ago
- finetune your florence2 model easy☆20Updated 8 months ago
- H1111 --- Simple GUI for Video Models☆35Updated this week
- [ECCV 2024] DC-Solver: Improving Predictor-Corrector Diffusion Sampler via Dynamic Compensation☆47Updated 7 months ago
- Gradio UI for training video models using finetrainers☆27Updated this week
- Custom LORA training on DynamiCrafter☆18Updated 8 months ago
- Swiftly get tons of images from indexed tars on Huggingface☆54Updated 4 months ago
- Multimodal captioner☆104Updated last week
- A system for Prompt generation to improve Text-to-Image performance.☆77Updated last month
- Tiny AutoEncoder for Hunyuan Video & Wan 2.1☆30Updated 3 weeks ago
- Crawler and cleaner of data for novelai embedding's training☆20Updated 2 weeks ago
- A progressive upscaling-img2img version of hires.fix, extension script for AUTOMATIC1111/stable-diffusion-webui.☆26Updated last year
- Inference code of "Golden Noise for Diffusion Models: A Learning Framework".☆33Updated 4 months ago
- Comfy UI nodes for Flex.1☆15Updated last week
- ☆44Updated 3 months ago
- ComfyUI powertools for SD1.5 and SDXL model merging☆82Updated 3 weeks ago
- Greatly increase the diversity of your generated images in Automatic1111 WebUI through Condition-Annealed Sampling.☆105Updated last year
- Pytorch implementation of Towards Consistent and Controllable Image Synthesis for Face Editing☆54Updated 2 months ago
- Janky implementation of DiffuseHigh for ComfyUI☆32Updated 3 months ago
- ☆78Updated last month
- Set of auxiliary tools to use with image and video generation libaries. Mainly created to be used with diffusers☆44Updated 3 months ago
- MoD Control Tile Upscaler for SDXL Pipeline☆54Updated last month
- ☆36Updated last year
- Vision Transformers Needs Registers. And Gated MLPs. And +20M params. Tiny modality gap ensues!☆41Updated last month