zer0int / Long-CLIP
Scripts for use with LongCLIP, including fine-tuning Long-CLIP
☆48Updated last month
Related projects: ⓘ
- finetune your florence2 model easy☆20Updated last month
- ☆40Updated 5 months ago
- Adaptive ODE Solvers for ComfyUI☆42Updated last month
- Token Downsampling optimization for stable-diffusion-webui☆23Updated 4 months ago
- Fine-tuning code for CLIP models☆120Updated this week
- ComfyUI powertools for SD1.5 and SDXL model merging☆61Updated last month
- Diffusers Implementation of Controlling Text-to-Image Diffusion by Orthogonal Finetuning☆31Updated 11 months ago
- ComfyUI Node for FlashFace☆61Updated 3 months ago
- Tools needed for training B-LoRA method with sd-scripts.☆32Updated last month
- A "loopback on steroids" type of extension for Stable Diffusion Web UI.☆27Updated last month
- ☆42Updated 8 months ago
- Various training scripts used to train bigasp☆35Updated 3 months ago
- Batched Runge-Kutta Samplers for ComfyUI☆48Updated last month
- Greatly increase the diversity of your generated images in Automatic1111 WebUI through Condition-Annealed Sampling.☆100Updated 4 months ago
- ☆68Updated 6 months ago
- ☆24Updated last month
- Testbed for the fastest SD pipelines☆35Updated 10 months ago
- Allows native usage of ModelScope based Text To Video Models in ComfyUI☆26Updated 3 months ago
- Provides the ability to set the temperature for both UNET and CLIP. For ComfyUI. Has for side effect to improve non-native resolutions.☆38Updated 2 months ago
- Merge safetensor files using the technique described in "Language Models are Super Mario: Absorbing Abilities from Homologous Models as a…☆67Updated last week
- Uses DARE to merge LoRA stacks as a ComfyUI node☆28Updated 3 months ago
- ComfyUI implementation of Long-CLIP☆93Updated 2 weeks ago
- [inactive] MoMA: Multimodal LLM Adapter for Fast Personalized Image Generation☆13Updated 4 months ago
- Fixed AttentionCouple/NegPip(negative weights in prompts), more CFG++ samplers, etc.☆58Updated last week
- ☆118Updated 2 weeks ago
- Prompt-Free Diffusion: Taking "Text" out of Text-to-Image Diffusion Models☆50Updated last year
- ☆56Updated last year
- Node to load LLM, it can be used to generate prompt or enhance them☆54Updated last month
- ☆21Updated 6 months ago