YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
RenderMatte
This repository contains RenderMatte matting model weights.
Checkpoints
base_sft10000/: SFT-trained base transformer checkpoint after 10,000 SFT steps.grpo_lora_step300/: LoRA weights obtained from GRPO training at step 300. This folder includes both the fused LoRA file and the PEFT adapter files.
Files
base_sft10000/
transformer/
config.json
diffusion_pytorch_model.safetensors
grpo_lora_step300/
e2p_fused_lora.safetensors
peft_lora/
adapter_config.json
adapter_model.safetensors
These weights are intended for research use with the corresponding RenderMatte inference code.
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support