How to use from the
Use from the
Diffusers library
pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline

# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Renz-7/RenderMatte", dtype=torch.bfloat16, device_map="cuda")

prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]

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