cocorang/FireRed-Image-Edit-1.0-FP8_And_BF16
Same weights, repacked vs FireRedTeam/FireRed-Image-Edit-1.0. Same weights in different files (re-saved, re-sharded or new metadata).
Tensors changed: other 0/246, Embeddings 0/4, Attention 0/960, Norms 0/243, MLP 0/480
1 derivatives checked
- Novice25/FireRed-Image-Edit-1.0_comfy_GGUF: Quantization