This is a DFloat11 losslessly compressed version of the original lodestones/Chroma (v39) model. It reduces model size by 32% compared to the original BFloat16 model, while maintaining bit-identical outputs and supporting efficient GPU inference .
Model source
Source description
Sources
1 sourceSource excerpts
3 excerptsThis is a DFloat11 losslessly compressed version of the original lodestones/Chroma (v39) model. It reduces model size by 32% compared to the original BFloat16 model, while maintaining bit-identical outputs and supporting efficient GPU inference .
lodestones/Chromalodestones/Chromabash pip install -U dfloat11[cuda12] # or if you have CUDA version 11: # pip install -U dfloat11[cuda11] bash pip install -U diffusers python import torch from diffusers import ChromaTransformer2DModel, ChromaPipeline from transformers.modeling_utils import no_init_weights from dfloat11 import DFloat11Model with no_init_weights(): transformer = ChromaTransformer2DModel().to(torch.bfloat16) DFloat11Model.from_pretrained( "DFloat11/Chroma-DF11", bfloat16_model=transformer, device="cpu", ) pipe = ChromaPipeline.from_pretrained("lodestones/Chroma", transformer=transformer, torch_dtype=torch.bfloat16) pipe.enable_model_cpu_offload() prompt = [ "A high-fashion close-up portrait of a blonde woman in clear sunglasses. The image uses a bold teal and red color split for dramatic lighting. The background is a simple teal-green. The photo is sharp and well-composed, and is designed for viewing with anaglyph 3D glasses for optimal effect. It looks professionally done." ] negative_prompt = ["low quality, ugly, unfinished, out of focus, deformed, disfigure, blurry, smudged, restricted palette, flat colors"] image = pipe( prompt=prompt, negative_prompt=negative_prompt, generator=torch.Generator("cpu").manual_seed(433), num_inference_steps=40, guidance_scale=3.0, ).images[0] image.save("chroma-output.png") basemodel: lodestones/Chroma basemodelrelation: quantized pipelinetag: text-to-image tags: dfloat11 df11 lossless compression 70% size, 100% accuracy
DFloat11/Chroma-DF11