Downloads · 30 days
7
2% of all-time downloads
Chroma-v36-dc-diffusers
imnotednamode/Chroma-v36-dc-diffusers
Chroma-v36-dc-diffusers is a text-to-image model from imnotednamode. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as apache-2.0.
All-time downloads
412
Public
Parameters
8.9B
27.5 GB on disk
Likes
4
Public
Repo makeup
Click a slice to open those files.
.safetensors27.5 GB · 100%
At a glance
- Task
- Text-to-Image
- Library
- diffusers
- License
- apache-2.0
- Access
- Public
- Created
- Jun 12, 2025
- Updated
- Jun 13, 2025
- SHA
- 38ce7ce7
Base models
Model card
From the Hugging Face model README
Generated with the following script
import torch
from diffusers import ChromaTransformer2DModel
from diffusers import ChromaPipeline
from transformers import T5EncoderModel, T5Tokenizer
chroma_transformer = ChromaTransformer2DModel.from_single_file("chroma-unlocked-v35.safetensors", torch_dtype=torch.bfloat16)
text_encoder = T5EncoderModel.from_pretrained("black-forest-labs/FLUX.1-schnell", subfolder="text_encoder_2", torch_dtype=torch.bfloat16)
tokenizer = T5Tokenizer.from_pretrained("black-forest-labs/FLUX.1-schnell", subfolder="tokenizer_2")
pipe = ChromaPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", transformer=chroma_transformer, text_encoder=text_encoder, tokenizer=tokenizer, torch_dtype=torch.bfloat16)
pipe.save_pretrained("Chroma-v36-dc-diffusers")
- Task
- Text-to-Image
- Library
- diffusers
- License
- apache-2.0
- Created
- Jun 12, 2025
- Updated
- Jun 13, 2025