Instructions to use SG161222/SPARK.Chroma_v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use SG161222/SPARK.Chroma_v1 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("SG161222/SPARK.Chroma_v1", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
i see 100% on the training update.
#4
by sasori7713 - opened
Hi!
So far, the training is fully completed only at 512 resolution. There may be artifacts, but I will upload this model. I recommend using it with Flash LoRA.
I am currently preparing the model for training at 1024 resolution, which should improve the model's quality and eliminate artifacts. Once the model is trained at 1024, it will mean that the training is fully completed.
Thank you so much for your great work. π
Wow, what an improvement, thank you!
what is the current status of the model? its been 57% for 5 days.
