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
next status update for the the sparks v1 training at step 2 resolution 1024?
Hi! The training attempt failed because of excessive regularization, and the modelβs outputs looked too artificial and plastic-like. Iβm now using different training settings and have already updated the training info card.
Hi! The training attempt failed because of excessive regularization, and the modelβs outputs looked too artificial and plastic-like. Iβm now using different training settings and have already updated the training info card.
Thank you for the reply and your extreme work related to this model.
damn... thanks for the update. live and learn.
Is it done? This is the longest wait ever lol. Multiple anons have had their eyes on this project for awhile.
Is it done? This is the longest wait ever lol. Multiple anons have had their eyes on this project for awhile.
Hi! The model training will be completed on May 3β4.
