Instructions to use common-canvas/CommonCanvas-S-C with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use common-canvas/CommonCanvas-S-C with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("common-canvas/CommonCanvas-S-C", 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 Settings
- Draw Things
- DiffusionBee
Commit History
-
minor summar updates
Verified signature11ebd62 -
Update README.md
Verified signature0c2552d -
minor text updates
Verified signatureb75c29e -
update summary
Verified signature1b002a5 -
Update README.md
Verified signature037f660 -
Fix typo
Verified signatureFix typo336a0a0 -
Add tags
Verified signature561302c -
Improve formatting
Verified signaturebfa3806 -
Add Model Card Properly
Verified signatureabebcb4 -
Add Model Card
Verified signature# CommonCanvas-SNC ## Summary CommonCanvas is a family of latent diffusion models capable of generating images from a given text prompt. The architecture is based off of Stable Diffusion 2. Different CommonCanvas models are trained exclusively on subsets of the CommonCatalog Dataset (See Data Card), a large dataset of Creative Commons licensed images with synthetic captions produced using a pre-trained BLIP-2 captioning model. Input: CommonCatalog Text Captions Output: CommonCatalog Images Architecture: Stable Diffusion 2 Version Number: 0.1 The goal of this purpose is to produce a model that is competitive with Stable Diffusion 2, but to do so using an easily accessible dataset of known provenance. Doing so makes replicating the model significantly easier and provides proper attribution to all the creative commons work used to train the model. The exact training recipe of the model can be found in the paper hosted at this link. https://arxiv.org/abs/2310.16825 ## Performance Li…ac29fe9
-
Upload commoncanvas_s_c.safetensors with huggingface_hub
Verified signature2257218
-
Update README.md
Verified signature002e690 -
Upload unet/diffusion_pytorch_model.fp16.safetensors with huggingface_hub
Verified signature01cc4f5 -
Upload sd2-cc-512x512-comm-ep66-ba850000-rank0.pt with huggingface_hub
Verified signaturead26079 -
Delete v2-1_512-nonema-pruned.safetensors
Verified signaturec26907f -
Delete v2-1_512-nonema-pruned.ckpt
Verified signaturea576b4a -
Delete v2-1_512-ema-pruned.safetensors
Verified signature7bc083f -
Delete v2-1_512-ema-pruned.ckpt
Verified signature7c47e57 -
Delete diffusion_pytorch_model.safetensors
Verified signaturedd68c96 -
Upload unet/diffusion_pytorch_model.safetensors with huggingface_hub
Verified signatureebbdb26 -
Upload diffusion_pytorch_model.safetensors with huggingface_hub
Verified signaturecf0f0a7 -
Delete unet/diffusion_pytorch_model.safetensors
Verified signatureaecb852 -
Delete unet/diffusion_pytorch_model.fp16.bin
Verified signature1331c9e -
Delete unet/diffusion_pytorch_model.bin
Verified signatured925edd -
Delete unet/diffusion_pytorch_model.fp16.safetensors
Verified signature81f5334 -
Duplicate from stabilityai/stable-diffusion-2-1-base
Verified signatureCo-authored-by: Robin Rombach <rromb@users.noreply.huggingface.co>3f5521a