Text-to-Image
Diffusers
English
stable-diffusion
inference-time-alignment
preference-optimization
pg-map
Instructions to use sophialan/pg-map-sd15 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use sophialan/pg-map-sd15 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("sophialan/pg-map-sd15", 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
-
Compliance: venue-neutral for double-blind review
Ruolan Sun +1: Claude Opus 4.8Remove all 'under review at NeurIPS 2026' / NeurIPS-venue mentions (card text, @misc note, frontmatter tag/short_description, app.py title); cite arXiv only. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>44b267a
-
Add arXiv 2606.22958 to citations/links
Ruolan Sun +1: Claude Opus 4.8Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>82529a3
-
Update for PyPI rename + fixes
Ruolan Sun +1: Claude Opus 4.8- Install line: pip install pgmap-align (pg-map/pgmap taken on PyPI; import stays `pgmap`) - BibTeX @inproceedings -> @misc (preprint; under review at NeurIPS 2026) - De-claim NeurIPS acceptance framing - (SD1.5) model id runwayml/stable-diffusion-v1-5 -> stable-diffusion-v1-5/stable-diffusion-v1-5 Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>bea1f43
-
PG-MAP NeurIPS 2026 — v1.0 custom-pipeline release
Verified signature54b17f2 -
initial commit
Verified signature4cb9d1c