ciaranbor 6f0cb99919 Ciaran/flux1 kontext (#1394) ...

## Motivation

Add support for FLUX.1-Kontext-dev, an image editing variant of
FLUX.1-dev

## Changes

- New FluxKontextModelAdapter: Handles Kontext's image-to-image workflow
- encodes input image as conditioning latents with special position IDs,
generates from pure noise
- Model config: 57 transformer blocks (19 joint + 38 single), guidance
scale 4.0, ImageToImage task
- Pipeline updates: Added kontext_image_ids property to PromptData
interface, passed through diffusion runner
  - Model cards: Added TOML configs for base, 4-bit, and 8-bit variants
  - Dependency: mflux 0.15.4 → 0.15.5
- Utility: tmp/quantize_and_upload.py for quantizing and uploading
models to HuggingFace

## Test Plan

### Manual Testing

Works better than Qwen-Image-Edit

2026-02-06 16:20:31 +00:00

..

config_examples

Fix bench after recent updates (#1331)

2026-01-29 19:14:40 +00:00

prompt.txt

Consolidate!!! Fixes

2025-12-03 12:19:25 +00:00

quantize_and_upload.py

Ciaran/flux1 kontext (#1394)

2026-02-06 16:20:31 +00:00

run_llm.py

8000 -> 52415 (#915)

2025-12-18 18:39:44 +00:00

run_llm.sh

8000 -> 52415 (#915)

2025-12-18 18:39:44 +00:00

set_rdma_network_config.sh

shfmt

2026-01-29 15:24:36 +00:00