diff --git a/CHANGELOG.md b/CHANGELOG.md index 99d0d0337..295279932 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,8 +1,8 @@ # Change Log for SD.Next -## Update for 2026-03-24 +## Update for 2026-03-25 -### Highlights for 2026-03-4 +### Highlights for 2026-03-25 This release brings massive code refactoring to modernize codebase and removal of some obsolete features. Leaner & Faster! And since its a bit quieter period when it comes to new models, notable additions would be : *FireRed-Image-Edit* *SkyWorks-UniPic-3* and new *Anima-Preview* @@ -18,7 +18,7 @@ But also many smaller quality-of-life improvements - for full details, see [Chan [ReadMe](https://github.com/vladmandic/automatic/blob/master/README.md) | [ChangeLog](https://github.com/vladmandic/automatic/blob/master/CHANGELOG.md) | [Docs](https://vladmandic.github.io/sdnext-docs/) | [WiKi](https://github.com/vladmandic/automatic/wiki) | [Discord](https://discord.com/invite/sd-next-federal-batch-inspectors-1101998836328697867) | [Sponsor](https://github.com/sponsors/vladmandic) -### Details for 2026-03-24 +### Details for 2026-03-25 - **Models** - [Google Flash 3.1 Image](https://ai.google.dev/gemini-api/docs/models/gemini-3-flash-preview) a.k.a. *Nano Banana 2* @@ -69,6 +69,9 @@ But also many smaller quality-of-life improvements - for full details, see [Chan - **Cuda** `torch==2.10` removed support for `rtx1000` series and older GPUs use following before first startup to force installation of `torch==2.9.1` with `cuda==12.6`: > `set TORCH_COMMAND='torch==2.9.1 torchvision==0.24.1 torchaudio==2.9.1 --index-url https://download.pytorch.org/whl/cu126'` + - **Ipex** update to `torch==2.11` + - **ROCm/Linux** update to `torch==2.11` with `rocm==7.2` + - **OpenVINO** update to `torch==2.11` and `openvino==2026.0` - **UI** - legacy panels **T2I** and **I2I** are disabled by default you can re-enable them in *settings -> ui -> hide legacy tabs* @@ -168,7 +171,9 @@ But also many smaller quality-of-life improvements - for full details, see [Chan - improve video generation progress tracking - handle startup with bad `scripts` more gracefully - thread-safety for `error-limiter`, thanks @awsr - - add `lora` support for flux2-klein + - add `lora` support for flux2-klein + - fix `lora` change when used with `sdnq` + - multiple `sdnq` fixes ## Update for 2026-02-04 diff --git a/TODO.md b/TODO.md index de3b0ef9f..3468c97f5 100644 --- a/TODO.md +++ b/TODO.md @@ -7,6 +7,7 @@ - Add notes: **Enso** - Tips: **Color Grading** - Regen: **Localization** +- AGENTS.md ## Internal @@ -20,6 +21,7 @@ - Engine: `TensorRT` acceleration - Feature: Auto handle scheduler `prediction_type` - Feature: Cache models in memory +- Feature: JSON image metadata - Validate: Control tab add overrides handling - Feature: Integrate natural language image search [ImageDB](https://github.com/vladmandic/imagedb) @@ -28,7 +30,6 @@ - Feature: Video tab add full API support - Refactor: Unify *huggingface* and *diffusers* model folders - Refactor: [GGUF](https://huggingface.co/docs/diffusers/main/en/quantization/gguf) -- Refactor: move sampler options from settings to config - Reimplement `llama` remover for Kanvas, pending end-to-end review of `Kanvas` ## OnHold @@ -55,6 +56,7 @@ TODO: Investigate which models are diffusers-compatible and prioritize! - [Chroma Zeta](https://huggingface.co/lodestones/Zeta-Chroma): Image and video generator for creative effects and professional filters - [Chroma Radiance](https://huggingface.co/lodestones/Chroma1-Radiance): Pixel-space model eliminating VAE artifacts for high visual fidelity +- [Bria FIBO](https://huggingface.co/briaai/FIBO): Fully JSON based - [Liquid](https://github.com/FoundationVision/Liquid): Unified vision-language auto-regressive generation paradigm - [Lumina-DiMOO](https://huggingface.co/Alpha-VLLM/Lumina-DiMOO): Foundational multi-modal generation and understanding via discrete diffusion - [nVidia Cosmos-Predict-2.5](https://huggingface.co/nvidia/Cosmos-Predict2.5-2B): Physics-aware world foundation model for consistent scene prediction @@ -113,8 +115,6 @@ TODO: Investigate which models are diffusers-compatible and prioritize! ### Not Planned -- [Bria FIBO](https://huggingface.co/briaai/FIBO): Fully JSON based -- [Bria FiboEdit](https://github.com/huggingface/diffusers/commit/d7a1c31f4f85bae5a9e01cdce49bd7346bd8ccd6): Fully JSON based - [LoRAdapter](https://github.com/CompVis/LoRAdapter): Not recently updated - [SD3 UltraEdit](https://github.com/HaozheZhao/UltraEdit): Based on SD3 - [PowerPaint](https://github.com/open-mmlab/PowerPaint): Based on SD15 diff --git a/extensions-builtin/sdnext-modernui b/extensions-builtin/sdnext-modernui index 9d584a1bd..e8374c5b5 160000 --- a/extensions-builtin/sdnext-modernui +++ b/extensions-builtin/sdnext-modernui @@ -1 +1 @@ -Subproject commit 9d584a1bdc0c2aca614aa0e1e34e4374c3aa779d +Subproject commit e8374c5b5e2b97961cf6ca9fa72a90b0dea479aa diff --git a/modules/image/metadata.py b/modules/image/metadata.py index d0d3e52e9..64ec08c40 100644 --- a/modules/image/metadata.py +++ b/modules/image/metadata.py @@ -1,4 +1,5 @@ import io +import os import re import json import piexif @@ -8,26 +9,24 @@ from modules.logger import log from modules.image.watermark import get_watermark +debug = log.trace if os.environ.get("SD_METADATA_DEBUG", None) is not None else lambda *args, **kwargs: None + + def safe_decode_string(s: bytes): - remove_prefix = lambda text, prefix: text[len(prefix):] if text.startswith(prefix) else text # pylint: disable=unnecessary-lambda-assignment + remove_prefix = lambda text, prefix: text[len(prefix):] if text.startswith(prefix) else text # pylint: disable=unnecessary-lambda-assignment s = remove_prefix(s, b'UNICODE') s = remove_prefix(s, b'ASCII') s = remove_prefix(s, b'\x00') - # Detect UTF-16LE: even length and every other byte (odd positions) is 0x00 in the first ~20 bytes - if len(s) >= 2 and len(s) % 2 == 0 and all(b == 0 for b in s[1:min(len(s), 20):2]): - try: - val = s.decode('utf-16-le', errors='strict') - val = re.sub(r'[\x00-\x09]', '', val).strip() - if val: - return val - except Exception: - pass - for encoding in ['utf-8', 'utf-16', 'utf-16-be', 'ascii', 'latin_1', 'cp1252', 'cp437']: # try different encodings + for encoding in ["utf-16-le", "utf-16-be", "utf-8", "utf-16", "ascii", "latin_1", "cp1252", "cp437"]: # try different encodings try: + if encoding == "utf-16-le": + if not (len(s) >= 2 and len(s) % 2 == 0 and all(b == 0 for b in s[1 : min(len(s), 20) : 2])): # not utf-16-le + continue val = s.decode(encoding, errors="strict") val = re.sub(r'[\x00-\x09]', '', val).strip() # remove remaining special characters if len(val) == 0: # remove empty strings val = None + debug(f'Metadata: decode="{val}" encoding="{encoding}"') return val except Exception: pass @@ -68,6 +67,7 @@ def parse_comfy_metadata(data: dict): if len(workflow) > 0 or len(prompt) > 0: parsed = f'App: ComfyUI{workflow}{prompt}' log.info(f'Image metadata: {parsed}') + debug(f'Metadata: comfy="{parsed}"') return parsed return '' @@ -90,6 +90,7 @@ def parse_invoke_metadata(data: dict): if len(metadata) > 0: parsed = f'App: InvokeAI{metadata}' log.info(f'Image metadata: {parsed}') + debug(f'Metadata: invoke="{parsed}"') return parsed return '' @@ -101,9 +102,25 @@ def parse_novelai_metadata(data: dict): dct = json.loads(data["Comment"]) sampler = sd_samplers.samplers_map.get(dct["sampler"], "Euler a") geninfo = f'{data["Description"]} Negative prompt: {dct["uc"]} Steps: {dct["steps"]}, Sampler: {sampler}, CFG scale: {dct["scale"]}, Seed: {dct["seed"]}, Clip skip: 2, ENSD: 31337' + debug(f'Metadata: novelai="{geninfo}"') + return geninfo except Exception: pass - return geninfo + return '' + + +def parse_xmp_metadata(data: dict): + # Extract XMP dc:subject tags into a readable field + geninfo = '' + xmp_raw = data.get("xmp") + if xmp_raw and isinstance(xmp_raw, (str, bytes)): + xmp_str = xmp_raw if isinstance(xmp_raw, str) else xmp_raw.decode("utf-8", errors="replace") + xmp_tags = re.findall(r"([^<]+)", xmp_str) + if xmp_tags: + geninfo = f"XMP Tags: {', '.join(xmp_tags)}" + debug(f'Metadata: xmp="{geninfo}"') + return geninfo + return '' def read_info_from_image(image: Image.Image, watermark: bool = False) -> tuple[str, dict]: @@ -131,6 +148,7 @@ def read_info_from_image(image: Image.Image, watermark: bool = False) -> tuple[s log.error(f'Error loading EXIF data: {e}') exif = {} for _key, subkey in exif.items(): + debug(f'Metadata EXIF: key="{_key}" subkey="{subkey}" type="{type(subkey)}"') if isinstance(subkey, dict): for key, val in subkey.items(): if isinstance(val, bytes): # decode bytestring @@ -145,27 +163,23 @@ def read_info_from_image(image: Image.Image, watermark: bool = False) -> tuple[s items[ExifTags.TAGS[key]] = val elif val is not None and key in ExifTags.GPSTAGS: items[ExifTags.GPSTAGS[key]] = val + if watermark: wm = get_watermark(image) if wm != '': + debug(f'Metadata: watermark="{wm}"') # geninfo += f' Watermark: {wm}' items['watermark'] = wm for key, val in items.items(): if isinstance(val, bytes): # decode bytestring items[key] = safe_decode_string(val) + debug(f'Metadata: key="{key}" value="{items[key]}"') geninfo += parse_comfy_metadata(items) geninfo += parse_invoke_metadata(items) geninfo += parse_novelai_metadata(items) - - # Extract XMP dc:subject tags into a readable field - xmp_raw = items.get('xmp') - if xmp_raw and isinstance(xmp_raw, (str, bytes)): - xmp_str = xmp_raw if isinstance(xmp_raw, str) else xmp_raw.decode('utf-8', errors='replace') - xmp_tags = re.findall(r'([^<]+)', xmp_str) - if xmp_tags: - items['xmp_tags'] = ', '.join(xmp_tags) + geninfo += parse_xmp_metadata(items) for key in ['exif', 'ExifOffset', 'JpegIFOffset', 'JpegIFByteCount', 'ExifVersion', 'icc_profile', 'jfif', 'jfif_version', 'jfif_unit', 'jfif_density', 'adobe', 'photoshop', 'loop', 'duration', 'dpi', 'xmp']: # remove unwanted tags items.pop(key, None) @@ -177,6 +191,8 @@ def read_info_from_image(image: Image.Image, watermark: bool = False) -> tuple[s except Exception: pass + debug(f'Metadata geninfoi: "{geninfo}"') + debug(f'Metadata items: "{items}"') return geninfo, items diff --git a/wiki b/wiki index 99f4e13d0..7abb07dc9 160000 --- a/wiki +++ b/wiki @@ -1 +1 @@ -Subproject commit 99f4e13d03191b5269b869c71283d7fcf9c98f60 +Subproject commit 7abb07dc95bdb2c1869e2901213f5c82b46905c3