Merge branch 'dev' into bundled-emb

.github/workflows/on_pull_request.yaml

@@ -7,6 +7,12 @@ on:
 jobs:
   lint:
     runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        flags:
+          - --debug --test --uv
+          - --debug --test
     steps:
       - name: checkout-code
         uses: actions/checkout@main
@@ -27,5 +33,5 @@ jobs:
           msg: apply code formatting and linting auto-fixes
       - name: test-startup
         run: |
-          export COMMANDLINE_ARGS="--debug --test"
+          export COMMANDLINE_ARGS="${{ matrix.flags }}"
           python launch.py

CHANGELOG.md

@@ -1,12 +1,21 @@
 # Change Log for SD.Next
 
-## Update for 2024-06-28
+TODO:
+- <https://github.com/huggingface/diffusers/issues/8771>
+- Requires `diffusers==0.30.0`
+- Alpha Lumina
 
+## Update for 2024-07-01
+
+- support for **HunyuanDiT 1.2**  
+- add support for [uv](https://pypi.org/project/uv/), extremely fast installer, thanks @Yoinky3000!  
+  to use, simply add `--uv` to your command line params  
 - enable `florence` VLM for all platforms, thanks @lshqqytiger!  
 - fix executing extensions with zero params  
 - fix nncf for lora, thanks @Disty0!
 - fix diffusers version detection for SD3
 - fix current step for higher order samplers
+- fix control input type video  
 - add SD3 with FP16 T5 to list of detected models
 - multiple ModernUI fixes
 

README.md

@@ -64,31 +64,31 @@ For screenshots and informations on other available themes, see [Themes Wiki](ht
 
 Additional models will be added as they become available and there is public interest in them
 
-- [RunwayML Stable Diffusion](https://github.com/Stability-AI/stablediffusion/) 1.x and 2.x *(all variants)*  
-- [StabilityAI Stable Diffusion XL](https://github.com/Stability-AI/generative-models)  
-- [StabilityAI Stable Diffusion 3 Medium](https://stability.ai/news/stable-diffusion-3-medium)  
+- [RunwayML Stable Diffusion](https://github.com/Stability-AI/stablediffusion/) 1.x and 2.x *(all variants)*
+- [StabilityAI Stable Diffusion XL](https://github.com/Stability-AI/generative-models)
+- [StabilityAI Stable Diffusion 3 Medium](https://stability.ai/news/stable-diffusion-3-medium)
 - [StabilityAI Stable Video Diffusion](https://huggingface.co/stabilityai/stable-video-diffusion-img2vid) Base, XT 1.0, XT 1.1
-- [LCM: Latent Consistency Models](https://github.com/openai/consistency_models)  
-- [Playground](https://huggingface.co/playgroundai/playground-v2-256px-base) *v1, v2 256, v2 512, v2 1024 and latest v2.5*  
+- [LCM: Latent Consistency Models](https://github.com/openai/consistency_models)
+- [Playground](https://huggingface.co/playgroundai/playground-v2-256px-base) *v1, v2 256, v2 512, v2 1024 and latest v2.5*
 - [Stable Cascade](https://github.com/Stability-AI/StableCascade) *Full* and *Lite*
 - [aMUSEd 256](https://huggingface.co/amused/amused-256) 256 and 512
-- [Segmind Vega](https://huggingface.co/segmind/Segmind-Vega)  
-- [Segmind SSD-1B](https://huggingface.co/segmind/SSD-1B)  
-- [Segmind SegMoE](https://github.com/segmind/segmoe) *SD and SD-XL*  
-- [Kandinsky](https://github.com/ai-forever/Kandinsky-2) *2.1 and 2.2 and latest 3.0*  
-- [PixArt-α XL 2](https://github.com/PixArt-alpha/PixArt-alpha) *Medium and Large*  
-- [PixArt-Σ](https://github.com/PixArt-alpha/PixArt-sigma)  
-- [Warp Wuerstchen](https://huggingface.co/blog/wuertschen)  
+- [Segmind Vega](https://huggingface.co/segmind/Segmind-Vega)
+- [Segmind SSD-1B](https://huggingface.co/segmind/SSD-1B)
+- [Segmind SegMoE](https://github.com/segmind/segmoe) *SD and SD-XL*
+- [Kandinsky](https://github.com/ai-forever/Kandinsky-2) *2.1 and 2.2 and latest 3.0*
+- [PixArt-α XL 2](https://github.com/PixArt-alpha/PixArt-alpha) *Medium and Large*
+- [PixArt-Σ](https://github.com/PixArt-alpha/PixArt-sigma)
+- [Warp Wuerstchen](https://huggingface.co/blog/wuertschen)
 - [Tenecent HunyuanDiT](https://github.com/Tencent/HunyuanDiT)
 - [Tsinghua UniDiffusion](https://github.com/thu-ml/unidiffuser)
 - [DeepFloyd IF](https://github.com/deep-floyd/IF) *Medium and Large*
 - [ModelScope T2V](https://huggingface.co/damo-vilab/text-to-video-ms-1.7b)
 - [Segmind SD Distilled](https://huggingface.co/blog/sd_distillation) *(all variants)*
-- [BLIP-Diffusion](https://dxli94.github.io/BLIP-Diffusion-website/)  
+- [BLIP-Diffusion](https://dxli94.github.io/BLIP-Diffusion-website/)
 - [KOALA 700M](https://github.com/youngwanLEE/sdxl-koala)
-- [VGen](https://huggingface.co/ali-vilab/i2vgen-xl)  
+- [VGen](https://huggingface.co/ali-vilab/i2vgen-xl)
 - [SDXS](https://github.com/IDKiro/sdxs)
-- [Hyper-SD](https://huggingface.co/ByteDance/Hyper-SD) 
+- [Hyper-SD](https://huggingface.co/ByteDance/Hyper-SD)
 
 
 Also supported are modifiers such as:
@@ -226,6 +226,7 @@ List of available parameters, run `webui --help` for the full & up-to-date list:
       --version                                          Print version information
       --ignore                                           Ignore any errors and attempt to continue
       --safe                                             Run in safe mode with no user extensions
+      --uv                                               Use uv as installer, default: False
 
     Logging options:
       --log LOG                                          Set log file, default: None

TODO.md

@@ -11,7 +11,6 @@ Main ToDo list can be found at [GitHub projects](https://github.com/users/vladma
 - diffusers public callbacks  
 - include reference styles
 - lora: sc lora, dora, etc
-- sd3 controlnet: <https://github.com/huggingface/diffusers/pull/8566>
 
 ## Experimental
 

html/reference.json

@@ -182,13 +182,20 @@
     "extras": "width: 1024, height: 1024, sampler: Default, cfg_scale: 2.0"
   },
 
-  "Tencent HunyuanDiT 1.1": {
-    "path": "Tencent-Hunyuan/HunyuanDiT-v1.1-Diffusers",
+  "Tencent HunyuanDiT 1.2": {
+    "path": "Tencent-Hunyuan/HunyuanDiT-v1.2-Diffusers",
     "desc": "Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding.",
     "preview": "Tencent-Hunyuan-HunyuanDiT.jpg",
     "extras": "width: 1024, height: 1024, sampler: Default, cfg_scale: 2.0"
   },
-
+
+  "AlphaVLLM Lumina Next SFT": {
+    "path": "Alpha-VLLM/Lumina-Next-SFT-diffusers",
+    "desc": "The Lumina-Next-SFT is a Next-DiT model containing 2B parameters and utilizes Gemma-2B as the text encoder, enhanced through high-quality supervised fine-tuning (SFT).",
+    "preview": "Alpha-VLLM-Lumina-Next-SFT-diffusers.jpg",
+    "extras": "width: 1024, height: 1024, sampler: Default, cfg_scale: 2.0"
+  }, 
+
   "Kandinsky 2.1": {
     "path": "kandinsky-community/kandinsky-2-1",
     "desc": "Kandinsky 2.1 is a text-conditional diffusion model based on unCLIP and latent diffusion, composed of a transformer-based image prior model, a unet diffusion model, and a decoder. Kandinsky 2.1 inherits best practices from Dall-E 2 and Latent diffusion while introducing some new ideas. It uses the CLIP model as a text and image encoder, and diffusion image prior (mapping) between latent spaces of CLIP modalities. This approach increases the visual performance of the model and unveils new horizons in blending images and text-guided image manipulation.",

installer.py

@@ -52,6 +52,7 @@ class Dot(dict): # dot notation access to dictionary attributes
     'reinstall': False,
     'version': False,
     'ignore': False,
+    'uv': False,
 })
 git_commit = "unknown"
 submodules_commit = {
@@ -235,22 +236,25 @@ def uninstall(package, quiet = False):
 
 
 @lru_cache()
-def pip(arg: str, ignore: bool = False, quiet: bool = False):
+def pip(arg: str, ignore: bool = False, quiet: bool = False, uv = True):
+    uv = uv and args.uv
+    pipCmd = "uv pip" if uv else "pip"
     arg = arg.replace('>=', '==')
     if not quiet and '-r ' not in arg:
-        log.info(f'Install: package="{arg.replace("install", "").replace("--upgrade", "").replace("--no-deps", "").replace("--force", "").replace("  ", " ").strip()}"')
+        log.info(f'Install: package="{arg.replace("install", "").replace("--upgrade", "").replace("--no-deps", "").replace("--force", "").replace(" ", " ").strip()}" mode={"uv" if uv else "pip"}')
     env_args = os.environ.get("PIP_EXTRA_ARGS", "")
-    log.debug(f'Running: pip="{pip_log}{arg} {env_args}"')
-    result = subprocess.run(f'"{sys.executable}" -m pip {pip_log}{arg} {env_args}', shell=True, check=False, env=os.environ, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+    all_args = f'{pip_log}{arg} {env_args}'.strip()
+    log.debug(f'Running: {pipCmd}="{all_args}"')
+    result = subprocess.run(f'"{sys.executable}" -m {pipCmd} {all_args}', shell=True, check=False, env=os.environ, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
     txt = result.stdout.decode(encoding="utf8", errors="ignore")
     if len(result.stderr) > 0:
         txt += ('\n' if len(txt) > 0 else '') + result.stderr.decode(encoding="utf8", errors="ignore")
     txt = txt.strip()
-    debug(f'Install pip: {txt}')
+    debug(f'Install {pipCmd}: {txt}')
     if result.returncode != 0 and not ignore:
         global errors # pylint: disable=global-statement
         errors += 1
-        log.error(f'Error running pip: {arg}')
+        log.error(f'Error running {pipCmd}: {arg}')
         log.debug(f'Pip output: {txt}')
     return txt
 
@@ -264,7 +268,7 @@ def install(package, friendly: str = None, ignore: bool = False, reinstall: bool
         quick_allowed = False
     if args.reinstall or reinstall or not installed(package, friendly, quiet=quiet):
         deps = '' if not no_deps else '--no-deps '
-        res = pip(f"install --upgrade {deps}{package}", ignore=ignore)
+        res = pip(f"install{' --upgrade' if not args.uv else ''} {deps}{package}", ignore=ignore, uv=package != "uv")
         try:
             import imp # pylint: disable=deprecated-module
             imp.reload(pkg_resources)
@@ -1223,6 +1227,7 @@ def add_args(parser):
     group.add_argument('--version', default = False, action='store_true', help = "Print version information")
     group.add_argument('--ignore', default = os.environ.get("SD_IGNORE",False), action='store_true', help = "Ignore any errors and attempt to continue")
     group.add_argument('--safe', default = os.environ.get("SD_SAFE",False), action='store_true', help = "Run in safe mode with no user extensions")
+    group.add_argument('--uv', default = os.environ.get("SD_UV",False), action='store_true', help = "Use uv instead of pip to install the packages")
 
     group = parser.add_argument_group('Logging options')
     group.add_argument("--log", type=str, default=os.environ.get("SD_LOG", None), help="Set log file, default: %(default)s")

launch.py

@@ -204,6 +204,8 @@ def main():
     installer.log.info(f'Platform: {installer.print_dict(installer.get_platform())}')
     if not args.skip_env:
         installer.set_environment()
+    if args.uv:
+        installer.install("uv", "uv")
     installer.check_torch()
     installer.check_onnx()
     installer.check_diffusers()