Last PR needed for v2.3.1 (#2788)

- Add curated set of starter models based on team discussion. The final
list of starter models can be found in
`invokeai/configs/INITIAL_MODELS.yaml`

- To test model installation, I selected and installed all the models on
the list. This led to my discovering that when there are no more starter
models to display, the console front end crashes. So I made a fix to
this in which the entire starter model selection is no longer shown.

- Update model table in 050_INSTALL_MODELS.md

- Add guide to dealing with low-memory situations
- Version is now `v2.3.1`

.github/workflows/pypi-release.yml

@@ -28,7 +28,7 @@ jobs:
         run: twine check dist/*
 
       - name: check PyPI versions
-        if: github.ref == 'refs/heads/main'
+        if: github.ref == 'refs/heads/main' || github.ref == 'refs/heads/v2.3'
         run: |
           pip install --upgrade requests
           python -c "\

docs/installation/010_INSTALL_AUTOMATED.md

@@ -221,7 +221,10 @@ experimental versions later.
 
     - ***NSFW checker***
       If checked, InvokeAI will test images for potential sexual content
-      and blur them out if found.
+      and blur them out if found. Note that the NSFW checker consumes
+      an additional 0.6 GB of VRAM on top of the 2-3 GB of VRAM used
+      by most image models. If you have a low VRAM GPU (4-6 GB), you
+      can reduce out of memory errors by disabling the checker.
 
     - ***HuggingFace Access Token***
       InvokeAI has the ability to download embedded styles and subjects
@@ -440,6 +443,52 @@ the [InvokeAI Issues](https://github.com/invoke-ai/InvokeAI/issues) section, or
 visit our [Discord Server](https://discord.gg/ZmtBAhwWhy) for interactive
 assistance.
 
+### Out of Memory Issues
+
+The models are large, VRAM is expensive, and you may find yourself
+faced with Out of Memory errors when generating images. Here are some
+tips to reduce the problem:
+
+* **4 GB of VRAM**
+
+This should be adequate for 512x512 pixel images using Stable Diffusion 1.5
+and derived models, provided that you **disable** the NSFW checker. To
+disable the filter, do one of the following:
+
+   * Select option (6) "_change InvokeAI startup options_" from the
+     launcher. This will bring up the console-based startup settings
+     dialogue and allow you to unselect the "NSFW Checker" option.
+   * Start the startup settings dialogue directly by running
+     `invokeai-configure --skip-sd-weights --skip-support-models`
+     from the command line.
+   * Find the `invokeai.init` initialization file in the InvokeAI root
+     directory, open it in a text editor, and change `--nsfw_checker`
+     to `--no-nsfw_checker`
+
+If you are on a CUDA system, you can realize significant memory
+savings by activating the `xformers` library as described above. The
+downside is `xformers` introduces non-deterministic behavior, such
+that images generated with exactly the same prompt and settings will
+be slightly different from each other. See above for more information.
+
+* **6 GB of VRAM**
+
+This is a border case. Using the SD 1.5 series you should be able to
+generate images up to 640x640 with the NSFW checker enabled, and up to
+1024x1024 with it disabled and `xformers` activated. 
+
+If you run into persistent memory issues there are a series of
+environment variables that you can set before launching InvokeAI that
+alter how the PyTorch machine learning library manages memory.  See
+https://pytorch.org/docs/stable/notes/cuda.html#memory-management for
+a list of these tweaks.
+
+* **12 GB of VRAM**
+
+This should be sufficient to generate larger images up to about
+1280x1280. If you wish to push further, consider activating
+`xformers`.
+
 ### Other Problems
 
 If you run into problems during or after installation, the InvokeAI team is

docs/installation/050_INSTALLING_MODELS.md

@@ -43,25 +43,31 @@ InvokeAI comes with support for a good set of starter models. You'll
 find them listed in the master models file
 `configs/INITIAL_MODELS.yaml` in the InvokeAI root directory. The
 subset that are currently installed are found in
-`configs/models.yaml`. The current list is:
+`configs/models.yaml`. As of v2.3.1, the list of starter models is:
 
-| Model                | HuggingFace Repo ID               | Description                                                | URL
-| -------------------- | --------------------------------- | ---------------------------------------------------------- | -------------------------------------------------------------- |
-| stable-diffusion-1.5 | runwayml/stable-diffusion-v1-5    | Most recent version of base Stable Diffusion model         | https://huggingface.co/runwayml/stable-diffusion-v1-5          |
-| stable-diffusion-1.4 | runwayml/stable-diffusion-v1-4    | Previous version of base Stable Diffusion model         | https://huggingface.co/runwayml/stable-diffusion-v1-4          |
-| inpainting-1.5       | runwayml/stable-diffusion-inpainting  | Stable diffusion 1.5 optimized for inpainting          | https://huggingface.co/runwayml/stable-diffusion-inpainting    |
-| stable-diffusion-2.1-base |stabilityai/stable-diffusion-2-1-base | Stable Diffusion version 2.1 trained on 512 pixel images | https://huggingface.co/stabilityai/stable-diffusion-2-1-base |
-| stable-diffusion-2.1-768 |stabilityai/stable-diffusion-2-1 | Stable Diffusion version 2.1 trained on 768 pixel images | https://huggingface.co/stabilityai/stable-diffusion-2-1        |
-| dreamlike-diffusion-1.0  | dreamlike-art/dreamlike-diffusion-1.0  | An SD 1.5 model finetuned on high quality art    | https://huggingface.co/dreamlike-art/dreamlike-diffusion-1.0   |
-| dreamlike-photoreal-2.0  | dreamlike-art/dreamlike-photoreal-2.0  | A photorealistic model trained on 768 pixel images| https://huggingface.co/dreamlike-art/dreamlike-photoreal-2.0   |
-| openjourney-4.0      | prompthero/openjourney              | An SD 1.5 model finetuned on Midjourney images prompt with "mdjrny-v4 style"   | https://huggingface.co/prompthero/openjourney  |
-| nitro-diffusion-1.0  | nitrosocke/Nitro-Diffusion          | An SD 1.5 model finetuned on three styles, prompt with "archer style", "arcane style" or "modern disney style" | https://huggingface.co/nitrosocke/Nitro-Diffusion|
-| trinart-2.0          | naclbit/trinart_stable_diffusion_v2 | An SD 1.5 model finetuned with ~40,000 assorted high resolution manga/anime-style pictures | https://huggingface.co/naclbit/trinart_stable_diffusion_v2|
-| trinart-characters-2_0 | naclbit/trinart_derrida_characters_v2_stable_diffusion | An SD 1.5 model finetuned with 19.2M manga/anime-style pictures | https://huggingface.co/naclbit/trinart_derrida_characters_v2_stable_diffusion|
+|Model Name | HuggingFace Repo ID | Description | URL |
+|---------- | ---------- | ----------- | --- |
+|stable-diffusion-1.5|runwayml/stable-diffusion-v1-5|Stable Diffusion version 1.5 diffusers model (4.27 GB)|https://huggingface.co/runwayml/stable-diffusion-v1-5 |
+|sd-inpainting-1.5|runwayml/stable-diffusion-inpainting|RunwayML SD 1.5 model optimized for inpainting, diffusers version (4.27 GB)|https://huggingface.co/runwayml/stable-diffusion-inpainting |
+|stable-diffusion-2.1|stabilityai/stable-diffusion-2-1|Stable Diffusion version 2.1 diffusers model, trained on 768 pixel images (5.21 GB)|https://huggingface.co/stabilityai/stable-diffusion-2-1 |
+|sd-inpainting-2.0|stabilityai/stable-diffusion-2-1|Stable Diffusion version 2.0 inpainting model (5.21 GB)|https://huggingface.co/stabilityai/stable-diffusion-2-1 |
+|analog-diffusion-1.0|wavymulder/Analog-Diffusion|An SD-1.5 model trained on diverse analog photographs (2.13 GB)|https://huggingface.co/wavymulder/Analog-Diffusion |
+|deliberate-1.0|XpucT/Deliberate|Versatile model that produces detailed images up to 768px (4.27 GB)|https://huggingface.co/XpucT/Deliberate |
+|d&d-diffusion-1.0|0xJustin/Dungeons-and-Diffusion|Dungeons & Dragons characters (2.13 GB)|https://huggingface.co/0xJustin/Dungeons-and-Diffusion |
+|dreamlike-photoreal-2.0|dreamlike-art/dreamlike-photoreal-2.0|A photorealistic model trained on 768 pixel images based on SD 1.5 (2.13 GB)|https://huggingface.co/dreamlike-art/dreamlike-photoreal-2.0 |
+|inkpunk-1.0|Envvi/Inkpunk-Diffusion|Stylized illustrations inspired by Gorillaz, FLCL and Shinkawa; prompt with "nvinkpunk" (4.27 GB)|https://huggingface.co/Envvi/Inkpunk-Diffusion |
+|openjourney-4.0|prompthero/openjourney|An SD 1.5 model fine tuned on Midjourney; prompt with "mdjrny-v4 style" (2.13 GB)|https://huggingface.co/prompthero/openjourney |
+|portrait-plus-1.0|wavymulder/portraitplus|An SD-1.5 model trained on close range portraits of people; prompt with "portrait+" (2.13 GB)|https://huggingface.co/wavymulder/portraitplus |
+|seek-art-mega-1.0|coreco/seek.art_MEGA|A general use SD-1.5 "anything" model that supports multiple styles (2.1 GB)|https://huggingface.co/coreco/seek.art_MEGA |
+|trinart-2.0|naclbit/trinart_stable_diffusion_v2|An SD-1.5 model finetuned with ~40K assorted high resolution manga/anime-style images (2.13 GB)|https://huggingface.co/naclbit/trinart_stable_diffusion_v2 |
+|waifu-diffusion-1.4|hakurei/waifu-diffusion|An SD-1.5 model trained on 680k anime/manga-style images (2.13 GB)|https://huggingface.co/hakurei/waifu-diffusion |
 
-Note that these files are covered by an "Ethical AI" license which forbids
-certain uses. When you initially download them, you are asked to
-accept the license terms.
+Note that these files are covered by an "Ethical AI" license which
+forbids certain uses. When you initially download them, you are asked
+to accept the license terms. In addition, some of these models carry
+additional license terms that limit their use in commercial
+applications or on public servers. Be sure to familiarize yourself
+with the model terms by visiting the URLs in the table above.
 
 ## Community-Contributed Models
 

installer/create_installer.sh

@@ -20,10 +20,9 @@ echo Building installer for version $VERSION
 echo "Be certain that you're in the 'installer' directory before continuing."
 read -p "Press any key to continue, or CTRL-C to exit..."
 
-read -e -p "Commit and tag this repo with '${VERSION}' and '${LATEST_TAG}'? [n]: " input
+read -e -p "Tag this repo with '${VERSION}' and '${LATEST_TAG}'? [n]: " input
 RESPONSE=${input:='n'}
 if [ "$RESPONSE" == 'y' ]; then
-    git commit -a
 
     if ! git tag $VERSION ; then
 	    echo "Existing/invalid tag"
@@ -32,6 +31,8 @@ if [ "$RESPONSE" == 'y' ]; then
 
     git push origin :refs/tags/$LATEST_TAG
     git tag -fa $LATEST_TAG
+
+    echo "remember to push --tags!"
 fi
 
 # ----------------------

invokeai/configs/INITIAL_MODELS.yaml

@@ -6,53 +6,78 @@ stable-diffusion-1.5:
      repo_id: stabilityai/sd-vae-ft-mse
    recommended: True
    default: True
-inpainting-1.5:
+sd-inpainting-1.5:
   description: RunwayML SD 1.5 model optimized for inpainting, diffusers version (4.27 GB)
   repo_id: runwayml/stable-diffusion-inpainting
   format: diffusers
   vae:
     repo_id: stabilityai/sd-vae-ft-mse
   recommended: True
-dreamlike-diffusion-1.0:
-  description: An SD 1.5 model fine tuned on high quality art by dreamlike.art, diffusers version (2.13 BG)
-  format: diffusers
-  repo_id: dreamlike-art/dreamlike-diffusion-1.0
-  vae:
-     repo_id: stabilityai/sd-vae-ft-mse
-  recommended: True
-dreamlike-photoreal-2.0:
-  description: A photorealistic model trained on 768 pixel images based on SD 1.5 (2.13 GB)
-  format: diffusers
-  repo_id: dreamlike-art/dreamlike-photoreal-2.0
-  recommended: False
-stable-diffusion-2.1-768:
+stable-diffusion-2.1:
    description: Stable Diffusion version 2.1 diffusers model, trained on 768 pixel images (5.21 GB)
    repo_id: stabilityai/stable-diffusion-2-1
    format: diffusers
    recommended: True
-stable-diffusion-2.1-base:
-   description: Stable Diffusion version 2.1 diffusers base model, trained on 512 pixel images (5.21 GB)
-   repo_id: stabilityai/stable-diffusion-2-1-base
+sd-inpainting-2.0:
+   description: Stable Diffusion version 2.0 inpainting model (5.21 GB)
+   repo_id: stabilityai/stable-diffusion-2-1
    format: diffusers
    recommended: False
+analog-diffusion-1.0:
+   description: An SD-1.5 model trained on diverse analog photographs (2.13 GB)
+   repo_id: wavymulder/Analog-Diffusion
+   format: diffusers
+   recommended: false
+deliberate-1.0:
+   description: Versatile model that produces detailed images up to 768px (4.27 GB)
+   format: diffusers
+   repo_id: XpucT/Deliberate
+   recommended: False
+d&d-diffusion-1.0:
+   description: Dungeons & Dragons characters (2.13 GB)
+   format: diffusers
+   repo_id: 0xJustin/Dungeons-and-Diffusion
+   recommended: False
+dreamlike-photoreal-2.0:
+   description: A photorealistic model trained on 768 pixel images based on SD 1.5 (2.13 GB)
+   format: diffusers
+   repo_id: dreamlike-art/dreamlike-photoreal-2.0
+   recommended: False
+inkpunk-1.0:
+   description: Stylized illustrations inspired by Gorillaz, FLCL and Shinkawa; prompt with "nvinkpunk" (4.27 GB)
+   format: diffusers
+   repo_id: Envvi/Inkpunk-Diffusion
+   recommended: False
 openjourney-4.0:
-  description: An SD 1.5 model fine tuned on Midjourney images by PromptHero - include "mdjrny-v4 style" in your prompts (2.13 GB)
-  format: diffusers
-  repo_id: prompthero/openjourney
-  vae:
+   description: An SD 1.5 model fine tuned on Midjourney; prompt with "mdjrny-v4 style" (2.13 GB)
+   format: diffusers
+   repo_id: prompthero/openjourney
+   vae:
      repo_id: stabilityai/sd-vae-ft-mse
-  recommended: False
-nitro-diffusion-1.0:
-   description: A SD 1.5 model trained on three artstyles - prompt with "archer style", "arcane style" and/or "modern disney style" (2.13 GB)
-   repo_id: nitrosocke/Nitro-Diffusion
+   recommended: False
+portrait-plus-1.0:
+   description: An SD-1.5 model trained on close range portraits of people; prompt with "portrait+" (2.13 GB)
+   format: diffusers
+   repo_id: wavymulder/portraitplus
+   recommended: False
+seek-art-mega-1.0:
+   description: A general use SD-1.5 "anything" model that supports multiple styles (2.1 GB)
+   repo_id: coreco/seek.art_MEGA
    format: diffusers
    vae:
      repo_id: stabilityai/sd-vae-ft-mse
    recommended: False
 trinart-2.0:
-   description: An SD model finetuned with ~40,000 assorted high resolution manga/anime-style pictures, diffusers version (2.13 GB)
+   description: An SD-1.5 model finetuned with ~40K assorted high resolution manga/anime-style images (2.13 GB)
    repo_id: naclbit/trinart_stable_diffusion_v2
    format: diffusers
    vae:
      repo_id: stabilityai/sd-vae-ft-mse
    recommended: False
+waifu-diffusion-1.4:
+   description: An SD-1.5 model trained on 680k anime/manga-style images (2.13 GB)
+   repo_id: hakurei/waifu-diffusion
+   format: diffusers
+   vae:
+     repo_id: stabilityai/sd-vae-ft-mse
+   recommended: False

ldm/generate.py

@@ -650,6 +650,8 @@ class Generate:
     def clear_cuda_cache(self):
         if self._has_cuda():
             self.gather_cuda_stats()
+            # Run garbage collection prior to emptying the CUDA cache
+            gc.collect()
             torch.cuda.empty_cache()
 
     def clear_cuda_stats(self):

ldm/invoke/CLI.py

@@ -625,7 +625,7 @@ def set_default_output_dir(opt: Args, completer: Completer):
     completer.set_default_dir(opt.outdir)
 
 
-def import_model(model_path: str, gen, opt, completer, convert=False) -> str:
+def import_model(model_path: str, gen, opt, completer, convert=False):
     """
     model_path can be (1) a URL to a .ckpt file; (2) a local .ckpt file path;
     (3) a huggingface repository id; or (4) a local directory containing a
@@ -679,7 +679,7 @@ def _verify_load(model_name: str, gen) -> bool:
     current_model = gen.model_name
     try:
         if not gen.set_model(model_name):
-            return False
+            return
     except Exception as e:
         print(f"** model failed to load: {str(e)}")
         print(
@@ -706,7 +706,7 @@ def _get_model_name_and_desc(
     )
     return model_name, model_description
 
-def convert_model(model_name_or_path: Union[Path, str], gen, opt, completer) -> str:
+def convert_model(model_name_or_path: Union[Path, str], gen, opt, completer):
     model_name_or_path = model_name_or_path.replace("\\", "/")  # windows
     manager = gen.model_manager
     ckpt_path = None
@@ -740,19 +740,14 @@ def convert_model(model_name_or_path: Union[Path, str], gen, opt, completer) ->
         )
     else:
         try:
-            model_name = import_model(model_name_or_path, gen, opt, completer, convert=True)
+            import_model(model_name_or_path, gen, opt, completer, convert=True)
         except KeyboardInterrupt:
             return
 
-    if not model_name:
-        print("** Conversion failed. Aborting.")
-        return
-
     manager.commit(opt.conf)    
     if click.confirm(f"Delete the original .ckpt file at {ckpt_path}?", default=False):
         ckpt_path.unlink(missing_ok=True)
         print(f"{ckpt_path} deleted")
-    return model_name
 
 
 def del_config(model_name: str, gen, opt, completer):

ldm/invoke/_version.py

@@ -1 +1 @@
-__version__='2.3.1+rc2'
+__version__='2.3.1'

ldm/invoke/ckpt_to_diffuser.py

@@ -17,16 +17,15 @@
 # Original file at: https://github.com/huggingface/diffusers/blob/main/scripts/convert_ldm_original_checkpoint_to_diffusers.py
 """ Conversion script for the LDM checkpoints. """
 
-import os
 import re
 import torch
 import warnings
 from pathlib import Path
 from ldm.invoke.globals import (
-    Globals,
     global_cache_dir,
     global_config_dir,
     )
+from ldm.invoke.model_manager import ModelManager, SDLegacyType
 from safetensors.torch import load_file
 from typing import Union
 
@@ -760,7 +759,12 @@ def convert_open_clip_checkpoint(checkpoint):
 
     text_model_dict = {}
 
-    d_model = int(checkpoint["cond_stage_model.model.text_projection"].shape[0])
+    if 'cond_stage_model.model.text_projection' in keys:
+        d_model = int(checkpoint["cond_stage_model.model.text_projection"].shape[0])
+    elif 'cond_stage_model.model.ln_final.bias' in keys:
+        d_model = int(checkpoint['cond_stage_model.model.ln_final.bias'].shape[0])
+    else:
+        raise KeyError('Expected key "cond_stage_model.model.text_projection" not found in model')
 
     text_model_dict["text_model.embeddings.position_ids"] = text_model.text_model.embeddings.get_buffer("position_ids")
 
@@ -856,20 +860,23 @@ def load_pipeline_from_original_stable_diffusion_ckpt(
 
         upcast_attention = False
         if original_config_file is None:
-            key_name = "model.diffusion_model.input_blocks.2.1.transformer_blocks.0.attn2.to_k.weight"
-
-            if key_name in checkpoint and checkpoint[key_name].shape[-1] == 1024:
+            model_type = ModelManager.probe_model_type(checkpoint)
+            
+            if model_type == SDLegacyType.V2:
                 original_config_file = global_config_dir() / 'stable-diffusion' / 'v2-inference-v.yaml'
-
                 if global_step == 110000:
                     # v2.1 needs to upcast attention
                     upcast_attention = True
-            elif str(checkpoint_path).lower().find('inpaint') >= 0: # brittle - please pass original_config_file parameter!
-                print(f'  | checkpoint has "inpaint" in name, assuming an inpainting model')
+                    
+            elif model_type == SDLegacyType.V1_INPAINT:
                 original_config_file = global_config_dir() / 'stable-diffusion' / 'v1-inpainting-inference.yaml'
-            else:
+                
+            elif model_type == SDLegacyType.V1:
                 original_config_file = global_config_dir() / 'stable-diffusion' / 'v1-inference.yaml'
 
+            else:
+                raise Exception('Unknown checkpoint type')
+
         original_config = OmegaConf.load(original_config_file)
 
         if num_in_channels is not None:
@@ -960,7 +967,7 @@ def load_pipeline_from_original_stable_diffusion_ckpt(
             text_model = convert_open_clip_checkpoint(checkpoint)
             tokenizer = CLIPTokenizer.from_pretrained("stabilityai/stable-diffusion-2",
                                                       subfolder="tokenizer",
-                                                      cache_dir=global_cache_dir('diffusers')
+                                                      cache_dir=cache_dir,
                                                       )
             pipe = pipeline_class(
                 vae=vae,

ldm/invoke/config/invokeai_configure.py

@@ -191,14 +191,18 @@ def download_bert():
 
 
 # ---------------------------------------------
-def download_clip():
-    print("Installing CLIP model...", file=sys.stderr)
+def download_sd1_clip():
+    print("Installing SD1 clip model...", file=sys.stderr)
     version = "openai/clip-vit-large-patch14"
-    print("Tokenizer...", file=sys.stderr)
     download_from_hf(CLIPTokenizer, version)
-    print("Text model...", file=sys.stderr)
     download_from_hf(CLIPTextModel, version)
 
+# ---------------------------------------------
+def download_sd2_clip():
+    version = 'stabilityai/stable-diffusion-2'
+    print("Installing SD2 clip model...", file=sys.stderr)
+    download_from_hf(CLIPTokenizer, version, subfolder='tokenizer')
+    download_from_hf(CLIPTextModel, version, subfolder='text_encoder')
 
 # ---------------------------------------------
 def download_realesrgan():
@@ -832,7 +836,8 @@ def main():
         else:
             print("\n** DOWNLOADING SUPPORT MODELS **")
             download_bert()
-            download_clip()
+            download_sd1_clip()
+            download_sd2_clip()
             download_realesrgan()
             download_gfpgan()
             download_codeformer()

ldm/invoke/config/invokeai_update.py

@@ -2,18 +2,16 @@
 Minimalist updater script. Prompts user for the tag or branch to update to and runs
 pip install <path_to_git_source>.
 '''
-
+import os
 import platform
 import requests
-import subprocess
 from rich import box, print
-from rich.console import Console, group
+from rich.console import Console, Group, group
 from rich.panel import Panel
 from rich.prompt import Prompt
 from rich.style import Style
+from rich.syntax import Syntax
 from rich.text import Text
-from rich.live import Live
-from rich.table import Table
 
 from ldm.invoke import __version__
 
@@ -23,19 +21,17 @@ INVOKE_AI_REL="https://api.github.com/repos/invoke-ai/InvokeAI/releases"
 OS = platform.uname().system
 ARCH = platform.uname().machine
 
-ORANGE_ON_DARK_GREY = Style(bgcolor="grey23", color="orange1")
-
 if OS == "Windows":
     # Windows terminals look better without a background colour
     console = Console(style=Style(color="grey74"))
 else:
-    console = Console(style=Style(color="grey74", bgcolor="grey23"))
+    console = Console(style=Style(color="grey74", bgcolor="grey19"))
 
 def get_versions()->dict:
     return requests.get(url=INVOKE_AI_REL).json()
 
 def welcome(versions: dict):
-
+    
     @group()
     def text():
         yield f'InvokeAI Version: [bold yellow]{__version__}'
@@ -48,55 +44,45 @@ def welcome(versions: dict):
 [3] Manually enter the tag or branch name you wish to update'''
 
     console.rule()
-    console.print(
+    print(
         Panel(
             title="[bold wheat1]InvokeAI Updater",
             renderable=text(),
             box=box.DOUBLE,
             expand=True,
             padding=(1, 2),
-            style=ORANGE_ON_DARK_GREY,
+            style=Style(bgcolor="grey23", color="orange1"),
             subtitle=f"[bold grey39]{OS}-{ARCH}",
         )
     )
-    # console.rule is used instead of console.line to maintain dark background
-    # on terminals where light background is the default
-    console.rule(characters=" ")
+    console.line()
 
 def main():
     versions = get_versions()
     welcome(versions)
 
     tag = None
-    choice = Prompt.ask(Text.from_markup(('[grey74 on grey23]Choice:')),choices=['1','2','3'],default='1')
-
+    choice = Prompt.ask('Choice:',choices=['1','2','3'],default='1')
+    
     if choice=='1':
         tag = versions[0]['tag_name']
     elif choice=='2':
         tag = 'main'
     elif choice=='3':
-        tag = Prompt.ask('[grey74 on grey23]Enter an InvokeAI tag or branch name')
-
-    console.print(Panel(f':crossed_fingers: Upgrading to [yellow]{tag}[/yellow]', box=box.MINIMAL, style=ORANGE_ON_DARK_GREY))
+        tag = Prompt.ask('Enter an InvokeAI tag or branch name')
 
+    print(f':crossed_fingers: Upgrading to [yellow]{tag}[/yellow]')
     cmd = f'pip install {INVOKE_AI_SRC}/{tag}.zip --use-pep517'
-
-    progress = Table.grid(expand=True)
-    progress_panel = Panel(progress, box=box.MINIMAL, style=ORANGE_ON_DARK_GREY)
-
-    with subprocess.Popen(['bash', '-c', cmd], stdout=subprocess.PIPE, stderr=subprocess.PIPE) as proc:
-        progress.add_column()
-        with Live(progress_panel, console=console, vertical_overflow='visible'):
-            while proc.poll() is None:
-                for l in iter(proc.stdout.readline, b''):
-                    progress.add_row(l.decode().strip(), style=ORANGE_ON_DARK_GREY)
-        if proc.returncode == 0:
-            console.rule(f':heavy_check_mark: Upgrade successful')
-        else:
-            console.rule(f':exclamation: [bold red]Upgrade failed[/red bold]')
-
+    print('')
+    print('')
+    if os.system(cmd)==0:
+        print(f':heavy_check_mark: Upgrade successful')
+    else:
+        print(f':exclamation: [bold red]Upgrade failed[/red bold]')
+    
 if __name__ == "__main__":
     try:
         main()
     except KeyboardInterrupt:
         pass
+

ldm/invoke/config/model_install.py

@@ -114,37 +114,37 @@ class addModelsForm(npyscreen.FormMultiPage):
                 relx=4,
             )
         self.nextrely += 1
-        self.add_widget_intelligent(
-            CenteredTitleText,
-            name="== STARTER MODELS (recommended ones selected) ==",
-            editable=False,
-            color="CONTROL",
-        )
-        self.nextrely -= 1
-        self.add_widget_intelligent(
-            CenteredTitleText,
-            name="Select from a starter set of Stable Diffusion models from HuggingFace:",
-            editable=False,
-            labelColor="CAUTION",
-        )
-
-        self.nextrely -= 1
-        # if user has already installed some initial models, then don't patronize them
-        # by showing more recommendations
-        show_recommended = not self.existing_models
-        self.models_selected = self.add_widget_intelligent(
-            npyscreen.MultiSelect,
-            name="Install Starter Models",
-            values=starter_model_labels,
-            value=[
-                self.starter_model_list.index(x)
-                for x in self.starter_model_list
-                if show_recommended and x in recommended_models
-            ],
-            max_height=len(starter_model_labels) + 1,
-            relx=4,
-            scroll_exit=True,
-        )
+        if len(self.starter_model_list) > 0:
+            self.add_widget_intelligent(
+                CenteredTitleText,
+                name="== STARTER MODELS (recommended ones selected) ==",
+                editable=False,
+                color="CONTROL",
+            )
+            self.nextrely -= 1
+            self.add_widget_intelligent(
+                CenteredTitleText,
+                name="Select from a starter set of Stable Diffusion models from HuggingFace.",
+                editable=False,
+                labelColor="CAUTION",
+            )
+            self.nextrely -= 1
+            # if user has already installed some initial models, then don't patronize them
+            # by showing more recommendations
+            show_recommended = not self.existing_models
+            self.models_selected = self.add_widget_intelligent(
+                npyscreen.MultiSelect,
+                name="Install Starter Models",
+                values=starter_model_labels,
+                value=[
+                    self.starter_model_list.index(x)
+                    for x in self.starter_model_list
+                    if show_recommended and x in recommended_models
+                ],
+                max_height=len(starter_model_labels) + 1,
+                relx=4,
+                scroll_exit=True,
+            )
         self.add_widget_intelligent(
             CenteredTitleText,
             name='== IMPORT LOCAL AND REMOTE MODELS ==',
@@ -166,7 +166,11 @@ class addModelsForm(npyscreen.FormMultiPage):
             )
             self.nextrely -= 1
         self.import_model_paths = self.add_widget_intelligent(
-            TextBox, max_height=5, scroll_exit=True, editable=True, relx=4
+            TextBox,
+            max_height=7,
+            scroll_exit=True,
+            editable=True,
+            relx=4
         )
         self.nextrely += 1
         self.show_directory_fields = self.add_widget_intelligent(
@@ -241,7 +245,8 @@ class addModelsForm(npyscreen.FormMultiPage):
 
     def resize(self):
         super().resize()
-        self.models_selected.values = self._get_starter_model_labels()
+        if hasattr(self,'models_selected'):
+            self.models_selected.values = self._get_starter_model_labels()
 
     def _clear_scan_directory(self):
         if not self.show_directory_fields.value:
@@ -320,11 +325,14 @@ class addModelsForm(npyscreen.FormMultiPage):
         selections = self.parentApp.user_selections
 
         # starter models to install/remove
-        starter_models = dict(
-            map(
-                lambda x: (self.starter_model_list[x], True), self.models_selected.value
+        if hasattr(self,'models_selected'):
+            starter_models = dict(
+                map(
+                    lambda x: (self.starter_model_list[x], True), self.models_selected.value
+                )
             )
-        )
+        else:
+            starter_models = dict()
         selections.purge_deleted_models = False
         if hasattr(self, "previously_installed_models"):
             unchecked = [

ldm/invoke/generator/base.py

@@ -137,17 +137,9 @@ class Generator:
         Given samples returned from a sampler, converts
         it into a PIL Image
         """
-        x_samples = self.model.decode_first_stage(samples)
-        x_samples = torch.clamp((x_samples + 1.0) / 2.0, min=0.0, max=1.0)
-        if len(x_samples) != 1:
-            raise Exception(
-                f'>> expected to get a single image, but got {len(x_samples)}')
-        x_sample = 255.0 * rearrange(
-            x_samples[0].cpu().numpy(), 'c h w -> h w c'
-        )
-        return Image.fromarray(x_sample.astype(np.uint8))
-
-        # write an approximate RGB image from latent samples for a single step to PNG
+        with torch.inference_mode():
+            image = self.model.decode_latents(samples)
+        return self.model.numpy_to_pil(image)[0]
 
     def repaste_and_color_correct(self, result: Image.Image, init_image: Image.Image, init_mask: Image.Image, mask_blur_radius: int = 8) -> Image.Image:
         if init_image is None or init_mask is None:

ldm/invoke/globals.py

@@ -19,15 +19,7 @@ from typing import Union
 
 Globals = Namespace()
 
-# This is usually overwritten by the command line and/or environment variables
-if os.environ.get('INVOKEAI_ROOT'):
-    Globals.root = osp.abspath(os.environ.get('INVOKEAI_ROOT'))
-elif os.environ.get('VIRTUAL_ENV'):
-    Globals.root = osp.abspath(osp.join(os.environ.get('VIRTUAL_ENV'), '..'))
-else:
-    Globals.root = osp.abspath(osp.expanduser('~/invokeai'))
-
-# Where to look for the initialization file
+# Where to look for the initialization file and other key components
 Globals.initfile = 'invokeai.init'
 Globals.models_file = 'models.yaml'
 Globals.models_dir = 'models'
@@ -35,6 +27,20 @@ Globals.config_dir = 'configs'
 Globals.autoscan_dir = 'weights'
 Globals.converted_ckpts_dir = 'converted_ckpts'
 
+# Set the default root directory. This can be overwritten by explicitly
+# passing the `--root <directory>` argument on the command line.
+# logic is:
+# 1) use INVOKEAI_ROOT environment variable (no check for this being a valid directory)
+# 2) use VIRTUAL_ENV environment variable, with a check for initfile being there
+# 3) use ~/invokeai
+
+if os.environ.get('INVOKEAI_ROOT'):
+    Globals.root = osp.abspath(os.environ.get('INVOKEAI_ROOT'))
+elif os.environ.get('VIRTUAL_ENV') and Path(os.environ.get('VIRTUAL_ENV'),'..',Globals.initfile).exists():
+    Globals.root = osp.abspath(osp.join(os.environ.get('VIRTUAL_ENV'), '..'))
+else:
+    Globals.root = osp.abspath(osp.expanduser('~/invokeai'))
+
 # Try loading patchmatch
 Globals.try_patchmatch = True
 

ldm/invoke/model_manager.py

@@ -725,7 +725,7 @@ class ModelManager(object):
         SDLegacyType.V1
         SDLegacyType.V1_INPAINT
         SDLegacyType.V2
-        UNKNOWN
+        SDLegacyType.UNKNOWN
         """
         key_name = "model.diffusion_model.input_blocks.2.1.transformer_blocks.0.attn2.to_k.weight"
         if key_name in checkpoint and checkpoint[key_name].shape[-1] == 1024:
@@ -785,7 +785,7 @@ class ModelManager(object):
         print(f">> Probing {thing} for import")
 
         if thing.startswith(("http:", "https:", "ftp:")):
-            print(f"   | {thing} appears to be a URL")
+            print(f"  | {thing} appears to be a URL")
             model_path = self._resolve_path(
                 thing, "models/ldm/stable-diffusion-v1"
             )  # _resolve_path does a download if needed
@@ -793,15 +793,15 @@ class ModelManager(object):
         elif Path(thing).is_file() and thing.endswith((".ckpt", ".safetensors")):
             if Path(thing).stem in ["model", "diffusion_pytorch_model"]:
                 print(
-                    f"   | {Path(thing).name} appears to be part of a diffusers model. Skipping import"
+                    f"  | {Path(thing).name} appears to be part of a diffusers model. Skipping import"
                 )
                 return
             else:
-                print(f"   | {thing} appears to be a checkpoint file on disk")
+                print(f"  | {thing} appears to be a checkpoint file on disk")
                 model_path = self._resolve_path(thing, "models/ldm/stable-diffusion-v1")
 
         elif Path(thing).is_dir() and Path(thing, "model_index.json").exists():
-            print(f"   | {thing} appears to be a diffusers file on disk")
+            print(f"  | {thing} appears to be a diffusers file on disk")
             model_name = self.import_diffuser_model(
                 thing,
                 vae=dict(repo_id="stabilityai/sd-vae-ft-mse"),
@@ -812,13 +812,13 @@ class ModelManager(object):
 
         elif Path(thing).is_dir():
             if (Path(thing) / "model_index.json").exists():
-                print(f">> {thing} appears to be a diffusers model.")
+                print(f"  | {thing} appears to be a diffusers model.")
                 model_name = self.import_diffuser_model(
                     thing, commit_to_conf=commit_to_conf
                 )
             else:
                 print(
-                    f">> {thing} appears to be a directory. Will scan for models to import"
+                    f"  |{thing} appears to be a directory. Will scan for models to import"
                 )
                 for m in list(Path(thing).rglob("*.ckpt")) + list(
                     Path(thing).rglob("*.safetensors")
@@ -830,7 +830,7 @@ class ModelManager(object):
                 return model_name
 
         elif re.match(r"^[\w.+-]+/[\w.+-]+$", thing):
-            print(f"   | {thing} appears to be a HuggingFace diffusers repo_id")
+            print(f"  | {thing} appears to be a HuggingFace diffusers repo_id")
             model_name = self.import_diffuser_model(
                 thing, commit_to_conf=commit_to_conf
             )
@@ -847,7 +847,7 @@ class ModelManager(object):
             return
 
         if model_path.stem in self.config:  # already imported
-            print("   | Already imported. Skipping")
+            print("  | Already imported. Skipping")
             return
 
         # another round of heuristics to guess the correct config file.
@@ -860,18 +860,18 @@ class ModelManager(object):
 
         model_config_file = None
         if model_type == SDLegacyType.V1:
-            print("   | SD-v1 model detected")
+            print("  | SD-v1 model detected")
             model_config_file = Path(
                 Globals.root, "configs/stable-diffusion/v1-inference.yaml"
             )
         elif model_type == SDLegacyType.V1_INPAINT:
-            print("   | SD-v1 inpainting model detected")
+            print("  | SD-v1 inpainting model detected")
             model_config_file = Path(
                 Globals.root, "configs/stable-diffusion/v1-inpainting-inference.yaml"
             )
         elif model_type == SDLegacyType.V2:
             print(
-                "   | SD-v2 model detected; model will be converted to diffusers format"
+                "  | SD-v2 model detected; model will be converted to diffusers format"
             )
             model_config_file = Path(
                 Globals.root, "configs/stable-diffusion/v2-inference-v.yaml"
@@ -923,7 +923,7 @@ class ModelManager(object):
         vae=None,
         original_config_file: Path = None,
         commit_to_conf: Path = None,
-    ) -> dict:
+    ) -> str:
         """
         Convert a legacy ckpt weights file to diffuser model and import
         into models.yaml.

pyproject.toml

@@ -38,7 +38,7 @@ dependencies = [
   "albumentations",
   "click",
   "clip_anytorch",          # replacing "clip @ https://github.com/openai/CLIP/archive/eaa22acb90a5876642d0507623e859909230a52d.zip",
-  "compel>=0.1.6",
+  "compel==0.1.7",
   "datasets",
   "diffusers[torch]~=0.13",
   "dnspython==2.2.1",

scripts/make_models_markdown_table.py

@@ -0,0 +1,23 @@
+#!/usr/bin/env python
+
+'''
+This script is used at release time to generate a markdown table describing the
+starter models. This text is then manually copied into 050_INSTALL_MODELS.md.
+'''
+
+from omegaconf import OmegaConf
+from pathlib import Path
+
+
+def main():
+    initial_models_file = Path(__file__).parent / '../invokeai/configs/INITIAL_MODELS.yaml'
+    models = OmegaConf.load(initial_models_file)
+    print('|Model Name | HuggingFace Repo ID | Description | URL |')
+    print('|---------- | ---------- | ----------- | --- |')
+    for model in models:
+        repo_id = models[model].repo_id
+        url = f'https://huggingface.co/{repo_id}'
+        print(f'|{model}|{repo_id}|{models[model].description}|{url} |')
+
+if __name__ == '__main__':
+    main()