Update README

README.md

@@ -9,7 +9,19 @@ This repo holds a modularized version of [Disco Diffusion](https://github.com/al
 1. Clone this repository into your `ComfyUI/custom_nodes` folder with `git clone --recursive https://github.com/space-nuko/ComfyUI-Disco-Diffusion`.
 2. Activate the virtualenv you use with ComfyUI.
 3. Navigate to the cloned folder and run `pip install -r requirements.txt`.
-4. Start ComfyUI.
+
+**NOTE:** You also have to make sure that inference mode is turned off within ComfyUI or you'll get errors.
+
+In `ComfyUI/execution.py`, change:
+
+``` python
+with torch.inference_mode():
+```
+
+to:
+``` python
+with torch.inference_mode(False):
+```
 
 ## Nodes included
 
@@ -22,7 +34,7 @@ This repo holds a modularized version of [Disco Diffusion](https://github.com/al
 
 The simplest usage is to connect the Guided Diffusion Loader and OpenAI CLIP Loader nodes into a Disco Diffusion node, then hook the Disco Diffusion node up to a Save Image node.
 
-Alternatively, you can substitude the OpenAI CLIP Loader for ComfyUI's CLIP Loader and CLIP Vision Loader, however in this case you need to copy the CLIP model you use into both the `clip` and `clip_vision` subfolders under your `ComfyUI/models` folder, because ComfyUI can't load both at once from the same model file.
+Alternatively, you can substitute the OpenAI CLIP Loader for ComfyUI's CLIP Loader and CLIP Vision Loader, however in this case you need to copy the CLIP model you use into both the `clip` and `clip_vision` subfolders under your `ComfyUI/models` folder, because ComfyUI can't load both at once from the same model file.
 
 The Disco Diffusion node uses a special syntax for writing prompts, which is shown below.
 

do_run.py

@@ -23,6 +23,7 @@ from numpy import asarray
 from . import py3d_tools as p3dT
 from . import disco_xform_utils as dxf
 from .CLIP import clip
+import open_clip
 
 import comfy.model_management
 import comfy.utils
@@ -118,8 +119,11 @@ def get_input_resolution(clip_model):
         if isinstance(clip_model, ClipVisionModel):
             # ComfyUI (Transformers)
             return clip_model.model.config.image_size
+        elif isinstance(clip_model, open_clip.CLIP):
+            # OpenClip
+            return clip_model.visual.image_size[0]
         else:
-            # OpenAI/OpenClip
+            # OpenAI
             return clip_model.visual.input_resolution
     except Exception as err:
         print("Couldn't find clip vision image size! " + str(err) + " " + str(type(clip_model)))
@@ -340,7 +344,6 @@ def run_one_frame(diffusion, model, clip_model, clip_vision, args, batchNum, fra
 
     print(f'Frame {frame_num} Prompt: {frame_prompt}')
 
-
     clip_models = [clip_model]
 
     model_stats = []