Update README.md

README.md

@@ -25,10 +25,9 @@ reference side of it. You can feed it up to **9 images**, which means you can bu
 of bits — a face from here, armour from there, a hat from somewhere else — and it'll actually hold
 them together.
 
-So this workflow does that, spins the character 360°, and spits out a reference sheet you can use to
+So this workflow does that, spins the character 360 (or 180 if using 4 panel version), and spits out a reference sheet you can use to
 keep them consistent in everything you make afterwards.
 
-Here's what went into that knight, by the way. Not exactly pristine source material:
 
 ![Celtic Knight inputs](https://huggingface.co/PoopMan333/H3_Character_Sheet_Generator/resolve/main/examples/CelticKnight%20-%20Example.PNG)
 
@@ -48,11 +47,11 @@ statue, and then the workflow grabs six frames and stitches them together.
 ## How it works
 
 1. You drop in your images and describe them in the **Input Text (A Prompt)** box
-2. That gets glued onto a fixed **B Prompt** which handles the spin, the pose, the lighting and all the boring staging stuff
-3. It generates a slow 360° with no hard cuts, so the character stays consistent
-4. Six frames get grabbed and stitched into the sheet
+2. That added with a **B Prompt** which handles the spin, pose, lighting etc. 
+3. It generates a slow 360 with no hard cuts, so the character stays consistent
+4. 6/4 frames get grabbed and stitched into the sheet
 
-You also get the full video and every individual frame as optional outputs, if you want to pick your
+You also have the option for a 360 spin video and every individual frame as optional outputs, if you want to pick your
 own angles or use single frames as references later.
 
 ---
@@ -92,7 +91,7 @@ optional Speed Ups group:
 - [KJNodes](https://github.com/kijai/ComfyUI-KJNodes)
 - [rgthree](https://github.com/rgthree/rgthree-comfy) (just the toggle panel)
 
-Delete that group and you're on core ComfyUI with zero dependencies.
+Delete that group if you want to.
 
 ---
 
@@ -107,7 +106,7 @@ One line per image. Say what to take, and — this bit matters more than people
 <Picture 3> - use the shield. It is attached to the man's back.
 ```
 
-If you don't rule things out by name, backgrounds and the wrong person's face sneak through.
+If you don't rule things out by name, backgrounds and the wrong person's hair sneak through.
 
 Also worth describing clothing **in words**, not just showing it. Faces carry across on their own but
 wardrobe drifts. "Black high-collared coat with silver buckles" sticks. "The coat from Picture 2"
@@ -116,7 +115,7 @@ wanders off.
 ---
 
 
-## Anime → Real
+## Anime to Real
 
 Someone asked if it could do anime to realistic, so there's a modified B prompt for that too. It's
 surprisingly good at it.
@@ -136,21 +135,32 @@ then a couple of face shots at the end:
 
 The six panels are just frames pulled out of that.
 
+
+
+---
+
+
+## Objects
+
+The model also does a excellent job of doing objects, however it is advised to show more angles as reference images. 
+
+![random shield picture i found on google](https://huggingface.co/PoopMan333/H3_Character_Sheet_Generator/resolve/main/examples/shield%20example.png)
+
+
 ---
 
 
 
+
 ## Caveats (being honest here)
 
 **It's slooooow.** You're generating 124 frames to use 6. That's the fundamental silliness of the
-approach. The 4-panel version helps.
+approach. The 4-panel version helps by only generating 73 frames and taking 4 (40% speed up).
 
 **Speed-ups cost you something.** Turbo LoRAs and caching do make it faster, but prompt adherence and
-quality take a hit. Worth it sometimes, not always. If you use the turbo LoRA, drop your steps to
-match it — running a 4-step LoRA at 25 steps gives you the downsides of both and the benefits of
-neither.
+quality take a slight hit. Worth it most times except final pass. 
 
-**Quality is limited.** It's a video model, it's better at video than stills. Crank the resolution if
+**Quality is limited.** It's a video model, it's better at video than stills. Crank the resolution and steps if
 you care, and pay for it in generation time.
 
 **The sheet alone might not be enough for close-ups.** Resolution per panel is what it is. For close
@@ -158,8 +168,6 @@ work I'd use the sheet *plus* some detail shots — face, clothing texture, what
 honestly, for a one-off video you might be better off skipping the sheet and just using your
 originals.
 
-**The back view is invented** if none of your references show the back. Nothing in the prompt fixes
-that. Give it a back or side shot if you have one — biggest single quality improvement available.
 
 ---