Update README.md

README.md

@@ -66,7 +66,6 @@ The v0.1 model was tuned toward a deliberately narrow domain to validate the app
 - **Semi-static establishing city / urban scenes** (no heavy camera motion)
 - **~100° horizontal field of view** in the source clip
 - **2.39:1 source aspect** (standard cinemascope)
-- **1024×512 @ 24 fps, 41 frames** at inference
 
 It will **generalize poorly** outside these conditions — fast action, extreme close-ups, heavily
 stylised imagery, or very different FOVs are not reliably handled yet.
@@ -87,16 +86,11 @@ Three sample clips (`clip1`, `clip2`, `clip3`) are included under `samples/`.
 
 Load on top of `ltx-2.3-22b-dev.safetensors` with the LTX-2 `video_to_video` pipeline and pass:
 
-- **Trigger word**: `equirectangular` (required, include in every prompt)
+- **Trigger word**: `equirectangular` (works without any prompt too, and with a descriptive prompt you can direct the content of outpainted part)
 - **Reference video**: your source clip projected into the equirect canvas with unknown regions masked
-- **Resolution**: 1024×512, 41 frames, 24 fps (other shapes untested)
+- **Resolution**: 1920x960, 121 frames, 24 fps
 
-Recommended starting points:
-
-- LoRA strength: **1.0**
-- Guidance scale (CFG): **4.0**
-- STG scale: **1.0**, blocks `[29]`, mode `stg_v`
-- Inference steps: **20–30**
+Only tested in ComfyUI with the workflow available in this repo. Please note that the workflow's padding node crops your input footage to 2.39:1, you can select whether it's cut from center, top or bottom. Other aspect ratios will work poorly in this early version.
 
 ### Companion tooling
 
@@ -123,9 +117,9 @@ repo shows the exact wiring.
 The final **step 3500** checkpoint is shipped here. Intermediate checkpoints were used for
 validation during training but aren't included in this release.
 
-## What's next (v0.2)
+## What's next
 
-v0.2 is planned on a significantly larger and more diverse dataset (thousands of clips) covering:
+Next version is planned on a significantly larger and more diverse dataset covering:
 
 - Broader subject matter (interiors, landscapes, crowds, vehicles, …)
 - Varied input FOVs and focal lengths
@@ -140,6 +134,11 @@ v0.2 is planned on a significantly larger and more diverse dataset (thousands of
 - Outputs are not a substitute for natively captured 360 footage — this is a creative
   re-projection, not a reconstruction
 
+## Acknowledgements
+
+- First training done at ADOS Paris event in collaboration with Cseti, NebSH and S4f3ty_Marc.
+- Advice from oumoumad in IC-LoRA training altogether has been very valuable to me. The workflow included in this release is modified from oumoumad's IC-LoRA workflow.
+
 ## License
 
 Apache-2.0. Inherits any base-model conditions from LTX-2.3-22B.