RainCCH commited on
Commit
8884191
·
1 Parent(s): 381691b

update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -5
README.md CHANGED
@@ -47,7 +47,7 @@ The framework leverages advanced diffusion models and transformer architectures
47
  - [ ] Release our unified creation model.
48
  - [ ] Release training code.
49
 
50
- ## 🏞️ Show Caeses
51
  **Results of generation tasks.** We show two generation tasks under our unified model. The top section presents text-to-image results, illustrating high-fidelity synthesis across diverse styles. The bottom rows show text-to-video results, demonstrating temporally coherent generation with natural motion for both realistic and stylized content.
52
  <p align="center">
53
  <img src="./assets/misc/gen_teaser.png" style="width: 100%; height: auto;"/>
@@ -63,7 +63,7 @@ The framework leverages advanced diffusion models and transformer architectures
63
  <img src="./assets/misc/videoedit_teaser5.png" style="width: 100%; height: auto;"/>
64
  </p>
65
 
66
- **Results of in-context visual creation.** We show in-context generation and in-context editing results , including subject-conditioned generation (S2V/S2I), conditional generation(C2V), image-to-video(I2V), reference-driven editing (II2I/IV2V).
67
  <p align="center">
68
  <img src="./assets/misc/incontext_teaser2.png" style="width: 100%; height: auto;"/>
69
  </p>
@@ -212,8 +212,8 @@ For editing tasks (TI2I / TV2V), prepare a CSV with `img_path`/`video_path` and
212
 
213
  ```csv
214
  img_path,instruction
215
- img1.jpeg,insturction1.
216
- img2.jpeg,insturction2.
217
  ```
218
 
219
  > The path column holds relative paths to media files (images or videos) under the data root directory.
@@ -268,7 +268,7 @@ ln -s /path/to/Capybara /path/to/ComfyUI/custom_nodes/Capybara
268
  | **Capybara Load Rewrite Model** | Load Qwen3-VL for prompt rewriting |
269
  | **Capybara Rewrite Instruction** | Expand short prompts into detailed instructions |
270
 
271
- A sample workflow is provided in [`comfyui/examples/`](comfyui/examples/). For setup details and node documentation, see the [ComfyUI README](comfyui/README.md).
272
 
273
  ## ⚙️ Configuration Details
274
 
 
47
  - [ ] Release our unified creation model.
48
  - [ ] Release training code.
49
 
50
+ ## 🏞️ Show Cases
51
  **Results of generation tasks.** We show two generation tasks under our unified model. The top section presents text-to-image results, illustrating high-fidelity synthesis across diverse styles. The bottom rows show text-to-video results, demonstrating temporally coherent generation with natural motion for both realistic and stylized content.
52
  <p align="center">
53
  <img src="./assets/misc/gen_teaser.png" style="width: 100%; height: auto;"/>
 
63
  <img src="./assets/misc/videoedit_teaser5.png" style="width: 100%; height: auto;"/>
64
  </p>
65
 
66
+ **Results of in-context visual creation.** We show in-context generation and in-context editing results, including subject-conditioned generation (S2V/S2I), conditional generation (C2V), image-to-video (I2V), reference-driven editing (II2I/IV2V).
67
  <p align="center">
68
  <img src="./assets/misc/incontext_teaser2.png" style="width: 100%; height: auto;"/>
69
  </p>
 
212
 
213
  ```csv
214
  img_path,instruction
215
+ img1.jpeg,instruction1.
216
+ img2.jpeg,instruction2.
217
  ```
218
 
219
  > The path column holds relative paths to media files (images or videos) under the data root directory.
 
268
  | **Capybara Load Rewrite Model** | Load Qwen3-VL for prompt rewriting |
269
  | **Capybara Rewrite Instruction** | Expand short prompts into detailed instructions |
270
 
271
+ A sample workflow is provided in [`comfyui/examples/`](https://github.com/xgen-universe/Capybara/tree/main/comfyui/examples). For setup details and node documentation, see the [ComfyUI README](https://github.com/xgen-universe/Capybara/tree/main/comfyui).
272
 
273
  ## ⚙️ Configuration Details
274