Hugging Face's logo

sensenova
/
SenseNova-U1-8B-MoT-SFT

Any-to-Any
Transformers
Safetensors
neo_chat
image-feature-extraction
multimodal
text-to-image
image-to-text
image-editing
interleaved-generation
custom_code
Model card Files
xet
 Community
6
TokenWang commited on
Commit
8417fe9
·
verified ·
1 Parent(s): 55fc6dd

Upload folder using huggingface_hub

Browse files
Files changed (1) hide show
  1. docs/showcases_CN.md +9 -1
docs/showcases_CN.md CHANGED
@@ -27,7 +27,7 @@
27
 
28
  #### 🖼️ *文生图（推理）*
29
 
30
- 可复现的 prompt 位于 [`examples/t2i/data/sample_reasoning.jsonl`](../examples/t2i/data/sample_reasoning.jsonl)。
31
 
32
  <table>
33
  <tr>
@@ -210,12 +210,20 @@
210
  | [<img alt="interleave case 01" src="./assets/showcases/interleave/case_0001_makeup_three_looks.webp">](./assets/showcases/interleave/case_0001_makeup_three_looks.webp) |
211
  | [<img alt="interleave case 07" src="./assets/showcases/interleave/case_0007_bowie_slide_design.webp">](./assets/showcases/interleave/case_0007_bowie_slide_design.webp) |
212
 
 
 
 
 
 
 
213
  ---
214
 
215
  ## 视觉理解
216
 
217
  涵盖空间推理、多图比较、OCR、几何以及知识密集型问答的通用视觉理解能力：
218
 
 
 
219
  | |
220
  | :---: |
221
  | [<img alt="vqa agentic case" src="./assets/showcases/vqa/agentic_case.webp">](./assets/showcases/vqa/agentic_case.webp) |
 
27
 
28
  #### 🖼️ *文生图（推理）*
29
 
30
+ 可复现的 prompt 位于 [`examples/t2i/data/samples_reasoning.jsonl`](../examples/t2i/data/samples_reasoning.jsonl)。
31
 
32
  <table>
33
  <tr>
 
210
  | [<img alt="interleave case 01" src="./assets/showcases/interleave/case_0001_makeup_three_looks.webp">](./assets/showcases/interleave/case_0001_makeup_three_looks.webp) |
211
  | [<img alt="interleave case 07" src="./assets/showcases/interleave/case_0007_bowie_slide_design.webp">](./assets/showcases/interleave/case_0007_bowie_slide_design.webp) |
212
 
213
+ #### ♻️ *图文交错生成（推理）*
214
+
215
+ | |
216
+ | :---: |
217
+ | [<img alt="interleave reasoning case 2" src="./assets/showcases/interleave/reasoning_case2.png">](./assets/showcases/interleave/reasoning_case2.png) |
218
+
219
  ---
220
 
221
  ## 视觉理解
222
 
223
  涵盖空间推理、多图比较、OCR、几何以及知识密集型问答的通用视觉理解能力：
224
 
225
+ 可复现的 prompt 位于 [`examples/vqa/data/samples.jsonl`](../examples/vqa/data/samples.jsonl)。
226
+
227
  | |
228
  | :---: |
229
  | [<img alt="vqa agentic case" src="./assets/showcases/vqa/agentic_case.webp">](./assets/showcases/vqa/agentic_case.webp) |