feat: add desi-max model weights and demo images

.gitattributes

@@ -45,6 +45,13 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.wasm filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+desi-max_10.safetensors filter=lfs diff=lfs merge=lfs -text
+demo/gen-6-1.jpeg filter=lfs diff=lfs merge=lfs -text
+demo/google-2.png filter=lfs diff=lfs merge=lfs -text
+demo/pulse.png filter=lfs diff=lfs merge=lfs -text
+demo/bharat-ai.png filter=lfs diff=lfs merge=lfs -text
+demo/bournvita.png filter=lfs diff=lfs merge=lfs -text
+demo/gen-1.jpeg filter=lfs diff=lfs merge=lfs -text
 *.png filter=lfs diff=lfs merge=lfs -text
 *.jpeg filter=lfs diff=lfs merge=lfs -text
 *.jpg filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,55 +1,74 @@
 ---
-base_model: Qwen/Qwen-Image-2512@master
-license: Apache License 2.0
+base_model: Qwen/Qwen-Image-2512
+license: apache-2.0
 tags:
-- LoRA
-- text-to-image
-tasks:
-- text-to-image-synthesis
-trigger_words:
-- desi-max
-vision_foundation: QWEN_IMAGE_20_B
-
-#model-type:
-##such as  gpt、phi、llama、chatglm、baichuan, etc.
-#- gpt
-
-#domain:
-##such as  nlp、cv、audio、multi-modal, etc.
-#- nlp
-
-#language:
-##language code list https://help.aliyun.com/document_detail/215387.html?spm=a2c4g.11186623.0.0.9f8d7467kni6Aa
-#- cn 
-
-#metrics:
-##such as  CIDEr、Blue、ROUGE, etc.
-#- CIDEr
-
-#tags:
-##various custom tags, including pretrained, fine-tuned, instruction-tuned, RL-tuned, and others
-#- pretrained
-
-#tools:
-##such as  vllm、fastchat、llamacpp、AdaSeq, etc.
-#- vllm
+  - lora
+  - text-to-image
+  - fine-tuned
+  - style-transfer
+pipeline_tag: text-to-image
+trigger_word: desi-max
 ---
-### You are viewing the default Readme template as no detailed model-card was provided by the model’s contributors. You can access the model files in the "Files and versions" tab.
-#### Model files may be downloaded with ModelScope SDK or through git clone directly.
 
-Download with ModelScope’s Python SDK
-```bash
-#Install ModelScope
-pip install modelscope
-```
-```python
-#Download with ModelScope’s Python SDK
-from modelscope import snapshot_download
-model_dir = snapshot_download('yumpyy/desi-max')
-```
-Download with Git clone
+# Desi Maximalism LoRA
+
+<p align="center">
+  <img src="demo/gen-1.jpeg" width="30%" style="border-radius:6px; margin:4px"/>
+  <img src="demo/gen-6-1.jpeg" width="30%" style="border-radius:6px; margin:4px"/>
+  <img src="demo/bharat-ai.png" width="30%" style="border-radius:6px; margin:4px"/>
+</p>
+<p align="center">
+  <img src="demo/bournvita.png" width="30%" style="border-radius:6px; margin:4px"/>
+  <img src="demo/google-2.png" width="30%" style="border-radius:6px; margin:4px"/>
+  <img src="demo/pulse.png" width="30%" style="border-radius:6px; margin:4px"/>
+</p>
+
+---
+
+## Model
+
+| | |
+|---|---|
+| **Base Model** | `Qwen/Qwen-Image-2512` |
+| **Vision Foundation** | Qwen2.5-VL · 20B parameters |
+| **Fine-tuning Method** | LoRA |
+| **Task** | Text-to-image · style transfer |
+| **Trigger Word** | `desi-max` |
+| **License** | Apache 2.0 |
+
+---
+
+## Dataset
+
+78 handpicked images of vintage South Asian commercial print — matchbox labels, product packaging, film posters, and magazine ads (c. 1940–1985). Each image was manually selected to represent a distinct visual sub-pattern, keeping the dataset tight and avoiding style collapse.
+
+---
+
+## Training Target
+
+The LoRA is optimised to reproduce:
+
+- Bold flat colour blocking and high-contrast palettes
+- Decorative borders, concentric rules, cartouche framing
+- Halftone and offset print grain/texture
+- Dense multi-scale typographic hierarchy
+- Hand-painted illustration shading and exaggerated perspective
+
+---
+
+## Usage
+
+Prepend and append `desi-max` to your prompt.
+
 ```
-git clone https://www.modelscope.ai/yumpyy/desi-max.git
+desi-max, vintage Indian matchbox label, GAJRAJ AUTO in large red lettering,
+blue starburst, illustrated autorickshaw in green and pink, yellow background,
+bold halftone print texture, mid-century South Asian commercial design, desi-max
 ```
 
-<p style="color: lightgrey;">If you are a contributor to this model, we invite you to promptly update the model card content according to <a href="https://www.modelscope.ai/docs/contribute/model-integration" style="color: lightgrey; text-decoration: underline;">the model contribution documentation</a>.</p>
+---
+
+## Limitations
+
+- Devanagari / Tamil script accuracy is bounded by the base model's multilingual capability
+- Optimised for flat illustrated aesthetics — not photorealism

configuration.json

@@ -0,0 +1 @@
+{"aigc_model":true,"framework":"pytorch","model_file_location":"desi-max_10.safetensors","task":"text-to-image-synthesis"}

desi-max_10.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82d7e08c7f12e1161155e90a84213dd514c1a1fa0c95ff4d4a8183eae6571ef7
+size 236117024

desi-max_5.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef49c32ff4b9f82fb13269c1fab702b51de0881cf90689ccd16c1b24a1f507ff
+size 236117024