commit d7ea36943e8c769ab53df5b1271f88d662d78fb2 Author: ModelHub XC Date: Sat Aug 15 02:23:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: srk0102200/AnimTOON-3B Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52373fe --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..58d9297 --- /dev/null +++ b/README.md @@ -0,0 +1,179 @@ +--- +language: +- en +license: mit +library_name: transformers +base_model: Qwen/Qwen2.5-3B-Instruct +tags: +- animation +- lottie +- svg +- animtoon +- vector-animation +- text-to-animation +- conversational +- text-generation-inference +datasets: +- OmniLottie/MMLottie-2M +pipeline_tag: text-generation +--- + +# AnimTOON-3B (v3): Token-Efficient Vector Animation Generation + +**3-4x fewer tokens than OmniLottie (CVPR 2026) for generating Lottie animations. Now with character animation support.** + +| | AnimTOON | OmniLottie | +|---|---|---| +| **Tokens (simple)** | **166** | 616 | +| **Tokens (complex)** | **597** | 4095 | +| **VRAM** | **5GB** | 15.2GB | +| **FPS** | **30** | 8 | +| **Model Size** | **3B LoRA** | 4B full | +| **Custom Tokenizer** | **No** | Yes (40k tokens) | +| **Accepts SVG** | **Yes** | No | + +## What is AnimTOON? + +AnimTOON is a compact, plain-text animation format that any LLM can generate. Instead of outputting 18,000+ tokens of raw Lottie JSON, AnimTOON describes animations in ~166-597 tokens of human-readable text. + +``` +anim fr=30 dur=120 + +layer Logo shape + fill #000000 + path sh x2 + pos [0.5,0.5] + rot 0.0->-67 0.04->46 0.14->-31 0.28->0 ease=bounce + scale 0.0->[0,0] 0.14->[90,90] 0.28->[100,100] ease=smooth + opacity 0.0->0 0.14->100 ease=fade +``` + +This produces a complete animated .lottie file with bounce entrance, rotation wobble, and fade-in. + +## How to Use + +```python +from transformers import AutoModelForCausalLM, AutoTokenizer +import torch + +tokenizer = AutoTokenizer.from_pretrained("srk0102200/AnimTOON-3B") +model = AutoModelForCausalLM.from_pretrained( + "srk0102200/AnimTOON-3B", + dtype=torch.float16, + device_map="cuda" +) + +prompt = "a red circle pulsing in the center with a smooth bounce" +messages = [{"role": "user", "content": f"Generate AnimTOON animation: {prompt}"}] +text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) +inputs = tokenizer(text, return_tensors="pt").to("cuda") + +with torch.no_grad(): + out = model.generate(**inputs, max_new_tokens=512, temperature=0.7, do_sample=True) +result = tokenizer.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True) +print(result) +``` + +## Convert to .lottie + +```python +# Clone: git clone https://github.com/srk0102/AnimTOON.git +import sys; sys.path.insert(0, 'src') +from toon_animator import animtoon_to_dotlottie_full + +animtoon_to_dotlottie_full(result, "output.lottie") +# Preview at https://lottiefiles.com/preview +``` + +## Animate Any SVG + +```python +from lottie import parsers # pip install lottie + +# Convert SVG to Lottie (perfect paths) +anim = parsers.svg.parse_svg_file("your_logo.svg") +lottie_dict = anim.to_dict() + +# Generate AnimTOON animations with the model +# Apply animations to the Lottie layers +# Output: .lottie file with real SVG shapes + AI animations +``` + +See full pipeline: [test_svg_pipeline.py](https://github.com/srk0102/AnimTOON/blob/master/test_svg_pipeline.py) + +## Benchmark Results (Measured) + +**Same prompt, same hardware:** + +| Test | AnimTOON Tokens | OmniLottie Tokens | Ratio | +|------|----------------|-------------------|-------| +| Apple logo bounce | 207 (41 shape + 166 anim) | 1113 | 5.4x fewer | +| Smiley face complex | 597 | 4095 | 6.9x fewer | +| Simple ball bounce | 176 | 616 | 3.5x fewer | + +**Dataset statistics (99,650 samples):** +- Average raw Lottie JSON: 18,202 tokens +- Average AnimTOON: 222 tokens +- Token reduction: 98.8% + +## Current Status (v3) + +**v3 adds character animation support** trained on Spine + DragonBones skeletal data. + +The model now works for: +- Icon/logo animations (pulse, bounce, spin, fade, wobble) +- **Character idle/walk cycles (14 layers, coordinated)** +- **Multi-part SVG animation (47-part crab demo)** +- Correct color matching from text descriptions +- SVG + animation pipeline with per-part anchor points + +**Limitations:** +- No shape generation (requires SVG input) +- Model output varies between runs (temperature-dependent) +- Position animation on shape groups not yet supported +- Not yet trained on facial expressions + +## Training Details + +| Parameter | Value | +|-----------|-------| +| Base Model | Qwen/Qwen2.5-3B-Instruct | +| Method | LoRA (r=16, alpha=32) merged into base | +| Version | v3 (final 3B Lite release) | +| Training Data | 99,650 (MMLottie-2M) + 10,000 (layer-aware) + 984 (Spine/DragonBones) | +| Hardware | 1x NVIDIA RTX 5060 Ti (16GB) | +| Framework | Unsloth | +| Token Reduction | 98.8% vs raw Lottie JSON | + +## Architecture: Why Animation-Only is Better + +> "Asking one model to draw AND animate is like asking one person to paint AND dance at the same time." + +AnimTOON separates concerns: +- **SVG provides shapes** (perfect, no hallucination, 0 tokens) +- **Model generates animation** (focused, token-efficient) +- **Converter merges them** (deterministic, 100% valid output) + +OmniLottie generates everything in one model → hallucinated shapes, token bloat (2001 tokens for a "crab" that looks like binoculars). + +## Links + +- **GitHub:** [github.com/srk0102/AnimTOON](https://github.com/srk0102/AnimTOON) +- **PitchHut:** [pitchhut.com/project/animtoon-lottie-animation](https://www.pitchhut.com/project/animtoon-lottie-animation) +- **OmniLottie (comparison):** [arxiv.org/abs/2603.02138](https://arxiv.org/abs/2603.02138) +- **MMLottie-2M Dataset:** [huggingface.co/datasets/OmniLottie/MMLottie-2M](https://huggingface.co/datasets/OmniLottie/MMLottie-2M) + +## Citation + +```bibtex +@misc{sivaramakrishna2026animtoon, + title={AnimTOON: Token-Efficient Vector Animation Generation via Compact Text Format}, + author={Siva RamaKrishna}, + year={2026}, + url={https://github.com/srk0102/AnimTOON} +} +``` + +## License + +MIT License - see [LICENSE](https://github.com/srk0102/AnimTOON/blob/master/LICENSE) diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..9840d40 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,54 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0]['role'] == 'system' %} + {{- messages[0]['content'] }} + {%- else %} + {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }} + {%- endif %} + {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0]['role'] == 'system' %} + {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }} + {%- else %} + {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- for message in messages %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %} + {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {{- '<|im_start|>' + message.role }} + {%- if message.content %} + {{- '\n' + message.content }} + {%- endif %} + {%- for tool_call in message.tool_calls %} + {%- if tool_call.function is defined %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {{- tool_call.arguments | tojson }} + {{- '}\n' }} + {%- endfor %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- message.content }} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} +{%- endif %} diff --git a/config.json b/config.json new file mode 100644 index 0000000..8d27bac --- /dev/null +++ b/config.json @@ -0,0 +1,69 @@ +{ + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dtype": "float16", + "eos_token_id": 151645, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 11008, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 70, + "model_type": "qwen2", + "num_attention_heads": 16, + "num_hidden_layers": 36, + "num_key_value_heads": 2, + "pad_token_id": null, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 1000000.0, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": true, + "transformers_version": "5.3.0", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..daedcce --- /dev/null +++ b/generation_config.json @@ -0,0 +1,14 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "repetition_penalty": 1.05, + "temperature": 0.7, + "top_k": 20, + "top_p": 0.8, + "transformers_version": "5.3.0" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..676eb04 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e021ad2795299db080811ec567dbec9605db16c21a86a28b0cac9ea4cbdf53e +size 6171926680 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..34510ff --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8 +size 11421892 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..a8f5ccb --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,29 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "is_local": true, + "model_max_length": 131072, + "pad_token": "<|endoftext|>", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +}