| --- |
| license: mit |
| license_name: tencent-hunyuan-community |
| license_link: LICENSE |
| datasets: |
| - trojblue/test-HunyuanVideo-anime-images |
| - calcuis/anime-descriptor |
| language: |
| - en |
| base_model: |
| - tencent/HunyuanVideo |
| - trojblue/HunyuanVideo-lora-AnimeShots |
| pipeline_tag: text-to-video |
| tags: |
| - hyvid |
| - lora |
| - gguf-comfy |
| - gguf-node |
| widget: |
| - text: >- |
| anime style anime girl with massive fennec ears and one big fluffy tail, she |
| has blonde long hair blue eyes wearing a maid outfit with a long black gold |
| leaf pattern dress, walking slowly to the front with sweetie smile, holding |
| a fancy black forest cake with candles on top in the kitchen of an old dark |
| Victorian mansion lit by candlelight with a bright window to the foggy |
| output: |
| url: samples\ComfyUI_00007_.webp |
| - text: >- |
| anime scene of a vibrant carnival with colorful rides, games, and food |
| stalls, and a cute anime girl with multicolored hair, holding a melting |
| ice-cream, wearing a fluffy white hoodie and blue mini shorts, winking her |
| eye, smiling to the camera |
| output: |
| url: samples\ComfyUI_00002_.webp |
| - text: >- |
| anime girl with pink twin tails and green eyes, wearing a school uniform, |
| holding a stack of books in a bustling library filled with sunlight |
| streaming through tall windows |
| output: |
| url: samples\ComfyUI_00001_.webp |
| - text: >- |
| anime boy with silver hair and blue eyes, wearing a casual hoodie, sitting |
| on a park bench, feeding pigeons with a gentle smile |
| output: |
| url: samples\ComfyUI_00003_.webp |
| - text: >- |
| anime style anime girl with massive fennec ears and one big fluffy tail, she |
| has blonde long hair blue eyes wearing a maid outfit with a long black gold |
| leaf pattern dress, walking slowly to the front with sweetie smile, holding |
| a fancy black forest cake with candles on top in the kitchen of an old dark |
| Victorian mansion lit by candlelight with a bright window to the foggy |
| forest |
| output: |
| url: samples\ComfyUI_00004_.webp |
| - text: >- |
| anime style anime girl with massive fennec ears and one big fluffy tail, she |
| has blonde hair long hair blue eyes wearing a pink sweater and a long blue |
| skirt walking in a beautiful outdoor scenery with snow mountains in the |
| background |
| output: |
| url: samples\ComfyUI_00005_.webp |
| --- |
| |
| # **GGUF quantized and fp8 scaled version of hyvid with lora anime adapter** |
|
|
| <Gallery /> |
|
|
|  |
|
|
| ## **setup (once)** |
| - drag hyvid_lora_adapter.safetensors [[323MB](https://huggingface.co/calcuis/hyvid/blob/main/hyvid_lora_adapter.safetensors)] to > ./ComfyUI/models/loras |
| - drag hunyuan-video-t2v-720p-q4_0.gguf [[7.74GB](https://huggingface.co/calcuis/hyvid/blob/main/hunyuan-video-t2v-720p-q4_0.gguf)] to > ./ComfyUI/models/diffusion_models |
| - drag llava_llama3-q4_0.gguf [[4.68GB](https://huggingface.co/calcuis/hyvid/blob/main/llava_llama3-q4_0.gguf)] to > ./ComfyUI/models/text_encoders |
| - drag clip_l_fp8_e4m3fn.safetensors [[123MB](https://huggingface.co/calcuis/hyvid/blob/main/clip_l_fp8_e4m3fn.safetensors)] to > ./ComfyUI/models/text_encoders |
| - drag hunyuan_video_vae_fp8_e4m3fn.safetensors [[247MB](https://huggingface.co/calcuis/hyvid/blob/main/hunyuan_video_vae_fp8_e4m3fn.safetensors)] to > ./ComfyUI/models/vae |
| |
| ## **run it straight (no installation needed way)** |
| - run the .bat file in the main directory (assuming you are using the gguf-node pack below) |
| - drag the demo [clip](https://huggingface.co/calcuis/hyvid/blob/main/samples%5CComfyUI_00007_.webp) or the workflow json file (below) to > your browser |
| |
| ### **workflows** |
| - example workflow for [gguf](https://huggingface.co/calcuis/hyvid/blob/main/workflow-hyvid-gguf.json) (upgrade your [node](https://github.com/calcuis/gguf) for llava gguf support; more quantized llava-llama3 version [here](https://huggingface.co/chatpig/llava-llama3/tree/main)) |
| - example workflow for [safetensors](https://huggingface.co/calcuis/hyvid/blob/main/workflow-hyvid-safetensors.json) (fp8 scaled version [[13.2GB](https://huggingface.co/calcuis/hyvid/blob/main/hunyuan_video_t2v_720_fp8_scaled.safetensors)] is recommended) |
| |
| ### **review** |
| - more stable output if adapter applied |
| - working good even with fp8_e4m3fn scaled clip and vae |
| - significant changes in loading speed while using the new quantized/scaled file(s) with revised workflow (see above) |
|
|
| ### **references** |
| - lora adapter from [trojblue](https://huggingface.co/trojblue/HunyuanVideo-lora-AnimeShots) |
| - base model from [tencent](https://huggingface.co/tencent/HunyuanVideo) |
| - fast model from [fastvideo](https://huggingface.co/FastVideo/FastHunyuan) |
| - comfyui from [comfyanonymous](https://github.com/comfyanonymous/ComfyUI) |
| - comfyui-gguf [city96](https://github.com/city96/ComfyUI-GGUF) |
| - gguf-comfy [pack](https://github.com/calcuis/gguf-comfy/releases) |
| - gguf-node ([pypi](https://pypi.org/project/gguf-node)|[repo](https://github.com/calcuis/gguf)|[pack](https://github.com/calcuis/gguf/releases)) |
|
|
| ### **appendices** |
| - get more test prompt from the training [dataset](https://huggingface.co/datasets/calcuis/anime-descriptor) |
| - still no ideas? get fresh prompt from our [simulator](https://prompt.calcuis.us) |
