DarthAffe/stable-diffusion.cpp
1
0
Fork 0
mirror of https://github.com/leejet/stable-diffusion.cpp.git synced 2025-12-13 05:48:56 +00:00
Code Issues Packages Projects Releases Wiki Activity

update docs

Browse Source
This commit is contained in:
leejet 2025-09-06 18:03:07 +08:00
parent 29c61c8c29
commit 125acc845f
14 changed files with 191 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

68
README.md
View File

@ -4,19 +4,33 @@
# stable-diffusion.cpp
Inference of Stable Diffusion and Flux in pure C/C++
Diffusion model(SD,Flux,Wan,...) inference in pure C/C++
***Note that this project is under active development. \
API and command-line parameters may change frequently.***
## Features
- Plain C/C++ implementation based on [ggml](https://github.com/ggerganov/ggml), working in the same way as [llama.cpp](https://github.com/ggerganov/llama.cpp)
- Super lightweight and without external dependencies
- SD1.x, SD2.x, SDXL and [SD3/SD3.5](./docs/sd3.md) support
- !!!The VAE in SDXL encounters NaN issues under FP16, but unfortunately, the ggml_conv_2d only operates under FP16. Hence, a parameter is needed to specify the VAE that has fixed the FP16 NaN issue. You can find it here: [SDXL VAE FP16 Fix](https://huggingface.co/madebyollin/sdxl-vae-fp16-fix/blob/main/sdxl_vae.safetensors).
- [Flux-dev/Flux-schnell Support](./docs/flux.md)
- [FLUX.1-Kontext-dev](./docs/kontext.md)
- [Chroma](./docs/chroma.md)
- [SD-Turbo](https://huggingface.co/stabilityai/sd-turbo) and [SDXL-Turbo](https://huggingface.co/stabilityai/sdxl-turbo) support
- [PhotoMaker](https://github.com/TencentARC/PhotoMaker) support.
- Supported models
- Image Models
- SD1.x, SD2.x, [SD-Turbo](https://huggingface.co/stabilityai/sd-turbo)
- SDXL, [SDXL-Turbo](https://huggingface.co/stabilityai/sdxl-turbo)
- !!!The VAE in SDXL encounters NaN issues under FP16, but unfortunately, the ggml_conv_2d only operates under FP16. Hence, a parameter is needed to specify the VAE that has fixed the FP16 NaN issue. You can find it here: [SDXL VAE FP16 Fix](https://huggingface.co/madebyollin/sdxl-vae-fp16-fix/blob/main/sdxl_vae.safetensors).
- [SD3/SD3.5](./docs/sd3.md)
- [Flux-dev/Flux-schnell](./docs/flux.md)
- [Chroma](./docs/chroma.md)
- Image Edit Models
- [FLUX.1-Kontext-dev](./docs/kontext.md)
- Video Models
- [Wan2.1/Wan2.2](./docs/wan.md)
- [PhotoMaker](https://github.com/TencentARC/PhotoMaker) support.
- Control Net support with SD 1.5
- LoRA support, same as [stable-diffusion-webui](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Features#lora)
- Latent Consistency Models support (LCM/LCM-LoRA)
- Faster and memory efficient latent decoding with [TAESD](https://github.com/madebyollin/taesd)
- Upscale images generated with [ESRGAN](https://github.com/xinntao/Real-ESRGAN)
- 16-bit, 32-bit float support
- 2-bit, 3-bit, 4-bit, 5-bit and 8-bit integer quantization support
- Accelerated memory-efficient CPU inference
@ -26,15 +40,9 @@ Inference of Stable Diffusion and Flux in pure C/C++
- Can load ckpt, safetensors and diffusers models/checkpoints. Standalone VAEs models
- No need to convert to `.ggml` or `.gguf` anymore!
- Flash Attention for memory usage optimization
- Original `txt2img` and `img2img` mode
- Negative prompt
- [stable-diffusion-webui](https://github.com/AUTOMATIC1111/stable-diffusion-webui) style tokenizer (not all the features, only token weighting for now)
- LoRA support, same as [stable-diffusion-webui](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Features#lora)
- Latent Consistency Models support (LCM/LCM-LoRA)
- Faster and memory efficient latent decoding with [TAESD](https://github.com/madebyollin/taesd)
- Upscale images generated with [ESRGAN](https://github.com/xinntao/Real-ESRGAN)
- VAE tiling processing for reduce memory usage
- Control Net support with SD 1.5
- Sampling method
- `Euler A`
- `Euler`
@ -287,8 +295,10 @@ arguments:
If threads <= 0, then threads will be set to the number of CPU physical cores
-m, --model [MODEL] path to full model
--diffusion-model path to the standalone diffusion model
--high-noise-diffusion-model path to the standalone high noise diffusion model
--clip_l path to the clip-l text encoder
--clip_g path to the clip-g text encoder
--clip_vision path to the clip-vision encoder
--t5xxl path to the t5xxl text encoder
--vae [VAE] path to vae
--taesd [TAESD_PATH] path to taesd. Using Tiny AutoEncoder for fast decoding (low quality)
@ -303,8 +313,9 @@ arguments:
If not specified, the default is the type of the weight file
--tensor-type-rules [EXPRESSION] weight type per tensor pattern (example: "^vae\.=f16,model\.=q8_0")
--lora-model-dir [DIR] lora model directory
-i, --init-img [IMAGE] path to the input image, required by img2img
-i, --init-img [IMAGE] path to the init image, required by img2img
--mask [MASK] path to the mask image, required by img2img with mask
-i, --end-img [IMAGE] path to the end image, required by flf2v
--control-image [IMAGE] path to image condition, control net
-r, --ref-image [PATH] reference image for Flux Kontext models (can be used multiple times)
-o, --output OUTPUT path to write result image to (default: ./output.png)
@ -319,6 +330,23 @@ arguments:
--skip-layers LAYERS Layers to skip for SLG steps: (default: [7,8,9])
--skip-layer-start START SLG enabling point: (default: 0.01)
--skip-layer-end END SLG disabling point: (default: 0.2)
--scheduler {discrete, karras, exponential, ays, gits} Denoiser sigma scheduler (default: discrete)
--sampling-method {euler, euler_a, heun, dpm2, dpm++2s_a, dpm++2m, dpm++2mv2, ipndm, ipndm_v, lcm, ddim_trailing, tcd}
sampling method (default: "euler_a")
--steps STEPS number of sample steps (default: 20)
--high-noise-cfg-scale SCALE (high noise) unconditional guidance scale: (default: 7.0)
--high-noise-img-cfg-scale SCALE (high noise) image guidance scale for inpaint or instruct-pix2pix models: (default: same as --cfg-scale)
--high-noise-guidance SCALE (high noise) distilled guidance scale for models with guidance input (default: 3.5)
--high-noise-slg-scale SCALE (high noise) skip layer guidance (SLG) scale, only for DiT models: (default: 0)
0 means disabled, a value of 2.5 is nice for sd3.5 medium
--high-noise-eta SCALE (high noise) eta in DDIM, only for DDIM and TCD: (default: 0)
--high-noise-skip-layers LAYERS (high noise) Layers to skip for SLG steps: (default: [7,8,9])
--high-noise-skip-layer-start (high noise) SLG enabling point: (default: 0.01)
--high-noise-skip-layer-end END (high noise) SLG disabling point: (default: 0.2)
--high-noise-scheduler {discrete, karras, exponential, ays, gits} Denoiser sigma scheduler (default: discrete)
--high-noise-sampling-method {euler, euler_a, heun, dpm2, dpm++2s_a, dpm++2m, dpm++2mv2, ipndm, ipndm_v, lcm, ddim_trailing, tcd}
(high noise) sampling method (default: "euler_a")
--high-noise-steps STEPS (high noise) number of sample steps (default: 20)
SLG will be enabled at step int([STEPS]*[START]) and disabled at int([STEPS]*[END])
--strength STRENGTH strength for noising/unnoising (default: 0.75)
--style-ratio STYLE-RATIO strength for keeping input identity (default: 20)
@ -326,14 +354,10 @@ arguments:
1.0 corresponds to full destruction of information in init image
-H, --height H image height, in pixel space (default: 512)
-W, --width W image width, in pixel space (default: 512)
--sampling-method {euler, euler_a, heun, dpm2, dpm++2s_a, dpm++2m, dpm++2mv2, ipndm, ipndm_v, lcm, ddim_trailing, tcd}
sampling method (default: "euler_a")
--steps STEPS number of sample steps (default: 20)
--rng {std_default, cuda} RNG (default: cuda)
-s SEED, --seed SEED RNG seed (default: 42, use random seed for < 0)
-b, --batch-count COUNT number of images to generate
--scheduler {discrete, karras, exponential, ays, gits} Denoiser sigma scheduler (default: discrete)
--clip-skip N ignore last layers of CLIP network; 1 ignores none, 2 ignores one layer (default: -1)
--clip-skip N ignore last_dot_pos layers of CLIP network; 1 ignores none, 2 ignores one layer (default: -1)
<= 0 represents unspecified, will be 1 for SD1.x, 2 for SD2.x
--vae-tiling process vae in tiles to reduce memory usage
--vae-on-cpu keep vae in cpu (for low vram)
@ -351,6 +375,8 @@ arguments:
--chroma-disable-dit-mask disable dit mask for chroma
--chroma-enable-t5-mask enable t5 mask for chroma
--chroma-t5-mask-pad PAD_SIZE t5 mask pad size of chroma
--video-frames video frames (default: 1)
--fps fps (default: 24)
-v, --verbose print extra info
```
@ -438,3 +464,5 @@ Thank you to all the people who have already contributed to stable-diffusion.cpp
- [latent-consistency-model](https://github.com/luosiallen/latent-consistency-model)
- [generative-models](https://github.com/Stability-AI/generative-models/)
- [PhotoMaker](https://github.com/TencentARC/PhotoMaker)
- [Wan2.1](https://github.com/Wan-Video/Wan2.1)
- [Wan2.2](https://github.com/Wan-Video/Wan2.2)

BIN
assets/wan/Wan2.1_1.3B_t2v.mp4 Normal file
View File

Binary file not shown.

BIN
assets/wan/Wan2.1_14B_flf2v.mp4 Normal file
View File

Binary file not shown.

BIN
assets/wan/Wan2.1_14B_i2v.mp4 Normal file
View File

Binary file not shown.

BIN
assets/wan/Wan2.1_14B_t2v.mp4 Normal file
View File

Binary file not shown.

BIN
assets/wan/Wan2.2_14B_flf2v.mp4 Normal file
View File

Binary file not shown.

BIN
assets/wan/Wan2.2_14B_i2v.mp4 Normal file
View File

Binary file not shown.

BIN
assets/wan/Wan2.2_14B_t2i.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 594 KiB

BIN
assets/wan/Wan2.2_14B_t2v.mp4 Normal file
View File

Binary file not shown.

BIN
assets/wan/Wan2.2_14B_t2v_lora.mp4 Normal file
View File

Binary file not shown.

BIN
assets/wan/Wan2.2_5B_i2v.mp4 Normal file
View File

Binary file not shown.

BIN
assets/wan/Wan2.2_5B_t2v.mp4 Normal file
View File

Binary file not shown.

141
docs/wan.md Normal file
View File

@ -0,0 +1,141 @@
# How to Use
## Download weights
- Download Wan
- Wan2.1
- Wan2.1 T2V 1.3B
- safetensors: https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/tree/main/split_files/diffusion_models
- Wan2.1 T2V 14B
- safetensors: https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/tree/main/split_files/diffusion_models
- gguf: https://huggingface.co/city96/Wan2.1-T2V-14B-gguf/tree/main
- Wan2.1 I2V 14B 480P
- safetensors: https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/tree/main/split_files/diffusion_models
- gguf: https://huggingface.co/city96/Wan2.1-I2V-14B-480P-gguf/tree/main
- Wan2.1 I2V 14B 720P
- safetensors: https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/tree/main/split_files/diffusion_models
- gguf: https://huggingface.co/city96/Wan2.1-I2V-14B-720P-gguf/tree/main
- Wan2.1 FLF2V 14B 720P
- safetensors: https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/tree/main/split_files/diffusion_models
- gguf: https://huggingface.co/city96/Wan2.1-FLF2V-14B-720P-gguf/tree/main
- Wan2.2
- Wan2.2 TI2V 5B
- safetensors: https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/tree/main/split_files/diffusion_models
- gguf: https://huggingface.co/QuantStack/Wan2.2-TI2V-5B-GGUF/tree/main
- Wan2.2 T2V A14B
- safetensors: https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/tree/main/split_files/diffusion_models
- gguf: https://huggingface.co/QuantStack/Wan2.2-T2V-A14B-GGUF/tree/main
- Wan2.2 I2V A14B
- safetensors: https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/tree/main/split_files/diffusion_models
- gguf: https://huggingface.co/QuantStack/Wan2.2-I2V-A14B-GGUF/tree/main
- Download vae
- wan_2.1_vae (for all the wan model except Wan2.2 TI2V 5B)
- safetensors: https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/blob/main/split_files/vae/wan_2.1_vae.safetensors
- wan_2.2_vae (for Wan2.2 TI2V 5B only)
- safetensors: https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/blob/main/split_files/vae/wan2.2_vae.safetensors
- Download umt5_xxl
- safetensors: https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/blob/main/split_files/text_encoders/umt5_xxl_fp16.safetensors
- gguf: https://huggingface.co/city96/umt5-xxl-encoder-gguf/tree/main
- Download clip_vison_h (for Wan2.1 I2V/FLF2V only)
- safetensors: https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/blob/main/split_files/clip_vision/clip_vision_h.safetensors
## Examples
Since GitHub does not support AVI files, the file I uploaded was converted from AVI to MP4.
### Wan2.1 T2V 1.3B
```
.\bin\Release\sd.exe -M vid_gen --diffusion-model ..\..\ComfyUI\models\diffusion_models\wan2.1_t2v_1.3B_fp16.safetensors --vae ..\..\ComfyUI\models\vae\wan_2.1_vae.safetensors --t5xxl ..\..\ComfyUI\models\text_encoders\umt5-xxl-encoder-Q8_0.gguf -p "a lovely cat" --cfg-scale 6.0 --sampling-method euler -v -n "色调艳丽，过曝，静态，细节模糊不清，字幕，风格，作品，画作，画面，静止，整体发灰，最差质量，低质量，JPEG压缩残留，丑陋的，残缺的，多余的手指，画得不好的手部，画得不好的脸部， 畸形的，毁容的，形态畸形的肢体，手指融合，静止不动的画面，杂乱的背景，三条腿，背景人很多，倒着走" -W 832 -H 480 --diffusion-fa --video-frames 33
```
<video src=../assets/wan/Wan2.1_1.3B_t2v.mp4 controls="controls" muted="muted" type="video/mp4"></video>
### Wan2.1 T2V 14B
```
.\bin\Release\sd.exe -M vid_gen --diffusion-model ..\..\ComfyUI\models\diffusion_models\wan2.1-t2v-14b-Q8_0.gguf --vae ..\..\ComfyUI\models\vae\wan_2.1_vae.safetensors --t5xxl ..\..\ComfyUI\models\text_encoders\umt5-xxl-encoder-Q8_0.gguf -p "a lovely cat" --cfg-scale 6.0 --sampling-method euler -v -n "色调艳丽，过曝，静态，细节模糊不清，字幕，风格，作品，画作，画面，静止，整体发灰，最差质量，低质量，JPEG压缩残留，丑陋的，残缺的，多余的手指，画得不好的手部，画得不好的脸部，畸形的，毁容的，形态畸形的肢体，手指融合，静止不动的画面，杂乱的背景，三条腿，背景人很多，倒着走" -W 832 -H 480 --diffusion-fa --offload-to-cpu --video-frames 33
```
<video src=../assets/wan/Wan2.1_14B_t2v.mp4 controls="controls" muted="muted" type="video/mp4"></video>
### Wan2.1 I2V 14B
```
.\bin\Release\sd.exe -M vid_gen --diffusion-model ..\..\ComfyUI\models\diffusion_models\wan2.1-i2v-14b-480p-Q8_0.gguf --vae ..\..\ComfyUI\models\vae\wan_2.1_vae.safetensors --t5xxl ..\..\ComfyUI\models\text_encoders\umt5-xxl-encoder-Q8_0.gguf --clip_vision ..\..\ComfyUI\models\clip_vision\clip_vision_h.safetensors -p "a lovely cat" --cfg-scale 6.0 --sampling-method euler -v -n "色调艳丽，过曝，静态，细节模糊不清，字幕，风格，作品，画作，画面，静止，整体发灰，最差质量，低质量，JPEG压缩残留，丑陋的，残缺的，多余的手指，画得不好的手部，画得不好的脸部，畸形的，毁容的，形态畸形的肢体，手指融合，静止不动的画面，杂乱的背景，三条腿，背景人很多，倒着走" -W 480 -H 832 --diffusion-fa --video-frames 33 --offload-to-cpu -i ..\assets\cat_with_sd_cpp_42.png
```
<video src=../assets/wan/Wan2.1_14B_i2v.mp4 controls="controls" muted="muted" type="video/mp4"></video>
### Wan2.2 T2V A14B
```
.\bin\Release\sd.exe -M vid_gen --diffusion-model ..\..\ComfyUI\models\diffusion_models\Wan2.2-T2V-A14B-LowNoise-Q8_0.gguf --high-noise-diffusion-model ..\..\ComfyUI\models\diffusion_models\Wan2.2-T2V-A14B-HighNoise-Q8_0.gguf --vae ..\..\ComfyUI\models\vae\wan_2.1_vae.safetensors --t5xxl ..\..\ComfyUI\models\text_encoders\umt5-xxl-encoder-Q8_0.gguf -p "a lovely cat" --cfg-scale 3.5 --sampling-method euler --steps 10 --high-noise-cfg-scale 3.5 --high-noise-sampling-method euler --high-noise-steps 8 -v -n "色调艳丽，过曝，静态，细节模糊不清，字幕，风格，作品，画作，画面，静止，整体发灰，最差质量，低质量，JPEG压缩残留，丑陋的，残缺的，多余的手指，画得不好的手部，画得不好的脸部，畸形的，毁容的，形态畸形的肢体，手指融合，静止不动的画面，杂乱的背景，三条腿，背景人很多，倒着走" -W 832 -H 480 --diffusion-fa --offload-to-cpu --video-frames 33
```
<video src=../assets/wan/Wan2.2_14B_t2v.mp4 controls="controls" muted="muted" type="video/mp4"></video>
### Wan2.2 I2V A14B
```
.\bin\Release\sd.exe -M vid_gen --diffusion-model ..\..\ComfyUI\models\diffusion_models\Wan2.2-I2V-A14B-LowNoise-Q8_0.gguf --high-noise-diffusion-model ..\..\ComfyUI\models\diffusion_models\Wan2.2-I2V-A14B-HighNoise-Q8_0.gguf --vae ..\..\ComfyUI\models\vae\wan_2.1_vae.safetensors --t5xxl ..\..\ComfyUI\models\text_encoders\umt5-xxl-encoder-Q8_0.gguf -p "a lovely cat" --cfg-scale 3.5 --sampling-method euler --steps 10 --high-noise-cfg-scale 3.5 --high-noise-sampling-method euler --high-noise-steps 8 -v -n "色调艳丽，过曝，静态，细节模糊不清，字幕，风格，作品，画作，画面，静止，整体发灰，最差质量，低质量，JPEG压缩残留，丑陋的，残缺的，多余的手指，画得不好的手部，画得不好的脸部，畸形的，毁容的，形态畸形的肢体，手指融合，静止不动的画面，杂乱的背景，三条腿，背景人很多，倒着走" -W 832 -H 480 --diffusion-fa --offload-to-cpu --video-frames 33 --offload-to-cpu -i ..\assets\cat_with_sd_cpp_42.png
```
<video src=../assets/wan/Wan2.2_14B_i2v.mp4 controls="controls" muted="muted" type="video/mp4"></video>
### Wan2.2 T2V A14B T2I
```
.\bin\Release\sd.exe -M vid_gen --diffusion-model ..\..\ComfyUI\models\diffusion_models\Wan2.2-T2V-A14B-LowNoise-Q8_0.gguf --high-noise-diffusion-model ..\..\ComfyUI\models\diffusion_models\Wan2.2-T2V-A14B-HighNoise-Q8_0.gguf --vae ..\..\ComfyUI\models\vae\wan_2.1_vae.safetensors --t5xxl ..\..\ComfyUI\models\text_encoders\umt5-xxl-encoder-Q8_0.gguf -p "a lovely cat" --cfg-scale 3.5 --sampling-method euler --steps 10 --high-noise-cfg-scale 3.5 --high-noise-sampling-method euler --high-noise-steps 8 -v -n "色调艳丽，过曝，静态，细节模糊不清，字幕，风格，作品，画作，画面，静止，整体发灰，最差质量，低质量，JPEG压缩残留，丑陋的，残缺的，多余的手指，画得不好的手部，画得不好的脸部，畸形的，毁容的，形态畸形的肢体，手指融合，静止不动的画面，杂乱的背景，三条腿，背景人很多，倒着走" -W 832 -H 480 --diffusion-fa --offload-to-cpu
```
<img width="832" height="480" alt="Wan2 2_14B_t2i" src="../assets/wan/Wan2.2_14B_t2i.png" />
### Wan2.2 T2V 14B with Lora
```
.\bin\Release\sd.exe -M vid_gen --diffusion-model ..\..\ComfyUI\models\diffusion_models\Wan2.2-T2V-A14B-LowNoise-Q8_0.gguf --high-noise-diffusion-model ..\..\ComfyUI\models\diffusion_models\Wan2.2-T2V-A14B-HighNoise-Q8_0.gguf --vae ..\..\ComfyUI\models\vae\wan_2.1_vae.safetensors --t5xxl ..\..\ComfyUI\models\text_encoders\umt5-xxl-encoder-Q8_0.gguf -p "a lovely cat<lora:wan2.2_t2v_lightx2v_4steps_lora_v1.1_low_noise:1><lora:|high_noise|wan2.2_t2v_lightx2v_4steps_lora_v1.1_high_noise:1>" --cfg-scale 3.5 --sampling-method euler --steps 4 --high-noise-cfg-scale 3.5 --high-noise-sampling-method euler --high-noise-steps 4 -v -n "色调艳丽，过曝，静态，细节模糊不清，字幕，风格，作品，画作，画面，静止，整体发灰，最差质量，低质量，JPEG压缩残留，丑陋的，残缺的，多余的手指，画得不好的手部，画得不好的脸部，畸形的，毁容的，形态畸形的肢体，手指融合，静止不动的画面，杂乱的背景，三条腿，背景人很多，倒着走" -W 832 -H 480 --diffusion-fa --offload-to-cpu --lora-model-dir ..\..\ComfyUI\models\loras --video-frames 33
```
<video src=../assets/wan/Wan2.2_14B_t2v_lora.mp4 controls="controls" muted="muted" type="video/mp4"></video>
### Wan2.2 TI2V 5B
#### T2V
```
.\bin\Release\sd.exe -M vid_gen --diffusion-model ..\..\ComfyUI\models\diffusion_models\wan2.2_ti2v_5B_fp16.safetensors --vae ..\..\ComfyUI\models\vae\wan2.2_vae.safetensors --t5xxl ..\..\ComfyUI\models\text_encoders\umt5-xxl-encoder-Q8_0.gguf -p "a lovely cat" --cfg-scale 6.0 --sampling-method euler -v -n "色调艳丽，过曝，静态，细节模糊不清，字幕，风格，作品，画作，画面，静止，整体发灰，最差质量，低质量，JPEG压缩残留，丑陋的，残缺的，多余的手指，画得不好的手部，画得不好的脸部，畸形的，毁容的，形态畸形的肢体，手指融合，静止不动的画面，杂乱的背景，三条腿，背景人很多，倒着走" -W 480 -H 832 --diffusion-fa --offload-to-cpu --video-frames 33
```
<video src=../assets/wan/Wan2.2_5B_t2v.mp4 controls="controls" muted="muted" type="video/mp4"></video>
#### I2V
```
.\bin\Release\sd.exe -M vid_gen --diffusion-model ..\..\ComfyUI\models\diffusion_models\wan2.2_ti2v_5B_fp16.safetensors --vae ..\..\ComfyUI\models\vae\wan2.2_vae.safetensors --t5xxl ..\..\ComfyUI\models\text_encoders\umt5-xxl-encoder-Q8_0.gguf -p "a lovely cat" --cfg-scale 6.0 --sampling-method euler -v -n "色调艳丽，过曝，静态，细节模糊不清，字幕，风格，作品，画作，画面，静止，整体发灰，最差质量，低质量，JPEG压缩残留，丑陋的，残缺的，多余的手指，画得不好的手部，画得不好的脸部，畸形的，毁容的，形态畸形的肢体，手指融合，静止不动的画面，杂乱的背景，三条腿，背景人很多，倒着走" -W 480 -H 832 --diffusion-fa --offload-to-cpu --video-frames 33 -i ..\assets\cat_with_sd_cpp_42.png
```
<video src=../assets/wan/Wan2.2_5B_i2v.mp4 controls="controls" muted="muted" type="video/mp4"></video>
### Wan2.1 FLF2V 14B
```
.\bin\Release\sd.exe -M vid_gen --diffusion-model ..\..\ComfyUI\models\diffusion_models\wan2.1-flf2v-14b-720p-Q8_0.gguf --vae ..\..\ComfyUI\models\vae\wan_2.1_vae.safetensors --t5xxl ..\..\ComfyUI\models\text_encoders\umt5-xxl-encoder-Q8_0.gguf --clip_vision ..\..\ComfyUI\models\clip_vision\clip_vision_h.safetensors -p "glass flower blossom" --cfg-scale 6.0 --sampling-method euler -v -n "色调艳丽，过曝，静态，细节模糊不清，字幕，风格，作品，画作，画面，静止，整体发灰，最差质量，低质量，JPEG压缩残留，丑陋的，残缺的，多余的手指，画得不好的手部，画得不好的脸部，畸形的，毁容的，形态畸形的肢体，手指融合，静止不动的画面，杂乱的背景，三条腿，背景人很多，倒着走" -W 480 -H 832 --diffusion-fa --video-frames 33 --offload-to-cpu --init-img ..\..\ComfyUI\input\start_image.png --end-img ..\..\ComfyUI\input\end_image.png
```
<video src=../assets/wan/Wan2.1_14B_flf2v.mp4 controls="controls" muted="muted" type="video/mp4"></video>
### Wan2.2 FLF2V 14B
```
.\bin\Release\sd.exe -M vid_gen --diffusion-model ..\..\ComfyUI\models\diffusion_models\Wan2.2-I2V-A14B-LowNoise-Q8_0.gguf --high-noise-diffusion-model ..\..\ComfyUI\models\diffusion_models\Wan2.2-I2V-A14B-HighNoise-Q8_0.gguf --vae ..\..\ComfyUI\models\vae\wan_2.1_vae.safetensors --t5xxl ..\..\ComfyUI\models\text_encoders\umt5-xxl-encoder-Q8_0.gguf --cfg-scale 3.5 --sampling-method euler --steps 10 --high-noise-cfg-scale 3.5 --high-noise-sampling-method euler --high-noise-steps 8 -v -p "glass flower blossom" -n "色调艳丽，过曝，静态，细节模糊不清，字幕，风格，作品，画作，画面，静止，整体发灰，最差质量，低质量，JPEG压缩残留，丑陋的，残缺的，多余的手指，画得不好的手部，画得不好的脸部，畸形的，毁容的，形态畸形的肢体，手指融合，静止不动的画面，杂乱的背景，三条腿，背景人很多，倒着走" -W 480 -H 832 --diffusion-fa --video-frames 33 --offload-to-cpu --init-img ..\..\ComfyUI\input\start_image.png --end-img ..\..\ComfyUI\input\end_image.png
```
<video src=../assets/wan/Wan2.2_14B_flf2v.mp4 controls="controls" muted="muted" type="video/mp4"></video>

4
examples/cli/main.cpp
View File

@ -262,9 +262,9 @@ void print_usage(int argc, const char* argv[]) {
printf(" --diffusion-fa use flash attention in the diffusion model (for low vram)\n");
printf(" Might lower quality, since it implies converting k and v to f16.\n");
printf(" This might crash if it is not supported by the backend.\n");
printf(" --diffusion-conv-direct use Conv2d direct in the diffusion model");
printf(" --diffusion-conv-direct use Conv2d direct in the diffusion model\n");
printf(" This might crash if it is not supported by the backend.\n");
printf(" --vae-conv-direct use Conv2d direct in the vae model (should improve the performance)");
printf(" --vae-conv-direct use Conv2d direct in the vae model (should improve the performance)\n");
printf(" This might crash if it is not supported by the backend.\n");
printf(" --control-net-cpu keep controlnet in cpu (for low vram)\n");
printf(" --canny apply canny preprocessor (edge detection)\n");