Compare commits

..

No commits in common. "5dc18879670c618a6e12ff9f713ee4666d39791f" and "3002c55d2d7cc5a58da8f1a9b34f302fc2d85a08" have entirely different histories.

4 changed files with 1 additions and 22 deletions

View File

@ -49,7 +49,6 @@ API and command-line option may change frequently.***
- [Chroma1-Radiance](./docs/chroma_radiance.md)
- [Qwen Image](./docs/qwen_image.md)
- [Z-Image](./docs/z_image.md)
- [Ovis-Image](./docs/ovis_image.md)
- Image Edit Models
- [FLUX.1-Kontext-dev](./docs/kontext.md)
- [Qwen Image Edit/Qwen Image Edit 2509](./docs/qwen_image_edit.md)
@ -135,7 +134,6 @@ If you want to improve performance or reduce VRAM/RAM usage, please refer to [pe
- [🔥Qwen Image Edit/Qwen Image Edit 2509](./docs/qwen_image_edit.md)
- [🔥Wan2.1/Wan2.2](./docs/wan.md)
- [🔥Z-Image](./docs/z_image.md)
- [Ovis-Image](./docs/ovis_image.md)
- [LoRA](./docs/lora.md)
- [LCM/LCM-LoRA](./docs/lcm.md)
- [Using PhotoMaker to personalize image generation](./docs/photo_maker.md)

Binary file not shown.

Before

Width:  |  Height:  |  Size: 401 KiB

View File

@ -1,19 +0,0 @@
# How to Use
## Download weights
- Download Ovis-Image-7B
- safetensors: https://huggingface.co/Comfy-Org/Ovis-Image/tree/main/split_files/diffusion_models
- gguf: https://huggingface.co/leejet/Ovis-Image-7B-GGUF
- Download vae
- safetensors: https://huggingface.co/black-forest-labs/FLUX.1-schnell/tree/main
- Download Ovis 2.5
- safetensors: https://huggingface.co/Comfy-Org/Ovis-Image/tree/main/split_files/text_encoders
## Examples
```
.\bin\Release\sd.exe --diffusion-model ovis_image-Q4_0.gguf --vae ..\..\ComfyUI\models\vae\ae.sft --llm ..\..\ComfyUI\models\text_encoders\ovis_2.5.safetensors -p "a lovely cat" --cfg-scale 5.0 -v --offload-to-cpu --diffusion-fa
```
<img alt="ovis image example" src="../assets/ovis_image/example.png" />

View File

@ -1124,7 +1124,7 @@ namespace LLM {
params.intermediate_size = pair.second.ne[1];
}
}
if (arch == LLMArch::QWEN3 && params.num_layers == 28) { // Qwen3 2B
if (params.num_layers == 28) { // Qwen3 2B
params.num_heads = 16;
}
LOG_DEBUG("llm: num_layers = %" PRId64 ", vocab_size = %" PRId64 ", hidden_size = %" PRId64 ", intermediate_size = %" PRId64,