--- title: P-H3-Image-ComfyUI-GGUF canonical_url: "https://www.modelscope.cn/models/vantagewithai/P-H3-Image-ComfyUI-GGUF" md_url: "https://www.modelscope.cn/models/vantagewithai/P-H3-Image-ComfyUI-GGUF.md" repository: vantagewithai/P-H3-Image-ComfyUI-GGUF last_updated: 2026-11-12 license: other pipeline_tag: text-to-image-synthesis tasks: - text-to-image-synthesis base_model: - PrunaAI/p-h3-image base_model_relation: quantized library_name: - lora - gguf - pytorch frameworks: - pytorch language: - en downloads: 40 stars: 0 tags: - comfyui - diffusion-single-file - text-to-image - image-to-image - image-generation - image-editing - prompt-upsampling - lora - int8 - 4-bit - minimax-h3 - pruna-ai - gguf --- # P-H3-Image-ComfyUI-GGUF > P-H3-Image-ComfyUI-GGUF - vantagewithai 在 ModelScope 开源的模型。GGUF Quants of P-H3-Image for ComfyUI. vantagewithai/P-H3-Image-ComfyUI-GGUF 是 ModelScope 魔搭社区上的text-to-image-synthesis模型，采用 other 许可，基于 PrunaAI/p-h3-image 构建。 - **Repository**: vantagewithai/P-H3-Image-ComfyUI-GGUF - **License**: other - **Tasks**: text-to-image-synthesis - **Base model**: PrunaAI/p-h3-image - **Tags**: comfyui, diffusion-single-file, text-to-image, image-to-image, image-generation, image-editing, prompt-upsampling, lora, int8, 4-bit, minimax-h3, pruna-ai, gguf - **Downloads**: 40 - **Stars**: 0 - **Last updated**: 2026-11-12 Source: https://www.modelscope.cn/models/vantagewithai/P-H3-Image-ComfyUI-GGUF --- **GGUF Quants of P-H3-Image for ComfyUI.** **Original model repository:** [https://huggingface.co/PrunaAI/P-H3-Image-Comfy](https://huggingface.co/PrunaAI/P-H3-Image-Comfy) **Watch us on Youtube:** [@VantageWithAI](https://www.youtube.com/@vantagewithai)

P-H3-Image

ComfyUI files for P-H3-Image, based on MiniMax-H3

This repository holds the ComfyUI GGUF quants files for **P-H3-Image**, an image model for text-to-image generation and image editing based on [MiniMax-H3](https://huggingface.co/MiniMaxAI/MiniMax-H3). It renders 8-megapixel images in 8 steps without CFG and edits with up to 8 input images. Every component comes in bf16 and in ComfyUI's native int8 and 4-bit formats. The smallest set is a 20 GB download that peaks at 21 GB of VRAM at 8 MP, against 143 GB of weights for MiniMax-H3. Text-to-image works best at 8 MP. In the workflows, Resolution Selector at 8 megapixels and a multiple of 32 gives these sizes. Edits work best at 4 or 8 MP. In the edit workflows, Scale Image to Total Pixels brings `image_1`, the image being edited, to 4 MP, and p-h3-image Conditioning generates the edit at its size unless `width` and `height` are set. Reference images above about 8 MP are scaled down. ## Prompt upsampler P-H3-Image is sensitive to prompting and renders full, specific prompts much better than short requests. The prompt upsampler, based on Qwen3.5-9B, turns a one-line request into that prompt, and all example workflows use it. It thinks about the request first and then writes the prompt. It runs on ComfyUI's own nodes, the way FLUX.3 Klein's templates run theirs: Load CLIP (type `minimax`) and Generate Text, with greedy decoding, so a request always gives the same prompt. - **Text-to-image.** Format Text turns the request into the upsampler's input, `Aspect ratio: 1:1` and `Request: ...` on two lines, and Generate Text runs with `thinking` on. Keep the aspect ratio the same as in Resolution Selector. - **Edits.** Format Text writes the upsampler's input with a `` block for every image, and the images reach Generate Text through Batch Images: `image_1` at 1 MP, the references padded to its size. The result is the edit prompt for p-h3-image Conditioning. - **Use prompt upsampler**, an If/Else switch, set to false sends the request to the model as it is. The upsampler runs before P-H3-Image, and ComfyUI moves it out of VRAM when P-H3-Image needs the memory. Its output is cached, so it only runs again when the request or the images change. | Upsampler file | Size | Peak VRAM | Time per prompt, L40S | |---|:---:|:---:|:---:| | `p-h3-image_prompt_upsampler_bf16` (recommended) | 19.3 GB | about 21 GB | about 7 s | | `p-h3-image_prompt_upsampler_int8_convrot` | 9.7 GB | about 12 GB | about 13 s | | `p-h3-image_prompt_upsampler_w4a8` | 6.7 GB | about 9 GB | about 11 s | The w4a8 prompts differ most from bf16. Use the smaller files only when 21 GB does not fit. ## Editing Connect the image to edit as `image_1` and up to 7 references after it, in the same order in Batch Images and on p-h3-image Conditioning, with a `` block in Upsampler input for every image. The request can name the images however you like, such as "the hat from the second photo".

*Top, eight public-domain portraits and the dinner party P-H3-Image composed from them, from a one-sentence request. Bottom, eight scientists at a poker table, seven presidents wading through the swamp with an astronaut, and characters from our own renders in the same swamp.* ## Already have MiniMax-H3? If you run MiniMax-H3 in ComfyUI, the 2 GB LoRA `loras/p-h3-image_lora_bf16.safetensors` runs P-H3-Image on its FL2VA transformer without a second large download. Load `minimax_h3_fl2va_bf16.safetensors` from [Comfy-Org/MiniMax-H3](https://huggingface.co/Comfy-Org/MiniMax-H3) (the pruned and quantized FL2VA files work too), apply the LoRA with Load LoRA (Bypass, Model Only) at strength 1.0, and start from the `lora` workflows. ## Limitations - **It is sensitive to prompting.** Keep the prompt upsampler in the graph. Hype words and very long prompts make images worse, and very short prompts give weak results without it. - **Hands can break, and small people in the background can come out distorted.** Rendering at 8 MP helps. - **Text is not fully reliable.** Small or dense text turns into pseudo-text, and longer passages sometimes get single letters wrong. Short quoted strings render well. - **Quantized files are not identical to bf16.** int8 stays very close, w4a8 changes more of the details. ## License The P-H3-Image weights are based on MiniMax-H3 and released under the [MiniMax H3 Community License](LICENSE). Please read it before use. Among other terms, it excludes the European Union, the United Kingdom, the Republic of Korea and the United States unless you have a separate license from MiniMax, and products built on it must show "Powered by MiniMax H3". The text encoder's Qwen3-VL-4B parts and the prompt upsampler, based on Qwen3.5-9B, are under the [Apache License 2.0](LICENSE-APACHE). See [NOTICE](NOTICE) for details.