Edit a picture in plain words or make a new one from scratch. For an edit, you can give P-H3 up to seven more pictures and tell it what to take from each one.
<h3>How to use it</h3>
<ol>
<li>Drop the workflow into ComfyUI. Load the picture you want to change and write your edit.</li>
<li>For a reference, connect an image loader to picture 2 on Write the prompt. Add more in order through picture 8. Name the picture in your request, for example “Give the person in picture 1 the jacket from picture 2.”</li>
<li>Press Run. Drag the comparison slider to check what changed. Auto prompt shows the expanded request in Show Text.</li>
<li>To generate from words, turn Edit a picture off and choose a size in Latent Size. Turn Upscale the result on if you want SeedVR2 to double the width and height.</li>
</ol>
<h3>What you need</h3>
Update ComfyUI and <a target="_blank" href="https://github.com/ausboss/ComfyUI-AusBoss" rel="ugc">AusBoss nodes</a> first. This version ran on ComfyUI 0.44.0 with AusBoss nodes 2.20.5. Pick one matching model and text encoder pair. The workflow opens on Low VRAM.
<ul>
<li>Low VRAM · <a target="_blank" href="https://huggingface.co/PrunaAI/P-H3-Image-Comfy/resolve/main/diffusion_models/p-h3-image_w4a8.safetensors" rel="ugc">p-h3-image_w4a8.safetensors</a> → <code>models/diffusion_models</code> · 13.4 GB</li>
<li>Low VRAM · <a target="_blank" href="https://huggingface.co/PrunaAI/P-H3-Image-Comfy/resolve/main/text_encoders/p-h3-image_text_encoder_w4a8.safetensors" rel="ugc">p-h3-image_text_encoder_w4a8.safetensors</a> → <code>models/text_encoders</code> · 3.6 GB</li>
<li>High VRAM · <a target="_blank" href="https://huggingface.co/PrunaAI/P-H3-Image-Comfy/resolve/main/diffusion_models/p-h3-image_int8_convrot.safetensors" rel="ugc">p-h3-image_int8_convrot.safetensors</a> → <code>models/diffusion_models</code> · 21.2 GB</li>
<li>High VRAM · <a target="_blank" href="https://huggingface.co/PrunaAI/P-H3-Image-Comfy/resolve/main/text_encoders/p-h3-image_text_encoder_int8_convrot.safetensors" rel="ugc">p-h3-image_text_encoder_int8_convrot.safetensors</a> → <code>models/text_encoders</code> · 5.1 GB</li>
<li>Both · <a target="_blank" href="https://huggingface.co/PrunaAI/P-H3-Image-Comfy/resolve/main/vae/p-h3-image_vae_int8_convrot.safetensors" rel="ugc">p-h3-image_vae_int8_convrot.safetensors</a> → <code>models/vae</code> · 3.1 GB</li>
<li>Auto prompt · <a target="_blank" href="https://huggingface.co/PrunaAI/P-H3-Image-Comfy/resolve/main/text_encoders/p-h3-image_prompt_upsampler_bf16.safetensors" rel="ugc">p-h3-image_prompt_upsampler_bf16.safetensors</a> → <code>models/text_encoders</code> · 19.3 GB</li>
<li>2× upscale · <a target="_blank" href="https://huggingface.co/Comfy-Org/SeedVR2/resolve/main/diffusion_models/seedvr2_3b_int8_convrot.safetensors" rel="ugc">seedvr2_3b_int8_convrot.safetensors</a> → <code>models/diffusion_models</code> · 3.46 GB</li>
<li>2× upscale · <a target="_blank" href="https://huggingface.co/Comfy-Org/SeedVR2/resolve/main/vae/seedvr2_ema_vae_fp16.safetensors" rel="ugc">seedvr2_ema_vae_fp16.safetensors</a> → <code>models/vae</code> · 501 MB</li>
</ul>
<h3>Tips</h3>
<ul>
<li>With Auto prompt off, say what should stay the same as well as what you want to change.</li>
<li>Check faces, lighting and the background after a multi-picture edit. The model can change more than you asked for.</li>
<li>Edits start at 4 megapixels. The Resize row on the picture loader sets that size.</li>
</ul>
Powered by MiniMax H3. P-H3-Image is by Pruna AI and uses the <a target="_blank" href="https://huggingface.co/PrunaAI/P-H3-Image-Comfy/blob/main/LICENSE" rel="ugc">MiniMax H3 Community License</a>. Optional upscaling uses <a target="_blank" href="https://huggingface.co/Comfy-Org/SeedVR2" rel="ugc">SeedVR2</a> under Apache 2.0.
v1.0 (2026-11-06) · First release.
<a target="_blank" href="https://github.com/ausboss/ComfyUI-AusBoss/issues" rel="ugc">Report an issue</a> · <a target="_blank" href="https://discord.gg/RwVxY9Fuaj" rel="ugc">Discord</a> · <a target="_blank" href="https://www.youtube.com/@ausbossdev" rel="ugc">YouTube @ausbossdev</a> · <a target="_blank" href="https://x.com/Zanzibased" rel="ugc">X @Zanzibased</a> · <a target="_blank" href="https://github.com/ausboss" rel="ugc">GitHub</a>

P-H3-Image Generate + Edit | 8 Pictures + Auto Prompt

First release. Tested with ComfyUI 0.44.0 and AusBoss nodes 2.20.5 on both VRAM settings.

Files with SHA256: 31dd654751b3df66b04c85a4aaa4b0b3a9530b7fe6b75b03672ca74cd9b1f13c