Instructions to use wikeeyang/Magic-Wan-T2IV-V3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use wikeeyang/Magic-Wan-T2IV-V3 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("wikeeyang/Magic-Wan-T2IV-V3", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
This is High version or low version?
This is High version or low version?
This is High version or low version?
It's not a simple choice between High or Low. If want to add some LoRA, it is recommended to use Low version.
i am getting black image as output what might be the issue
The workflow looks fine. If you can provide the log for me to take a look, I can help you analyze it and guess the possible reasons. You might need to upgrade the Comfy core. You can try to see if the GGUF format can run normally. If GGUF works but fp8mixed does not, then it can basically be determined that Comfy needs to be upgraded.
Wan2_1_VAE.safetensors
can i get link of this VAE decoder
'π₯ - 13 Nodes not included in prompt but is activated'
Failed to validate prompt for output 227:
- VAELoader 228:
- Value not in list: vae_name: 'Wan2_1_VAE.safetensors' not in ['BerrysMix.vae.safetensors', 'ae.safetensors', 'flux2-vae.safetensors', 'kl-f8-anime2.ckpt', 'sdxl_vae.safetensors', 'stage_a.safetensors', 'vae-ft-mse-840000-ema-pruned.ckpt', 'wan_2.1_vae.safetensors']
Output will be ignored
invalid prompt: {'type': 'prompt_outputs_failed_validation', 'message': 'Prompt outputs failed validation', 'details': '', 'extra_info': {}}
- Value not in list: vae_name: 'Wan2_1_VAE.safetensors' not in ['BerrysMix.vae.safetensors', 'ae.safetensors', 'flux2-vae.safetensors', 'kl-f8-anime2.ckpt', 'sdxl_vae.safetensors', 'stage_a.safetensors', 'vae-ft-mse-840000-ema-pruned.ckpt', 'wan_2.1_vae.safetensors']
i am getting black image as output what might be the issue
The workflow looks fine. If you can provide the log for me to take a look, I can help you analyze it and guess the possible reasons. You might need to upgrade the Comfy core. You can try to see if the GGUF format can run normally. If GGUF works but fp8mixed does not, then it can basically be determined that Comfy needs to be upgraded.
'π₯ - 12 Nodes not included in prompt but is activated'
Requested to load WAN21
loaded completely 14488.710500817871 13626.337951660156 True
100%|ββββββββββ| 25/25 [01:15<00:00, 3.02s/it]
Requested to load WanVAE
loaded completely 330.8902282714844 242.02829551696777 True
/home/ComfyUI/nodes.py:1585: RuntimeWarning: invalid value encountered in cast
img = Image.fromarray(np.clip(i, 0, 255).astype(np.uint8))
Prompt executed in 91.66 seconds
Wan2_1_VAE.safetensors
can i get link of this VAE decoder
you can download it from ComfyUI offical repo: https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/vae/wan_2.1_vae.safetensors
